From 834d07312e0cd9308e7e20fe5f814a5756238ada Mon Sep 17 00:00:00 2001 From: XuehaoSun Date: Sat, 14 Sep 2024 10:15:13 +0000 Subject: [PATCH] deploy: 24458114c0765e177b3f4dfbb73d7cfda6b196ab --- .../algorithms/weight_only/autoround/index.rst.txt | 2 +- .../algorithms/weight_only/save_load/index.rst.txt | 8 +++++++- .../torch/quantization/config/index.rst.txt | 2 +- .../neural_compressor/adaptor/mxnet_utils/index.html | 2 +- .../adaptor/mxnet_utils/util/index.html | 2 +- .../adaptor/ox_utils/calibration/index.html | 2 +- .../adaptor/ox_utils/calibrator/index.html | 2 +- .../neural_compressor/adaptor/ox_utils/index.html | 2 +- .../adaptor/ox_utils/operators/activation/index.html | 2 +- .../adaptor/ox_utils/operators/argmax/index.html | 2 +- .../adaptor/ox_utils/operators/attention/index.html | 2 +- .../adaptor/ox_utils/operators/binary_op/index.html | 2 +- .../adaptor/ox_utils/operators/concat/index.html | 2 +- .../adaptor/ox_utils/operators/conv/index.html | 2 +- .../adaptor/ox_utils/operators/direct_q8/index.html | 2 +- .../ox_utils/operators/embed_layernorm/index.html | 2 +- .../adaptor/ox_utils/operators/gather/index.html | 2 +- .../adaptor/ox_utils/operators/gavgpool/index.html | 2 +- .../adaptor/ox_utils/operators/gemm/index.html | 2 +- .../adaptor/ox_utils/operators/index.html | 2 +- .../adaptor/ox_utils/operators/lstm/index.html | 2 +- .../adaptor/ox_utils/operators/matmul/index.html | 2 +- .../adaptor/ox_utils/operators/maxpool/index.html | 2 +- .../adaptor/ox_utils/operators/norm/index.html | 2 +- .../adaptor/ox_utils/operators/ops/index.html | 2 +- .../adaptor/ox_utils/operators/pad/index.html | 2 +- .../adaptor/ox_utils/operators/pooling/index.html | 2 +- .../adaptor/ox_utils/operators/reduce/index.html | 2 +- .../adaptor/ox_utils/operators/resize/index.html | 2 +- .../adaptor/ox_utils/operators/split/index.html | 2 +- .../adaptor/ox_utils/operators/unary_op/index.html | 2 +- .../adaptor/ox_utils/quantizer/index.html | 2 +- .../adaptor/ox_utils/smooth_quant/index.html | 2 +- .../adaptor/ox_utils/util/index.html | 2 +- .../adaptor/ox_utils/weight_only/index.html | 2 +- .../neural_compressor/adaptor/tensorflow/index.html | 2 +- .../adaptor/tf_utils/graph_converter/index.html | 2 +- .../tf_utils/graph_converter_without_calib/index.html | 2 +- .../graph_rewriter/bf16/bf16_convert/index.html | 2 +- .../bf16/dequantize_cast_optimizer/index.html | 2 +- .../adaptor/tf_utils/graph_rewriter/bf16/index.html | 2 +- .../generic/convert_add_to_biasadd/index.html | 2 +- .../graph_rewriter/generic/convert_layout/index.html | 2 +- .../generic/convert_leakyrelu/index.html | 2 +- .../generic/convert_nan_to_random/index.html | 2 +- .../generic/convert_placeholder_to_const/index.html | 2 +- .../generic/dilated_contraction/index.html | 2 +- .../graph_rewriter/generic/dummy_biasadd/index.html | 2 +- .../generic/expanddims_optimizer/index.html | 2 +- .../generic/fetch_weight_from_reshape/index.html | 2 +- .../graph_rewriter/generic/fold_batch_norm/index.html | 2 +- .../graph_rewriter/generic/fold_constant/index.html | 2 +- .../generic/fuse_biasadd_add/index.html | 2 +- .../generic/fuse_column_wise_mul/index.html | 2 +- .../generic/fuse_conv_with_math/index.html | 2 +- .../generic/fuse_decomposed_bn/index.html | 2 +- .../generic/fuse_decomposed_in/index.html | 2 +- .../graph_rewriter/generic/fuse_gelu/index.html | 2 +- .../graph_rewriter/generic/fuse_layer_norm/index.html | 2 +- .../generic/fuse_pad_with_conv/index.html | 2 +- .../generic/fuse_pad_with_fp32_conv/index.html | 2 +- .../generic/fuse_reshape_transpose/index.html | 2 +- .../generic/graph_cse_optimizer/index.html | 2 +- .../graph_rewriter/generic/grappler_pass/index.html | 2 +- .../tf_utils/graph_rewriter/generic/index.html | 2 +- .../generic/insert_print_node/index.html | 2 +- .../generic/move_squeeze_after_relu/index.html | 2 +- .../graph_rewriter/generic/pre_optimize/index.html | 2 +- .../generic/remove_training_nodes/index.html | 2 +- .../generic/rename_batch_norm/index.html | 2 +- .../generic/split_shared_input/index.html | 2 +- .../generic/strip_equivalent_nodes/index.html | 2 +- .../generic/strip_unused_nodes/index.html | 2 +- .../generic/switch_optimizer/index.html | 2 +- .../tf_utils/graph_rewriter/graph_base/index.html | 2 +- .../adaptor/tf_utils/graph_rewriter/index.html | 2 +- .../graph_rewriter/int8/freeze_fake_quant/index.html | 2 +- .../graph_rewriter/int8/freeze_value/index.html | 2 +- .../int8/freeze_value_without_calib/index.html | 2 +- .../int8/fuse_conv_redundant_dequantize/index.html | 2 +- .../int8/fuse_conv_requantize/index.html | 2 +- .../int8/fuse_matmul_redundant_dequantize/index.html | 2 +- .../int8/fuse_matmul_requantize/index.html | 2 +- .../adaptor/tf_utils/graph_rewriter/int8/index.html | 2 +- .../graph_rewriter/int8/meta_op_optimizer/index.html | 2 +- .../int8/post_hostconst_converter/index.html | 2 +- .../int8/post_quantized_op_cse/index.html | 2 +- .../graph_rewriter/int8/rnn_convert/index.html | 2 +- .../graph_rewriter/int8/scale_propagation/index.html | 2 +- .../adaptor/tf_utils/graph_rewriter/onnx/index.html | 2 +- .../graph_rewriter/onnx/onnx_graph/index.html | 2 +- .../tf_utils/graph_rewriter/onnx/onnx_node/index.html | 2 +- .../graph_rewriter/onnx/onnx_schema/index.html | 2 +- .../graph_rewriter/onnx/tf2onnx_utils/index.html | 2 +- .../adaptor/tf_utils/graph_rewriter/qdq/index.html | 2 +- .../graph_rewriter/qdq/insert_qdq_pattern/index.html | 2 +- .../qdq/merge_duplicated_qdq/index.html | 2 +- .../graph_rewriter/qdq/share_qdq_y_pattern/index.html | 2 +- .../adaptor/tf_utils/graph_util/index.html | 2 +- .../neural_compressor/adaptor/tf_utils/index.html | 2 +- .../adaptor/tf_utils/quantize_graph/index.html | 2 +- .../quantize_graph/qat/fake_quantize/index.html | 2 +- .../adaptor/tf_utils/quantize_graph/qat/index.html | 2 +- .../quantize_graph/qat/quantize_config/index.html | 2 +- .../quantize_graph/qat/quantize_helper/index.html | 2 +- .../quantize_graph/qat/quantize_layers/index.html | 2 +- .../qat/quantize_layers/optimize_layer/index.html | 2 +- .../qat/quantize_layers/quantize_layer_add/index.html | 2 +- .../quantize_layers/quantize_layer_base/index.html | 2 +- .../qat/quantize_layers/quantize_layer_bn/index.html | 2 +- .../quantize_graph/qat/quantize_wrapper/index.html | 2 +- .../quantize_graph/qdq/fuse_qdq_bn/index.html | 2 +- .../quantize_graph/qdq/fuse_qdq_concatv2/index.html | 2 +- .../quantize_graph/qdq/fuse_qdq_conv/index.html | 2 +- .../quantize_graph/qdq/fuse_qdq_deconv/index.html | 2 +- .../quantize_graph/qdq/fuse_qdq_in/index.html | 2 +- .../quantize_graph/qdq/fuse_qdq_matmul/index.html | 2 +- .../quantize_graph/qdq/fuse_qdq_pooling/index.html | 2 +- .../adaptor/tf_utils/quantize_graph/qdq/index.html | 2 +- .../quantize_graph/qdq/optimize_qdq/index.html | 2 +- .../quantize_graph/quantize_graph_base/index.html | 2 +- .../quantize_graph/quantize_graph_bn/index.html | 2 +- .../quantize_graph/quantize_graph_concatv2/index.html | 2 +- .../quantize_graph/quantize_graph_conv/index.html | 2 +- .../quantize_graph_for_intel_cpu/index.html | 2 +- .../quantize_graph/quantize_graph_matmul/index.html | 2 +- .../quantize_graph/quantize_graph_pooling/index.html | 2 +- .../adaptor/tf_utils/quantize_graph_common/index.html | 2 +- .../tf_utils/smooth_quant_calibration/index.html | 2 +- .../adaptor/tf_utils/smooth_quant_scaler/index.html | 2 +- .../adaptor/tf_utils/tf2onnx_converter/index.html | 2 +- .../transform_graph/bias_correction/index.html | 2 +- .../transform_graph/graph_transform_base/index.html | 2 +- .../adaptor/tf_utils/transform_graph/index.html | 2 +- .../transform_graph/insert_logging/index.html | 2 +- .../rerange_quantized_concat/index.html | 2 +- .../adaptor/tf_utils/util/index.html | 2 +- .../adaptor/torch_utils/bf16_convert/index.html | 2 +- .../adaptor/torch_utils/hawq_metric/index.html | 2 +- .../neural_compressor/adaptor/torch_utils/index.html | 2 +- .../adaptor/torch_utils/layer_wise_quant/index.html | 2 +- .../layer_wise_quant/modified_pickle/index.html | 2 +- .../torch_utils/layer_wise_quant/quantize/index.html | 2 +- .../layer_wise_quant/torch_load/index.html | 2 +- .../torch_utils/layer_wise_quant/utils/index.html | 2 +- .../adaptor/torch_utils/model_wrapper/index.html | 2 +- .../adaptor/torch_utils/pattern_detector/index.html | 2 +- .../adaptor/torch_utils/symbolic_trace/index.html | 2 +- .../adaptor/torch_utils/util/index.html | 2 +- .../neural_compressor/algorithm/algorithm/index.html | 2 +- .../algorithm/fast_bias_correction/index.html | 2 +- latest/autoapi/neural_compressor/algorithm/index.html | 2 +- .../algorithm/smooth_quant/index.html | 2 +- .../algorithm/weight_correction/index.html | 2 +- latest/autoapi/neural_compressor/benchmark/index.html | 2 +- .../neural_compressor/common/base_config/index.html | 2 +- .../neural_compressor/common/base_tuning/index.html | 2 +- .../neural_compressor/common/benchmark/index.html | 2 +- latest/autoapi/neural_compressor/common/index.html | 2 +- .../neural_compressor/common/tuning_param/index.html | 2 +- .../common/utils/constants/index.html | 2 +- .../autoapi/neural_compressor/common/utils/index.html | 2 +- .../neural_compressor/common/utils/logger/index.html | 2 +- .../common/utils/save_load/index.html | 2 +- .../neural_compressor/common/utils/utility/index.html | 2 +- .../compression/callbacks/index.html | 2 +- .../compression/distillation/criterions/index.html | 2 +- .../compression/distillation/index.html | 2 +- .../compression/distillation/optimizers/index.html | 2 +- .../compression/distillation/utility/index.html | 2 +- .../neural_compressor/compression/hpo/index.html | 2 +- .../compression/hpo/sa_optimizer/index.html | 2 +- .../compression/pruner/criteria/index.html | 2 +- .../neural_compressor/compression/pruner/index.html | 2 +- .../pruner/model_slim/auto_slim/index.html | 2 +- .../compression/pruner/model_slim/index.html | 2 +- .../pruner/model_slim/pattern_analyzer/index.html | 2 +- .../pruner/model_slim/weight_slim/index.html | 2 +- .../compression/pruner/patterns/base/index.html | 2 +- .../compression/pruner/patterns/index.html | 2 +- .../compression/pruner/patterns/mha/index.html | 2 +- .../compression/pruner/patterns/ninm/index.html | 2 +- .../compression/pruner/patterns/nxm/index.html | 2 +- .../compression/pruner/pruners/base/index.html | 2 +- .../compression/pruner/pruners/basic/index.html | 2 +- .../compression/pruner/pruners/block_mask/index.html | 2 +- .../compression/pruner/pruners/index.html | 2 +- .../compression/pruner/pruners/mha/index.html | 2 +- .../pruner/pruners/pattern_lock/index.html | 2 +- .../compression/pruner/pruners/progressive/index.html | 2 +- .../pruner/pruners/retrain_free/index.html | 2 +- .../compression/pruner/pruning/index.html | 2 +- .../compression/pruner/regs/index.html | 2 +- .../compression/pruner/schedulers/index.html | 2 +- .../compression/pruner/tf_criteria/index.html | 2 +- .../compression/pruner/utils/index.html | 2 +- .../compression/pruner/wanda/index.html | 2 +- .../compression/pruner/wanda/utils/index.html | 2 +- latest/autoapi/neural_compressor/config/index.html | 2 +- latest/autoapi/neural_compressor/contrib/index.html | 2 +- .../neural_compressor/contrib/strategy/index.html | 2 +- .../contrib/strategy/sigopt/index.html | 2 +- .../neural_compressor/contrib/strategy/tpe/index.html | 2 +- .../data/dataloaders/base_dataloader/index.html | 2 +- .../data/dataloaders/dataloader/index.html | 2 +- .../data/dataloaders/default_dataloader/index.html | 2 +- .../data/dataloaders/fetcher/index.html | 2 +- .../data/dataloaders/mxnet_dataloader/index.html | 2 +- .../data/dataloaders/onnxrt_dataloader/index.html | 2 +- .../data/dataloaders/pytorch_dataloader/index.html | 2 +- .../data/dataloaders/sampler/index.html | 2 +- .../data/dataloaders/tensorflow_dataloader/index.html | 2 +- .../data/datasets/bert_dataset/index.html | 2 +- .../data/datasets/coco_dataset/index.html | 2 +- .../data/datasets/dataset/index.html | 2 +- .../data/datasets/dummy_dataset/index.html | 2 +- .../data/datasets/dummy_dataset_v2/index.html | 2 +- .../data/datasets/imagenet_dataset/index.html | 2 +- .../neural_compressor/data/datasets/index.html | 2 +- .../data/datasets/style_transfer_dataset/index.html | 2 +- .../data/filters/coco_filter/index.html | 2 +- .../neural_compressor/data/filters/filter/index.html | 2 +- .../autoapi/neural_compressor/data/filters/index.html | 2 +- latest/autoapi/neural_compressor/data/index.html | 2 +- .../data/transforms/imagenet_transform/index.html | 2 +- .../neural_compressor/data/transforms/index.html | 2 +- .../data/transforms/postprocess/index.html | 2 +- .../data/transforms/tokenization/index.html | 2 +- .../data/transforms/transform/index.html | 2 +- latest/autoapi/neural_compressor/index.html | 2 +- .../autoapi/neural_compressor/metric/bleu/index.html | 2 +- .../neural_compressor/metric/bleu_util/index.html | 2 +- .../metric/coco_label_map/index.html | 2 +- .../neural_compressor/metric/coco_tools/index.html | 2 +- .../metric/evaluate_squad/index.html | 2 +- latest/autoapi/neural_compressor/metric/f1/index.html | 2 +- latest/autoapi/neural_compressor/metric/index.html | 2 +- .../neural_compressor/metric/metric/index.html | 2 +- .../neural_compressor/mix_precision/index.html | 2 +- .../neural_compressor/model/base_model/index.html | 2 +- latest/autoapi/neural_compressor/model/index.html | 2 +- .../neural_compressor/model/keras_model/index.html | 2 +- .../autoapi/neural_compressor/model/model/index.html | 2 +- .../neural_compressor/model/mxnet_model/index.html | 2 +- .../neural_compressor/model/nets_factory/index.html | 2 +- .../neural_compressor/model/onnx_model/index.html | 2 +- .../model/tensorflow_model/index.html | 2 +- .../neural_compressor/model/torch_model/index.html | 2 +- latest/autoapi/neural_compressor/objective/index.html | 2 +- latest/autoapi/neural_compressor/profiling/index.html | 2 +- .../profiling/parser/factory/index.html | 2 +- .../profiling/parser/onnx_parser/factory/index.html | 2 +- .../profiling/parser/onnx_parser/parser/index.html | 2 +- .../profiling/parser/parser/index.html | 2 +- .../profiling/parser/result/index.html | 2 +- .../parser/tensorflow_parser/factory/index.html | 2 +- .../parser/tensorflow_parser/parser/index.html | 2 +- .../profiling/profiler/factory/index.html | 2 +- .../profiler/onnxrt_profiler/factory/index.html | 2 +- .../profiler/onnxrt_profiler/profiler/index.html | 2 +- .../profiler/onnxrt_profiler/utils/index.html | 2 +- .../profiling/profiler/profiler/index.html | 2 +- .../profiler/tensorflow_profiler/factory/index.html | 2 +- .../profiler/tensorflow_profiler/profiler/index.html | 2 +- .../profiler/tensorflow_profiler/utils/index.html | 2 +- .../autoapi/neural_compressor/quantization/index.html | 2 +- .../neural_compressor/strategy/auto/index.html | 2 +- .../strategy/auto_mixed_precision/index.html | 2 +- .../neural_compressor/strategy/basic/index.html | 2 +- .../neural_compressor/strategy/bayesian/index.html | 2 +- .../strategy/conservative/index.html | 2 +- .../neural_compressor/strategy/exhaustive/index.html | 2 +- .../neural_compressor/strategy/hawq_v2/index.html | 2 +- latest/autoapi/neural_compressor/strategy/index.html | 2 +- .../autoapi/neural_compressor/strategy/mse/index.html | 2 +- .../neural_compressor/strategy/mse_v2/index.html | 2 +- .../neural_compressor/strategy/random/index.html | 2 +- .../neural_compressor/strategy/strategy/index.html | 2 +- .../strategy/utils/constant/index.html | 2 +- .../neural_compressor/strategy/utils/index.html | 2 +- .../strategy/utils/tuning_sampler/index.html | 2 +- .../strategy/utils/tuning_space/index.html | 2 +- .../strategy/utils/tuning_structs/index.html | 2 +- .../strategy/utils/utility/index.html | 2 +- .../template/api_doc_example/index.html | 2 +- .../tensorflow/algorithms/index.html | 2 +- .../algorithms/smoother/calibration/index.html | 2 +- .../tensorflow/algorithms/smoother/core/index.html | 2 +- .../tensorflow/algorithms/smoother/index.html | 2 +- .../tensorflow/algorithms/smoother/scaler/index.html | 2 +- .../tensorflow/algorithms/static_quant/index.html | 2 +- .../algorithms/static_quant/keras/index.html | 2 +- .../algorithms/static_quant/tensorflow/index.html | 2 +- .../autoapi/neural_compressor/tensorflow/index.html | 2 +- .../neural_compressor/tensorflow/keras/index.html | 2 +- .../tensorflow/keras/layers/conv2d/index.html | 2 +- .../tensorflow/keras/layers/dense/index.html | 2 +- .../keras/layers/depthwise_conv2d/index.html | 2 +- .../tensorflow/keras/layers/index.html | 2 +- .../keras/layers/layer_initializer/index.html | 2 +- .../tensorflow/keras/layers/pool2d/index.html | 2 +- .../keras/layers/separable_conv2d/index.html | 2 +- .../tensorflow/keras/quantization/config/index.html | 2 +- .../tensorflow/keras/quantization/index.html | 2 +- .../quantization/algorithm_entry/index.html | 2 +- .../tensorflow/quantization/autotune/index.html | 2 +- .../tensorflow/quantization/config/index.html | 2 +- .../tensorflow/quantization/index.html | 2 +- .../tensorflow/quantization/quantize/index.html | 2 +- .../quantization/utils/graph_converter/index.html | 2 +- .../utils/graph_rewriter/bf16/bf16_convert/index.html | 2 +- .../bf16/dequantize_cast_optimizer/index.html | 2 +- .../quantization/utils/graph_rewriter/bf16/index.html | 2 +- .../generic/convert_add_to_biasadd/index.html | 2 +- .../graph_rewriter/generic/convert_layout/index.html | 2 +- .../generic/convert_leakyrelu/index.html | 2 +- .../generic/convert_nan_to_random/index.html | 2 +- .../generic/convert_placeholder_to_const/index.html | 2 +- .../generic/dilated_contraction/index.html | 2 +- .../graph_rewriter/generic/dummy_biasadd/index.html | 2 +- .../generic/expanddims_optimizer/index.html | 2 +- .../generic/fetch_weight_from_reshape/index.html | 2 +- .../graph_rewriter/generic/fold_batch_norm/index.html | 2 +- .../graph_rewriter/generic/fold_constant/index.html | 2 +- .../generic/fuse_biasadd_add/index.html | 2 +- .../generic/fuse_column_wise_mul/index.html | 2 +- .../generic/fuse_conv_with_math/index.html | 2 +- .../generic/fuse_decomposed_bn/index.html | 2 +- .../generic/fuse_decomposed_in/index.html | 2 +- .../utils/graph_rewriter/generic/fuse_gelu/index.html | 2 +- .../graph_rewriter/generic/fuse_layer_norm/index.html | 2 +- .../generic/fuse_pad_with_conv/index.html | 2 +- .../generic/fuse_pad_with_fp32_conv/index.html | 2 +- .../generic/fuse_reshape_transpose/index.html | 2 +- .../generic/graph_cse_optimizer/index.html | 2 +- .../graph_rewriter/generic/grappler_pass/index.html | 2 +- .../utils/graph_rewriter/generic/index.html | 2 +- .../generic/insert_print_node/index.html | 2 +- .../generic/move_squeeze_after_relu/index.html | 2 +- .../graph_rewriter/generic/pre_optimize/index.html | 2 +- .../generic/remove_training_nodes/index.html | 2 +- .../generic/rename_batch_norm/index.html | 2 +- .../generic/split_shared_input/index.html | 2 +- .../generic/strip_equivalent_nodes/index.html | 2 +- .../generic/strip_unused_nodes/index.html | 2 +- .../generic/switch_optimizer/index.html | 2 +- .../utils/graph_rewriter/graph_base/index.html | 2 +- .../quantization/utils/graph_rewriter/index.html | 2 +- .../graph_rewriter/int8/freeze_fake_quant/index.html | 2 +- .../utils/graph_rewriter/int8/freeze_value/index.html | 2 +- .../int8/fuse_conv_redundant_dequantize/index.html | 2 +- .../int8/fuse_conv_requantize/index.html | 2 +- .../int8/fuse_matmul_redundant_dequantize/index.html | 2 +- .../int8/fuse_matmul_requantize/index.html | 2 +- .../quantization/utils/graph_rewriter/int8/index.html | 2 +- .../graph_rewriter/int8/meta_op_optimizer/index.html | 2 +- .../int8/post_hostconst_converter/index.html | 2 +- .../int8/post_quantized_op_cse/index.html | 2 +- .../graph_rewriter/int8/scale_propagation/index.html | 2 +- .../quantization/utils/graph_rewriter/qdq/index.html | 2 +- .../graph_rewriter/qdq/insert_qdq_pattern/index.html | 2 +- .../qdq/merge_duplicated_qdq/index.html | 2 +- .../graph_rewriter/qdq/share_qdq_y_pattern/index.html | 2 +- .../quantization/utils/graph_util/index.html | 2 +- .../tensorflow/quantization/utils/index.html | 2 +- .../quantization/utils/quantize_graph/index.html | 2 +- .../utils/quantize_graph/qdq/fuse_qdq_bn/index.html | 2 +- .../quantize_graph/qdq/fuse_qdq_concatv2/index.html | 2 +- .../utils/quantize_graph/qdq/fuse_qdq_conv/index.html | 2 +- .../quantize_graph/qdq/fuse_qdq_deconv/index.html | 2 +- .../utils/quantize_graph/qdq/fuse_qdq_in/index.html | 2 +- .../quantize_graph/qdq/fuse_qdq_matmul/index.html | 2 +- .../quantize_graph/qdq/fuse_qdq_pooling/index.html | 2 +- .../quantization/utils/quantize_graph/qdq/index.html | 2 +- .../utils/quantize_graph/qdq/optimize_qdq/index.html | 2 +- .../quantize_graph/quantize_graph_base/index.html | 2 +- .../utils/quantize_graph/quantize_graph_bn/index.html | 2 +- .../quantize_graph/quantize_graph_concatv2/index.html | 2 +- .../quantize_graph/quantize_graph_conv/index.html | 2 +- .../quantize_graph_for_intel_cpu/index.html | 2 +- .../quantize_graph/quantize_graph_matmul/index.html | 2 +- .../quantize_graph/quantize_graph_pooling/index.html | 2 +- .../utils/quantize_graph_common/index.html | 2 +- .../utils/transform_graph/bias_correction/index.html | 2 +- .../transform_graph/graph_transform_base/index.html | 2 +- .../quantization/utils/transform_graph/index.html | 2 +- .../utils/transform_graph/insert_logging/index.html | 2 +- .../rerange_quantized_concat/index.html | 2 +- .../tensorflow/quantization/utils/utility/index.html | 2 +- .../tensorflow/utils/constants/index.html | 2 +- .../tensorflow/utils/data/index.html | 2 +- .../neural_compressor/tensorflow/utils/index.html | 2 +- .../tensorflow/utils/model/index.html | 2 +- .../tensorflow/utils/model_wrappers/index.html | 2 +- .../tensorflow/utils/utility/index.html | 2 +- .../torch/algorithms/base_algorithm/index.html | 2 +- .../algorithms/fp8_quant/utils/logger/index.html | 2 +- .../neural_compressor/torch/algorithms/index.html | 2 +- .../torch/algorithms/layer_wise/index.html | 2 +- .../torch/algorithms/layer_wise/load/index.html | 2 +- .../algorithms/layer_wise/modified_pickle/index.html | 2 +- .../torch/algorithms/layer_wise/utils/index.html | 2 +- .../mixed_precision/half_precision_convert/index.html | 2 +- .../torch/algorithms/mixed_precision/index.html | 2 +- .../mixed_precision/module_wrappers/index.html | 2 +- .../torch/algorithms/mx_quant/index.html | 2 +- .../torch/algorithms/mx_quant/mx/index.html | 2 +- .../torch/algorithms/mx_quant/utils/index.html | 2 +- .../torch/algorithms/pt2e_quant/core/index.html | 2 +- .../pt2e_quant/half_precision_rewriter/index.html | 2 +- .../torch/algorithms/pt2e_quant/index.html | 2 +- .../torch/algorithms/pt2e_quant/save_load/index.html | 2 +- .../torch/algorithms/pt2e_quant/utility/index.html | 2 +- .../torch/algorithms/smooth_quant/index.html | 2 +- .../algorithms/smooth_quant/save_load/index.html | 2 +- .../algorithms/smooth_quant/smooth_quant/index.html | 2 +- .../torch/algorithms/smooth_quant/utility/index.html | 2 +- .../torch/algorithms/static_quant/index.html | 2 +- .../algorithms/static_quant/save_load/index.html | 2 +- .../algorithms/static_quant/static_quant/index.html | 2 +- .../torch/algorithms/static_quant/utility/index.html | 2 +- .../torch/algorithms/weight_only/autoround/index.html | 4 ++-- .../torch/algorithms/weight_only/awq/index.html | 2 +- .../torch/algorithms/weight_only/gptq/index.html | 2 +- .../algorithms/weight_only/hqq/bitpack/index.html | 2 +- .../algorithms/weight_only/hqq/config/index.html | 2 +- .../torch/algorithms/weight_only/hqq/core/index.html | 2 +- .../torch/algorithms/weight_only/hqq/index.html | 2 +- .../algorithms/weight_only/hqq/optimizer/index.html | 2 +- .../algorithms/weight_only/hqq/qtensor/index.html | 2 +- .../algorithms/weight_only/hqq/quantizer/index.html | 2 +- .../torch/algorithms/weight_only/index.html | 2 +- .../torch/algorithms/weight_only/modules/index.html | 2 +- .../torch/algorithms/weight_only/rtn/index.html | 2 +- .../torch/algorithms/weight_only/save_load/index.html | 11 ++++++++--- .../torch/algorithms/weight_only/teq/index.html | 2 +- .../torch/algorithms/weight_only/utility/index.html | 2 +- .../autoapi/neural_compressor/torch/export/index.html | 2 +- .../torch/export/pt2e_export/index.html | 2 +- latest/autoapi/neural_compressor/torch/index.html | 2 +- .../torch/quantization/algorithm_entry/index.html | 2 +- .../torch/quantization/autotune/index.html | 2 +- .../torch/quantization/config/index.html | 4 ++-- .../neural_compressor/torch/quantization/index.html | 2 +- .../torch/quantization/load_entry/index.html | 2 +- .../torch/quantization/quantize/index.html | 2 +- .../torch/utils/auto_accelerator/index.html | 2 +- .../torch/utils/constants/index.html | 2 +- .../neural_compressor/torch/utils/environ/index.html | 2 +- .../autoapi/neural_compressor/torch/utils/index.html | 2 +- .../neural_compressor/torch/utils/utility/index.html | 2 +- latest/autoapi/neural_compressor/training/index.html | 2 +- .../transformers/quantization/utils/index.html | 2 +- .../neural_compressor/transformers/utils/index.html | 2 +- .../transformers/utils/quantization_config/index.html | 2 +- .../utils/collect_layer_histogram/index.html | 2 +- .../neural_compressor/utils/constant/index.html | 2 +- .../utils/create_obj_from_config/index.html | 2 +- .../autoapi/neural_compressor/utils/export/index.html | 2 +- .../utils/export/qlinear2qdq/index.html | 2 +- .../neural_compressor/utils/export/tf2onnx/index.html | 2 +- .../utils/export/torch2onnx/index.html | 2 +- latest/autoapi/neural_compressor/utils/index.html | 2 +- .../neural_compressor/utils/kl_divergence/index.html | 2 +- .../utils/load_huggingface/index.html | 2 +- .../autoapi/neural_compressor/utils/logger/index.html | 2 +- .../neural_compressor/utils/options/index.html | 2 +- .../neural_compressor/utils/pytorch/index.html | 2 +- .../neural_compressor/utils/utility/index.html | 2 +- .../utils/weights_details/index.html | 2 +- latest/autoapi/neural_compressor/version/index.html | 2 +- latest/docs/build_docs/source/index.html | 2 +- latest/docs/source/2x_user_guide.html | 2 +- latest/docs/source/3x/PT_DynamicQuant.html | 2 +- latest/docs/source/3x/PT_FP8Quant.html | 2 +- latest/docs/source/3x/PT_MXQuant.html | 2 +- latest/docs/source/3x/PT_MixedPrecision.html | 2 +- latest/docs/source/3x/PT_SmoothQuant.html | 2 +- latest/docs/source/3x/PT_StaticQuant.html | 2 +- latest/docs/source/3x/PT_WeightOnlyQuant.html | 2 +- latest/docs/source/3x/PyTorch.html | 2 +- latest/docs/source/3x/TF_Quant.html | 2 +- latest/docs/source/3x/TF_SQ.html | 2 +- latest/docs/source/3x/TensorFlow.html | 2 +- latest/docs/source/3x/autotune.html | 2 +- latest/docs/source/3x/benchmark.html | 2 +- latest/docs/source/3x/client_quant.html | 2 +- latest/docs/source/3x/design.html | 2 +- latest/docs/source/3x/gaudi_version_map.html | 2 +- latest/docs/source/3x/llm_recipes.html | 2 +- latest/docs/source/3x/quantization.html | 2 +- latest/docs/source/CODE_OF_CONDUCT.html | 2 +- latest/docs/source/CONTRIBUTING.html | 2 +- latest/docs/source/FX.html | 2 +- latest/docs/source/SECURITY.html | 2 +- latest/docs/source/Welcome.html | 2 +- latest/docs/source/adaptor.html | 2 +- latest/docs/source/add_new_adaptor.html | 2 +- latest/docs/source/add_new_data_type.html | 2 +- latest/docs/source/api-doc/adaptor.html | 2 +- latest/docs/source/api-doc/adaptor/onnxrt.html | 2 +- latest/docs/source/api-doc/adaptor/torch_utils.html | 2 +- latest/docs/source/api-doc/api_2.html | 2 +- latest/docs/source/api-doc/api_3.html | 2 +- latest/docs/source/api-doc/api_doc_example.html | 2 +- latest/docs/source/api-doc/apis.html | 2 +- latest/docs/source/api-doc/benchmark.html | 2 +- latest/docs/source/api-doc/compression.html | 2 +- latest/docs/source/api-doc/config.html | 2 +- latest/docs/source/api-doc/mix_precision.html | 2 +- latest/docs/source/api-doc/model.html | 2 +- latest/docs/source/api-doc/objective.html | 2 +- latest/docs/source/api-doc/quantization.html | 2 +- latest/docs/source/api-doc/strategy.html | 2 +- .../docs/source/api-doc/tf_quantization_autotune.html | 2 +- .../docs/source/api-doc/tf_quantization_common.html | 2 +- .../docs/source/api-doc/tf_quantization_config.html | 2 +- .../source/api-doc/torch_quantization_autotune.html | 2 +- .../source/api-doc/torch_quantization_common.html | 2 +- .../source/api-doc/torch_quantization_config.html | 2 +- latest/docs/source/api-doc/training.html | 2 +- latest/docs/source/benchmark.html | 2 +- latest/docs/source/calibration.html | 2 +- latest/docs/source/coding_style.html | 2 +- latest/docs/source/dataloader.html | 2 +- latest/docs/source/design.html | 2 +- latest/docs/source/distillation_quantization.html | 2 +- latest/docs/source/distributed.html | 2 +- latest/docs/source/examples_readme.html | 2 +- latest/docs/source/export.html | 2 +- latest/docs/source/faq.html | 2 +- latest/docs/source/framework_yaml.html | 2 +- latest/docs/source/get_started.html | 2 +- latest/docs/source/incompatible_changes.html | 2 +- latest/docs/source/infrastructure.html | 2 +- latest/docs/source/installation_guide.html | 2 +- latest/docs/source/legal_information.html | 2 +- latest/docs/source/llm_recipes.html | 2 +- latest/docs/source/metric.html | 2 +- latest/docs/source/migration.html | 2 +- latest/docs/source/mixed_precision.html | 2 +- latest/docs/source/model.html | 2 +- latest/docs/source/mx_quantization.html | 2 +- latest/docs/source/objective.html | 2 +- latest/docs/source/orchestration.html | 2 +- latest/docs/source/pruning.html | 2 +- latest/docs/source/publication_list.html | 2 +- latest/docs/source/quantization.html | 2 +- latest/docs/source/quantization_layer_wise.html | 2 +- latest/docs/source/quantization_mixed_precision.html | 2 +- latest/docs/source/quantization_weight_only.html | 2 +- latest/docs/source/releases_info.html | 2 +- latest/docs/source/sigopt_strategy.html | 2 +- latest/docs/source/smooth_quant.html | 2 +- latest/docs/source/transform.html | 2 +- latest/docs/source/tuning_strategies.html | 2 +- latest/docs/source/validated_model_list.html | 2 +- latest/genindex.html | 2 +- latest/py-modindex.html | 2 +- latest/search.html | 2 +- latest/searchindex.js | 2 +- 561 files changed, 576 insertions(+), 565 deletions(-) diff --git a/latest/_sources/autoapi/neural_compressor/torch/algorithms/weight_only/autoround/index.rst.txt b/latest/_sources/autoapi/neural_compressor/torch/algorithms/weight_only/autoround/index.rst.txt index cea1bd523d1..5e1b81f892a 100644 --- a/latest/_sources/autoapi/neural_compressor/torch/algorithms/weight_only/autoround/index.rst.txt +++ b/latest/_sources/autoapi/neural_compressor/torch/algorithms/weight_only/autoround/index.rst.txt @@ -28,7 +28,7 @@ Functions Module Contents --------------- -.. py:class:: AutoRoundQuantizer(quant_config: dict = {}, enable_full_range: bool = False, batch_size: int = 8, amp: bool = True, device: str = None, lr_scheduler=None, dataset: Union[str, list, tuple, torch.utils.data.DataLoader] = 'NeelNanda/pile-10k', enable_quanted_input: bool = True, enable_minmax_tuning: bool = True, lr: float = None, minmax_lr: float = None, low_gpu_mem_usage: bool = False, iters: int = 200, seqlen: int = 2048, nsamples: int = 128, sampler: str = 'rand', seed: int = 42, nblocks: int = 1, gradient_accumulate_steps: int = 1, not_use_best_mse: bool = False, dynamic_max_gap: int = -1, data_type: str = 'int', scale_dtype: str = 'fp16', quant_block_list: list = None, act_bits: int = 32, act_group_size: int = None, act_sym: bool = None, act_dynamic: bool = True, low_cpu_mem_usage: bool = False, **kwargs) +.. py:class:: AutoRoundQuantizer(quant_config: dict = {}, enable_full_range: bool = False, batch_size: int = 8, amp: bool = True, device: str = None, lr_scheduler=None, dataset: Union[str, list, tuple, torch.utils.data.DataLoader] = 'NeelNanda/pile-10k', enable_quanted_input: bool = True, enable_minmax_tuning: bool = True, lr: float = None, minmax_lr: float = None, low_gpu_mem_usage: bool = False, iters: int = 200, seqlen: int = 2048, nsamples: int = 128, sampler: str = 'rand', seed: int = 42, nblocks: int = 1, gradient_accumulate_steps: int = 1, not_use_best_mse: bool = False, dynamic_max_gap: int = -1, data_type: str = 'int', scale_dtype: str = 'fp16', quant_block_list: list = None, act_bits: int = 32, act_group_size: int = None, act_sym: bool = None, act_dynamic: bool = True, low_cpu_mem_usage: bool = False, export_format: str = 'itrex', **kwargs) diff --git a/latest/_sources/autoapi/neural_compressor/torch/algorithms/weight_only/save_load/index.rst.txt b/latest/_sources/autoapi/neural_compressor/torch/algorithms/weight_only/save_load/index.rst.txt index ec9d1fe03c7..d4c3d75e172 100644 --- a/latest/_sources/autoapi/neural_compressor/torch/algorithms/weight_only/save_load/index.rst.txt +++ b/latest/_sources/autoapi/neural_compressor/torch/algorithms/weight_only/save_load/index.rst.txt @@ -29,7 +29,7 @@ Functions Module Contents --------------- -.. py:function:: save(model, output_dir='./saved_results') +.. py:function:: save(model, output_dir='./saved_results', format=LoadFormat.DEFAULT, **kwargs) Save the quantized model and config to the output path. @@ -37,6 +37,12 @@ Module Contents :type model: torch.nn.module :param output_dir: output path to save. :type output_dir: str, optional + :param format: The format in which to save the model. Options include "default" and "huggingface". Defaults to "default". + :type format: str, optional + :param kwargs: Additional arguments for specific formats. For example: + - safe_serialization (bool): Whether to use safe serialization when saving (only applicable for 'huggingface' format). Defaults to True. + - tokenizer (Tokenizer, optional): The tokenizer to be saved along with the model (only applicable for 'huggingface' format). + - max_shard_size (str, optional): The maximum size for each shard (only applicable for 'huggingface' format). Defaults to "5GB". .. py:function:: load(model_name_or_path, original_model=None, format=LoadFormat.DEFAULT, device='cpu', **kwargs) diff --git a/latest/_sources/autoapi/neural_compressor/torch/quantization/config/index.rst.txt b/latest/_sources/autoapi/neural_compressor/torch/quantization/config/index.rst.txt index 25016aafe65..2dbc12aecc8 100644 --- a/latest/_sources/autoapi/neural_compressor/torch/quantization/config/index.rst.txt +++ b/latest/_sources/autoapi/neural_compressor/torch/quantization/config/index.rst.txt @@ -157,7 +157,7 @@ Module Contents :returns: the default teq config. -.. py:class:: AutoRoundConfig(dtype: str = 'int', bits: int = 4, use_sym: bool = False, group_size: int = 128, act_bits: int = 32, act_group_size: int = None, act_sym: bool = None, act_dynamic: bool = True, enable_full_range: bool = False, batch_size: int = 8, lr_scheduler=None, enable_quanted_input: bool = True, enable_minmax_tuning: bool = True, lr: float = None, minmax_lr: float = None, low_gpu_mem_usage: bool = False, iters: int = 200, seqlen: int = 2048, nsamples: int = 128, sampler: str = 'rand', seed: int = 42, nblocks: int = 1, gradient_accumulate_steps: int = 1, not_use_best_mse: bool = False, dynamic_max_gap: int = -1, scale_dtype: str = 'fp16', use_layer_wise: bool = False, quant_block_list: list = None, white_list: Optional[List[neural_compressor.common.utils.OP_NAME_OR_MODULE_TYPE]] = DEFAULT_WHITE_LIST) +.. py:class:: AutoRoundConfig(dtype: str = 'int', bits: int = 4, use_sym: bool = False, group_size: int = 128, act_bits: int = 32, act_group_size: int = None, act_sym: bool = None, act_dynamic: bool = True, enable_full_range: bool = False, batch_size: int = 8, lr_scheduler=None, enable_quanted_input: bool = True, enable_minmax_tuning: bool = True, lr: float = None, minmax_lr: float = None, low_gpu_mem_usage: bool = False, iters: int = 200, seqlen: int = 2048, nsamples: int = 128, sampler: str = 'rand', seed: int = 42, nblocks: int = 1, gradient_accumulate_steps: int = 1, not_use_best_mse: bool = False, dynamic_max_gap: int = -1, scale_dtype: str = 'fp16', use_layer_wise: bool = False, quant_block_list: list = None, export_format: str = 'itrex', white_list: Optional[List[neural_compressor.common.utils.OP_NAME_OR_MODULE_TYPE]] = DEFAULT_WHITE_LIST) diff --git a/latest/autoapi/neural_compressor/adaptor/mxnet_utils/index.html b/latest/autoapi/neural_compressor/adaptor/mxnet_utils/index.html index d5184db619b..0b06f6a9f46 100644 --- a/latest/autoapi/neural_compressor/adaptor/mxnet_utils/index.html +++ b/latest/autoapi/neural_compressor/adaptor/mxnet_utils/index.html @@ -114,7 +114,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

Cookies | Privacy
diff --git a/latest/autoapi/neural_compressor/adaptor/mxnet_utils/util/index.html b/latest/autoapi/neural_compressor/adaptor/mxnet_utils/util/index.html index 5c45ff85acf..f3ac0a8d292 100644 --- a/latest/autoapi/neural_compressor/adaptor/mxnet_utils/util/index.html +++ b/latest/autoapi/neural_compressor/adaptor/mxnet_utils/util/index.html @@ -678,7 +678,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/calibration/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/calibration/index.html index e276eb49a6b..39fe31234b9 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/calibration/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/calibration/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/calibrator/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/calibrator/index.html index d0e4c403d71..1cd0b24e689 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/calibrator/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/calibrator/index.html @@ -225,7 +225,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/index.html index 40f479e32da..69f90409dd4 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/index.html @@ -127,7 +127,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/activation/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/activation/index.html index d931cf895f6..d242b1d2977 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/activation/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/activation/index.html @@ -152,7 +152,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/argmax/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/argmax/index.html index 972115351c6..13f0c2ac5da 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/argmax/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/argmax/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/attention/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/attention/index.html index 72c9915d4ea..4a8e59fd1ec 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/attention/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/attention/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/binary_op/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/binary_op/index.html index a13fee6bb34..4f743c904e4 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/binary_op/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/binary_op/index.html @@ -152,7 +152,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/concat/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/concat/index.html index d80aa4d7def..1fe15b7d384 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/concat/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/concat/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/conv/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/conv/index.html index 949dfbac22d..fa2e85922de 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/conv/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/conv/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/direct_q8/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/direct_q8/index.html index 27a957ff706..ebbc1b06d94 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/direct_q8/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/direct_q8/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/embed_layernorm/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/embed_layernorm/index.html index a1bb4890ea5..5e57d95fe0d 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/embed_layernorm/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/embed_layernorm/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/gather/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/gather/index.html index 08fd11d5d51..b5e14edf03f 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/gather/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/gather/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/gavgpool/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/gavgpool/index.html index dda4b363fc5..feda49a5e2d 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/gavgpool/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/gavgpool/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/gemm/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/gemm/index.html index 1b650d016db..dfe4f021b7c 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/gemm/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/gemm/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/index.html index 5118418a78e..4cc29b733b6 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/index.html @@ -135,7 +135,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/lstm/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/lstm/index.html index 157d259338b..071ed48dcc6 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/lstm/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/lstm/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/matmul/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/matmul/index.html index ee9bbd1b2a5..efe57313a7a 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/matmul/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/matmul/index.html @@ -143,7 +143,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/maxpool/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/maxpool/index.html index 7542679a0f8..866255e3a81 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/maxpool/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/maxpool/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/norm/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/norm/index.html index 1c7a7638ce6..041ea83df1f 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/norm/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/norm/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/ops/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/ops/index.html index 773005934e5..7575ad8ae63 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/ops/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/ops/index.html @@ -159,7 +159,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/pad/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/pad/index.html index 0ddaecae6c5..5beb6ca73f2 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/pad/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/pad/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/pooling/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/pooling/index.html index cef99f3e51b..2456ac0fd80 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/pooling/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/pooling/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/reduce/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/reduce/index.html index c238afff029..d2ca7533a5a 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/reduce/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/reduce/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/resize/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/resize/index.html index b67f8756942..46772feb466 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/resize/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/resize/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/split/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/split/index.html index 5f57443c69e..ff3e28b8395 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/split/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/split/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/unary_op/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/unary_op/index.html index b24e2947420..2343b936c70 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/unary_op/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/operators/unary_op/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/quantizer/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/quantizer/index.html index 95785b93008..e4a2984ca8c 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/quantizer/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/quantizer/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/smooth_quant/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/smooth_quant/index.html index bd1e454c078..62e190d661d 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/smooth_quant/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/smooth_quant/index.html @@ -199,7 +199,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/util/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/util/index.html index 21c778d1215..196d4cc5b23 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/util/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/util/index.html @@ -462,7 +462,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/ox_utils/weight_only/index.html b/latest/autoapi/neural_compressor/adaptor/ox_utils/weight_only/index.html index 416ebf51468..c199a0327d2 100644 --- a/latest/autoapi/neural_compressor/adaptor/ox_utils/weight_only/index.html +++ b/latest/autoapi/neural_compressor/adaptor/ox_utils/weight_only/index.html @@ -483,7 +483,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tensorflow/index.html b/latest/autoapi/neural_compressor/adaptor/tensorflow/index.html index 43edf4c33de..b5b6342a37d 100644 --- a/latest/autoapi/neural_compressor/adaptor/tensorflow/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tensorflow/index.html @@ -143,7 +143,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_converter/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_converter/index.html index ddb2a9a4094..5f35e6bce15 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_converter/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_converter/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_converter_without_calib/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_converter_without_calib/index.html index dda08447097..79a1b7267e6 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_converter_without_calib/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_converter_without_calib/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/bf16_convert/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/bf16_convert/index.html index 1f9c7c6e06e..095ae56f8dc 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/bf16_convert/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/bf16_convert/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/dequantize_cast_optimizer/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/dequantize_cast_optimizer/index.html index 0b1a808938f..ade5b74a5c0 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/dequantize_cast_optimizer/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/dequantize_cast_optimizer/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/index.html index 455269dc55b..8d022c74afc 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/index.html @@ -115,7 +115,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_add_to_biasadd/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_add_to_biasadd/index.html index cca84b3bfd2..e7fda70410b 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_add_to_biasadd/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_add_to_biasadd/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_layout/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_layout/index.html index 08a55be4a14..01740d63fb3 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_layout/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_layout/index.html @@ -131,7 +131,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_leakyrelu/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_leakyrelu/index.html index 2b971df6178..83e34e020a7 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_leakyrelu/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_leakyrelu/index.html @@ -141,7 +141,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_nan_to_random/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_nan_to_random/index.html index ab0e5e3c04f..2ba11b47dab 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_nan_to_random/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_nan_to_random/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_placeholder_to_const/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_placeholder_to_const/index.html index f17994fbfa4..1c68fe81b84 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_placeholder_to_const/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_placeholder_to_const/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dilated_contraction/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dilated_contraction/index.html index 72acab4e8ef..2fe1dbc27a4 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dilated_contraction/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dilated_contraction/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dummy_biasadd/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dummy_biasadd/index.html index 214995f4d50..8efbf99c454 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dummy_biasadd/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dummy_biasadd/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/expanddims_optimizer/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/expanddims_optimizer/index.html index 6f818e789f5..1512f0bc89a 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/expanddims_optimizer/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/expanddims_optimizer/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fetch_weight_from_reshape/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fetch_weight_from_reshape/index.html index a96268a1348..1d6f4fd7184 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fetch_weight_from_reshape/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fetch_weight_from_reshape/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_batch_norm/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_batch_norm/index.html index 985778a5160..49779242b00 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_batch_norm/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_batch_norm/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_constant/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_constant/index.html index 410da6f7aab..7016167127a 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_constant/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_constant/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_biasadd_add/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_biasadd_add/index.html index 61636f88eee..fa42e579a66 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_biasadd_add/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_biasadd_add/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_column_wise_mul/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_column_wise_mul/index.html index 5682a0944a3..33f64685087 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_column_wise_mul/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_column_wise_mul/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_conv_with_math/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_conv_with_math/index.html index a9c9cc6f37e..0b23aaf0c7e 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_conv_with_math/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_conv_with_math/index.html @@ -140,7 +140,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_bn/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_bn/index.html index f3d72db1e2d..c885b28d7f2 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_bn/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_bn/index.html @@ -219,7 +219,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_in/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_in/index.html index 8a9036701b2..f6c7d1e7812 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_in/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_in/index.html @@ -219,7 +219,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_gelu/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_gelu/index.html index 7aa999b192b..a50026de295 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_gelu/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_gelu/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_layer_norm/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_layer_norm/index.html index c64851878f6..ed53c1993fb 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_layer_norm/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_layer_norm/index.html @@ -186,7 +186,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_conv/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_conv/index.html index 80a8e0c22b5..9868d65909d 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_conv/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_conv/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index.html index 7ca08afd7ad..b775eb700f9 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_reshape_transpose/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_reshape_transpose/index.html index 1127bdd357a..38c95f25688 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_reshape_transpose/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_reshape_transpose/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/graph_cse_optimizer/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/graph_cse_optimizer/index.html index b052fe22adf..2ff5876c014 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/graph_cse_optimizer/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/graph_cse_optimizer/index.html @@ -181,7 +181,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/grappler_pass/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/grappler_pass/index.html index bba903a16af..7819bbf8c46 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/grappler_pass/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/grappler_pass/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/index.html index ae08b5f6653..17c99ed1a78 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/index.html @@ -145,7 +145,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/insert_print_node/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/insert_print_node/index.html index d37e326a2a3..e13757b82e8 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/insert_print_node/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/insert_print_node/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/move_squeeze_after_relu/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/move_squeeze_after_relu/index.html index 8186b74eb5c..d2d6dfb3936 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/move_squeeze_after_relu/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/move_squeeze_after_relu/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/pre_optimize/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/pre_optimize/index.html index 0dcb040f0c5..1530ac411c7 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/pre_optimize/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/pre_optimize/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/remove_training_nodes/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/remove_training_nodes/index.html index 979ba1c05e9..32365f849f1 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/remove_training_nodes/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/remove_training_nodes/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/rename_batch_norm/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/rename_batch_norm/index.html index 1e5e7c91bff..14282976c63 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/rename_batch_norm/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/rename_batch_norm/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/split_shared_input/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/split_shared_input/index.html index 5e44bffa0ab..10ec932b68b 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/split_shared_input/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/split_shared_input/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_equivalent_nodes/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_equivalent_nodes/index.html index f77838ac42f..2a40c521496 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_equivalent_nodes/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_equivalent_nodes/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_unused_nodes/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_unused_nodes/index.html index c4c00fd292e..fb5e6e2618d 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_unused_nodes/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_unused_nodes/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/switch_optimizer/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/switch_optimizer/index.html index 3d477c28640..f182e3009c7 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/switch_optimizer/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/switch_optimizer/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/graph_base/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/graph_base/index.html index 5283c30218b..0e1d67efb17 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/graph_base/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/graph_base/index.html @@ -131,7 +131,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/index.html index d35699cb5da..6a34af4a266 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/index.html @@ -126,7 +126,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_fake_quant/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_fake_quant/index.html index 8e683f4adae..bb34947be18 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_fake_quant/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_fake_quant/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value/index.html index 5851ae68cb2..9ffc3166031 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value_without_calib/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value_without_calib/index.html index f0dbbfb31b2..2b39004f0c0 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value_without_calib/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value_without_calib/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index.html index e97bf53f737..b930857e20c 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_requantize/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_requantize/index.html index 9b3ceacf47c..a102ec10289 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_requantize/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_requantize/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index.html index d639075ec95..d6a09a6c9a5 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_requantize/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_requantize/index.html index 1a09ba7040a..4467e155886 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_requantize/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_requantize/index.html @@ -152,7 +152,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/index.html index 70e3b3a0a3a..d344b9bf079 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/index.html @@ -125,7 +125,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/meta_op_optimizer/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/meta_op_optimizer/index.html index cc77a3ea3e0..3ea03894332 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/meta_op_optimizer/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/meta_op_optimizer/index.html @@ -126,7 +126,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_hostconst_converter/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_hostconst_converter/index.html index e7a3813e242..863c5e3e253 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_hostconst_converter/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_hostconst_converter/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_quantized_op_cse/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_quantized_op_cse/index.html index edd8ba44c72..c28a7132ec0 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_quantized_op_cse/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_quantized_op_cse/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/rnn_convert/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/rnn_convert/index.html index 3b2a92d326e..e8b952ebbfa 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/rnn_convert/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/rnn_convert/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/scale_propagation/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/scale_propagation/index.html index 64247336496..fbee0d98f33 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/scale_propagation/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/scale_propagation/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/index.html index be2d5a9d38b..70802a20c68 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/index.html @@ -117,7 +117,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_graph/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_graph/index.html index 62b74cb6235..93ecefbb25c 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_graph/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_graph/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_node/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_node/index.html index e918bb6ba9c..d74be9f5d08 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_node/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_node/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_schema/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_schema/index.html index d7d61a18c1b..e6b8e557231 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_schema/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_schema/index.html @@ -150,7 +150,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/tf2onnx_utils/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/tf2onnx_utils/index.html index 88db20e3a51..e8481a2902c 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/tf2onnx_utils/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/tf2onnx_utils/index.html @@ -359,7 +359,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/index.html index 5de5f9fcef3..b3804b74766 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/index.html @@ -116,7 +116,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/insert_qdq_pattern/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/insert_qdq_pattern/index.html index f44e7beb898..3e2512dc282 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/insert_qdq_pattern/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/insert_qdq_pattern/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/merge_duplicated_qdq/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/merge_duplicated_qdq/index.html index 7d872fe7122..a3442c9113e 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/merge_duplicated_qdq/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/merge_duplicated_qdq/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/share_qdq_y_pattern/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/share_qdq_y_pattern/index.html index 9a19d302dd0..758447a1928 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/share_qdq_y_pattern/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/share_qdq_y_pattern/index.html @@ -126,7 +126,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_util/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_util/index.html index 3de73f71f37..eb33e844762 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_util/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/graph_util/index.html @@ -137,7 +137,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/index.html index 1a70b130fe3..22e89766731 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/index.html @@ -131,7 +131,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/index.html index 589035c98f3..06c1819ddce 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/index.html @@ -129,7 +129,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/fake_quantize/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/fake_quantize/index.html index 44af5d1ed69..50ab24e9723 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/fake_quantize/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/fake_quantize/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/index.html index 78b25f54f66..b6ad31be34d 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/index.html @@ -125,7 +125,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_config/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_config/index.html index e7c32af36fc..b3d200c313c 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_config/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_config/index.html @@ -126,7 +126,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_helper/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_helper/index.html index 6ea8281d382..d4283156a16 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_helper/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_helper/index.html @@ -163,7 +163,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/index.html index 95016277f95..1a17f8ae6c8 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/index.html @@ -117,7 +117,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/optimize_layer/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/optimize_layer/index.html index e8a44526363..6f1e24956c2 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/optimize_layer/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/optimize_layer/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_add/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_add/index.html index 0ee849e4d2f..1d3c1bc04ee 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_add/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_add/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_base/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_base/index.html index 2b62b86e6bb..718088a3fdd 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_base/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_base/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_bn/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_bn/index.html index e5a04473836..e7a1df40067 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_bn/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_bn/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_wrapper/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_wrapper/index.html index e5b4f7390da..be69c993ce0 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_wrapper/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_wrapper/index.html @@ -135,7 +135,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_bn/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_bn/index.html index 8763bd907d4..fae64e638a2 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_bn/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_bn/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_concatv2/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_concatv2/index.html index f4430494656..2953560bd80 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_concatv2/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_concatv2/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_conv/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_conv/index.html index a082908cd57..79bac51a5a7 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_conv/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_conv/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_deconv/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_deconv/index.html index 4f3f55ec677..66e917acbde 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_deconv/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_deconv/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_in/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_in/index.html index 6f35169542b..ce37bc1fce6 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_in/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_in/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_matmul/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_matmul/index.html index c8df056f9ed..f54d72eb8ec 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_matmul/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_matmul/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_pooling/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_pooling/index.html index 393e1f9a7b1..f2d87f46a2b 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_pooling/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_pooling/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/index.html index 96f6bf4c409..8a93e34a15f 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/index.html @@ -121,7 +121,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/optimize_qdq/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/optimize_qdq/index.html index 3222cd7e73b..5ddd9576fff 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/optimize_qdq/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/optimize_qdq/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_base/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_base/index.html index 8fdf02b7eb1..2696a188103 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_base/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_base/index.html @@ -139,7 +139,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_bn/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_bn/index.html index 1cd0faa8312..bec30abcb9b 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_bn/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_bn/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_concatv2/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_concatv2/index.html index 24ad40dc8bc..7b25f50d432 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_concatv2/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_concatv2/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_conv/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_conv/index.html index 1894a5eaa81..1697959cb2c 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_conv/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_conv/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_for_intel_cpu/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_for_intel_cpu/index.html index db0083c5612..b9498ac376e 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_for_intel_cpu/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_for_intel_cpu/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_matmul/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_matmul/index.html index 1efe8bf10a4..331b0910abf 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_matmul/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_matmul/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_pooling/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_pooling/index.html index 0462ff99b27..1cae366e78e 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_pooling/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_pooling/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph_common/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph_common/index.html index 7f763ee5ca8..e2293ace79c 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph_common/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/quantize_graph_common/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_calibration/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_calibration/index.html index 263c0ae9bf4..b8185abd802 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_calibration/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_calibration/index.html @@ -158,7 +158,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_scaler/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_scaler/index.html index b422eaaff6e..daa95a7a19b 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_scaler/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_scaler/index.html @@ -156,7 +156,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/tf2onnx_converter/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/tf2onnx_converter/index.html index 5b5c16ee661..3fee0b41a33 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/tf2onnx_converter/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/tf2onnx_converter/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/bias_correction/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/bias_correction/index.html index e4e17995c6e..f671b216a63 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/bias_correction/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/bias_correction/index.html @@ -135,7 +135,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/graph_transform_base/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/graph_transform_base/index.html index 8ed1beb3841..55be4acd807 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/graph_transform_base/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/graph_transform_base/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/index.html index ebf7abe4fd4..a0d7aaf17fd 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/index.html @@ -117,7 +117,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/insert_logging/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/insert_logging/index.html index b31377e474c..71afffcddc1 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/insert_logging/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/insert_logging/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/rerange_quantized_concat/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/rerange_quantized_concat/index.html index 4814349361d..74dd964206e 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/rerange_quantized_concat/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/transform_graph/rerange_quantized_concat/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/tf_utils/util/index.html b/latest/autoapi/neural_compressor/adaptor/tf_utils/util/index.html index 10b88837e86..9954d545f7a 100644 --- a/latest/autoapi/neural_compressor/adaptor/tf_utils/util/index.html +++ b/latest/autoapi/neural_compressor/adaptor/tf_utils/util/index.html @@ -550,7 +550,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/torch_utils/bf16_convert/index.html b/latest/autoapi/neural_compressor/adaptor/torch_utils/bf16_convert/index.html index 99dd68e3832..d44242bd11d 100644 --- a/latest/autoapi/neural_compressor/adaptor/torch_utils/bf16_convert/index.html +++ b/latest/autoapi/neural_compressor/adaptor/torch_utils/bf16_convert/index.html @@ -155,7 +155,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/torch_utils/hawq_metric/index.html b/latest/autoapi/neural_compressor/adaptor/torch_utils/hawq_metric/index.html index 86ebb22eda0..495172b1a10 100644 --- a/latest/autoapi/neural_compressor/adaptor/torch_utils/hawq_metric/index.html +++ b/latest/autoapi/neural_compressor/adaptor/torch_utils/hawq_metric/index.html @@ -197,7 +197,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/torch_utils/index.html b/latest/autoapi/neural_compressor/adaptor/torch_utils/index.html index 1bbe2588888..4e0658d03fa 100644 --- a/latest/autoapi/neural_compressor/adaptor/torch_utils/index.html +++ b/latest/autoapi/neural_compressor/adaptor/torch_utils/index.html @@ -127,7 +127,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/index.html b/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/index.html index 549911d04a8..3ecdb55cd07 100644 --- a/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/index.html +++ b/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/index.html @@ -117,7 +117,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/modified_pickle/index.html b/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/modified_pickle/index.html index ce99de0adfa..a9d406bec9b 100644 --- a/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/modified_pickle/index.html +++ b/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/modified_pickle/index.html @@ -168,7 +168,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/quantize/index.html b/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/quantize/index.html index c17a42e1325..eae523f1e2f 100644 --- a/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/quantize/index.html +++ b/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/quantize/index.html @@ -126,7 +126,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/torch_load/index.html b/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/torch_load/index.html index 4611c8d1a6e..a0eaaeed2b1 100644 --- a/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/torch_load/index.html +++ b/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/torch_load/index.html @@ -210,7 +210,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/utils/index.html b/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/utils/index.html index 29fc43d10b5..81bd7d5c751 100644 --- a/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/utils/index.html +++ b/latest/autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/utils/index.html @@ -214,7 +214,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/torch_utils/model_wrapper/index.html b/latest/autoapi/neural_compressor/adaptor/torch_utils/model_wrapper/index.html index d4ef085c58e..1ee6b502631 100644 --- a/latest/autoapi/neural_compressor/adaptor/torch_utils/model_wrapper/index.html +++ b/latest/autoapi/neural_compressor/adaptor/torch_utils/model_wrapper/index.html @@ -143,7 +143,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/torch_utils/pattern_detector/index.html b/latest/autoapi/neural_compressor/adaptor/torch_utils/pattern_detector/index.html index f823e9c17e9..b34009ee740 100644 --- a/latest/autoapi/neural_compressor/adaptor/torch_utils/pattern_detector/index.html +++ b/latest/autoapi/neural_compressor/adaptor/torch_utils/pattern_detector/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/torch_utils/symbolic_trace/index.html b/latest/autoapi/neural_compressor/adaptor/torch_utils/symbolic_trace/index.html index 2f396dc3f52..41e6b71a5d1 100644 --- a/latest/autoapi/neural_compressor/adaptor/torch_utils/symbolic_trace/index.html +++ b/latest/autoapi/neural_compressor/adaptor/torch_utils/symbolic_trace/index.html @@ -157,7 +157,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/adaptor/torch_utils/util/index.html b/latest/autoapi/neural_compressor/adaptor/torch_utils/util/index.html index 9c34054256b..002a8c95fc3 100644 --- a/latest/autoapi/neural_compressor/adaptor/torch_utils/util/index.html +++ b/latest/autoapi/neural_compressor/adaptor/torch_utils/util/index.html @@ -770,7 +770,7 @@

}

Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/algorithm/algorithm/index.html b/latest/autoapi/neural_compressor/algorithm/algorithm/index.html index 904d9891a58..6083df94014 100644 --- a/latest/autoapi/neural_compressor/algorithm/algorithm/index.html +++ b/latest/autoapi/neural_compressor/algorithm/algorithm/index.html @@ -174,7 +174,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/algorithm/fast_bias_correction/index.html b/latest/autoapi/neural_compressor/algorithm/fast_bias_correction/index.html index 600e55b749a..3131c1a02ce 100644 --- a/latest/autoapi/neural_compressor/algorithm/fast_bias_correction/index.html +++ b/latest/autoapi/neural_compressor/algorithm/fast_bias_correction/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/algorithm/index.html b/latest/autoapi/neural_compressor/algorithm/index.html index 3b722a93db4..807ca5a8de3 100644 --- a/latest/autoapi/neural_compressor/algorithm/index.html +++ b/latest/autoapi/neural_compressor/algorithm/index.html @@ -117,7 +117,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/algorithm/smooth_quant/index.html b/latest/autoapi/neural_compressor/algorithm/smooth_quant/index.html index 0609d2c2254..dd1c36ed900 100644 --- a/latest/autoapi/neural_compressor/algorithm/smooth_quant/index.html +++ b/latest/autoapi/neural_compressor/algorithm/smooth_quant/index.html @@ -131,7 +131,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/algorithm/weight_correction/index.html b/latest/autoapi/neural_compressor/algorithm/weight_correction/index.html index 92621e6ffac..5f82a3adce3 100644 --- a/latest/autoapi/neural_compressor/algorithm/weight_correction/index.html +++ b/latest/autoapi/neural_compressor/algorithm/weight_correction/index.html @@ -133,7 +133,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/benchmark/index.html b/latest/autoapi/neural_compressor/benchmark/index.html index f6599cf4d54..0c1ee938d1d 100644 --- a/latest/autoapi/neural_compressor/benchmark/index.html +++ b/latest/autoapi/neural_compressor/benchmark/index.html @@ -340,7 +340,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/common/base_config/index.html b/latest/autoapi/neural_compressor/common/base_config/index.html index 2a36244be83..07e7626ecea 100644 --- a/latest/autoapi/neural_compressor/common/base_config/index.html +++ b/latest/autoapi/neural_compressor/common/base_config/index.html @@ -251,7 +251,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/common/base_tuning/index.html b/latest/autoapi/neural_compressor/common/base_tuning/index.html index cf306576ee8..4f6a7b79fa3 100644 --- a/latest/autoapi/neural_compressor/common/base_tuning/index.html +++ b/latest/autoapi/neural_compressor/common/base_tuning/index.html @@ -274,7 +274,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/common/benchmark/index.html b/latest/autoapi/neural_compressor/common/benchmark/index.html index e5400bb7c02..9b64a33fab7 100644 --- a/latest/autoapi/neural_compressor/common/benchmark/index.html +++ b/latest/autoapi/neural_compressor/common/benchmark/index.html @@ -323,7 +323,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/common/index.html b/latest/autoapi/neural_compressor/common/index.html index 6368361533b..b1b64247561 100644 --- a/latest/autoapi/neural_compressor/common/index.html +++ b/latest/autoapi/neural_compressor/common/index.html @@ -125,7 +125,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/common/tuning_param/index.html b/latest/autoapi/neural_compressor/common/tuning_param/index.html index 8da0e180f0c..e1b05b1d992 100644 --- a/latest/autoapi/neural_compressor/common/tuning_param/index.html +++ b/latest/autoapi/neural_compressor/common/tuning_param/index.html @@ -174,7 +174,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/common/utils/constants/index.html b/latest/autoapi/neural_compressor/common/utils/constants/index.html index 88d5d2ca6cb..7345205bd85 100644 --- a/latest/autoapi/neural_compressor/common/utils/constants/index.html +++ b/latest/autoapi/neural_compressor/common/utils/constants/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/common/utils/index.html b/latest/autoapi/neural_compressor/common/utils/index.html index 8c4290d1e85..3a665833497 100644 --- a/latest/autoapi/neural_compressor/common/utils/index.html +++ b/latest/autoapi/neural_compressor/common/utils/index.html @@ -116,7 +116,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/common/utils/logger/index.html b/latest/autoapi/neural_compressor/common/utils/logger/index.html index 36a37ab74bd..bd887dbae1e 100644 --- a/latest/autoapi/neural_compressor/common/utils/logger/index.html +++ b/latest/autoapi/neural_compressor/common/utils/logger/index.html @@ -135,7 +135,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/common/utils/save_load/index.html b/latest/autoapi/neural_compressor/common/utils/save_load/index.html index 9edafaa9c28..e5dc32b2efd 100644 --- a/latest/autoapi/neural_compressor/common/utils/save_load/index.html +++ b/latest/autoapi/neural_compressor/common/utils/save_load/index.html @@ -157,7 +157,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/common/utils/utility/index.html b/latest/autoapi/neural_compressor/common/utils/utility/index.html index 8ab1023b02c..3dfadcffce2 100644 --- a/latest/autoapi/neural_compressor/common/utils/utility/index.html +++ b/latest/autoapi/neural_compressor/common/utils/utility/index.html @@ -278,7 +278,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/callbacks/index.html b/latest/autoapi/neural_compressor/compression/callbacks/index.html index fc2d3a84558..04820569fb1 100644 --- a/latest/autoapi/neural_compressor/compression/callbacks/index.html +++ b/latest/autoapi/neural_compressor/compression/callbacks/index.html @@ -196,7 +196,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/distillation/criterions/index.html b/latest/autoapi/neural_compressor/compression/distillation/criterions/index.html index 35ed5b43a30..91f0201f566 100644 --- a/latest/autoapi/neural_compressor/compression/distillation/criterions/index.html +++ b/latest/autoapi/neural_compressor/compression/distillation/criterions/index.html @@ -324,7 +324,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/distillation/index.html b/latest/autoapi/neural_compressor/compression/distillation/index.html index 633dc8383c0..3fd0e8e414e 100644 --- a/latest/autoapi/neural_compressor/compression/distillation/index.html +++ b/latest/autoapi/neural_compressor/compression/distillation/index.html @@ -116,7 +116,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/distillation/optimizers/index.html b/latest/autoapi/neural_compressor/compression/distillation/optimizers/index.html index fc4bab913c8..5ef88c97c3a 100644 --- a/latest/autoapi/neural_compressor/compression/distillation/optimizers/index.html +++ b/latest/autoapi/neural_compressor/compression/distillation/optimizers/index.html @@ -232,7 +232,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/distillation/utility/index.html b/latest/autoapi/neural_compressor/compression/distillation/utility/index.html index 2c75019efb3..b961be593b1 100644 --- a/latest/autoapi/neural_compressor/compression/distillation/utility/index.html +++ b/latest/autoapi/neural_compressor/compression/distillation/utility/index.html @@ -135,7 +135,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/hpo/index.html b/latest/autoapi/neural_compressor/compression/hpo/index.html index a645b9258cd..8d6f1fd76bc 100644 --- a/latest/autoapi/neural_compressor/compression/hpo/index.html +++ b/latest/autoapi/neural_compressor/compression/hpo/index.html @@ -114,7 +114,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/hpo/sa_optimizer/index.html b/latest/autoapi/neural_compressor/compression/hpo/sa_optimizer/index.html index 4d3c3d3eb3e..1616ea4edc0 100644 --- a/latest/autoapi/neural_compressor/compression/hpo/sa_optimizer/index.html +++ b/latest/autoapi/neural_compressor/compression/hpo/sa_optimizer/index.html @@ -106,7 +106,7 @@ Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/criteria/index.html b/latest/autoapi/neural_compressor/compression/pruner/criteria/index.html index 2e20c45946f..1fe3b624338 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/criteria/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/criteria/index.html @@ -321,7 +321,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/index.html b/latest/autoapi/neural_compressor/compression/pruner/index.html index fb587fbe2e0..f3942c9c661 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/index.html @@ -185,7 +185,7 @@

Package ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/model_slim/auto_slim/index.html b/latest/autoapi/neural_compressor/compression/pruner/model_slim/auto_slim/index.html index 3c8ac03a460..30c15181698 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/model_slim/auto_slim/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/model_slim/auto_slim/index.html @@ -183,7 +183,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/model_slim/index.html b/latest/autoapi/neural_compressor/compression/pruner/model_slim/index.html index 4686b21edd2..8fd8589034f 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/model_slim/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/model_slim/index.html @@ -116,7 +116,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/model_slim/pattern_analyzer/index.html b/latest/autoapi/neural_compressor/compression/pruner/model_slim/pattern_analyzer/index.html index 0092a79838f..309b4e8c2fd 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/model_slim/pattern_analyzer/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/model_slim/pattern_analyzer/index.html @@ -453,7 +453,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/model_slim/weight_slim/index.html b/latest/autoapi/neural_compressor/compression/pruner/model_slim/weight_slim/index.html index 781a083c760..47834df3a2d 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/model_slim/weight_slim/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/model_slim/weight_slim/index.html @@ -197,7 +197,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/patterns/base/index.html b/latest/autoapi/neural_compressor/compression/pruner/patterns/base/index.html index 7e07c0f466f..5c64611ed9c 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/patterns/base/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/patterns/base/index.html @@ -376,7 +376,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/patterns/index.html b/latest/autoapi/neural_compressor/compression/pruner/patterns/index.html index f2dc06f478e..9ab1cad3566 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/patterns/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/patterns/index.html @@ -151,7 +151,7 @@

Package ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/patterns/mha/index.html b/latest/autoapi/neural_compressor/compression/pruner/patterns/mha/index.html index 18a9ff1ec19..4ed525151a2 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/patterns/mha/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/patterns/mha/index.html @@ -145,7 +145,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/patterns/ninm/index.html b/latest/autoapi/neural_compressor/compression/pruner/patterns/ninm/index.html index 3b2c73cd2ab..09a61fc86bd 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/patterns/ninm/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/patterns/ninm/index.html @@ -145,7 +145,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/patterns/nxm/index.html b/latest/autoapi/neural_compressor/compression/pruner/patterns/nxm/index.html index c47cfb1933c..4e78bd95e5d 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/patterns/nxm/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/patterns/nxm/index.html @@ -172,7 +172,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/pruners/base/index.html b/latest/autoapi/neural_compressor/compression/pruner/pruners/base/index.html index 9ce2f2a698f..7cc2b04c326 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/pruners/base/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/pruners/base/index.html @@ -442,7 +442,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/pruners/basic/index.html b/latest/autoapi/neural_compressor/compression/pruner/pruners/basic/index.html index 10b21a10f11..e43755af105 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/pruners/basic/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/pruners/basic/index.html @@ -204,7 +204,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/pruners/block_mask/index.html b/latest/autoapi/neural_compressor/compression/pruner/pruners/block_mask/index.html index dcec094a7b4..6b2ca5c2237 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/pruners/block_mask/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/pruners/block_mask/index.html @@ -161,7 +161,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/pruners/index.html b/latest/autoapi/neural_compressor/compression/pruner/pruners/index.html index 4f2f7053491..cec065aa47b 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/pruners/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/pruners/index.html @@ -161,7 +161,7 @@

Package ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/pruners/mha/index.html b/latest/autoapi/neural_compressor/compression/pruner/pruners/mha/index.html index 1b622da7f85..16c7a5bab2d 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/pruners/mha/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/pruners/mha/index.html @@ -177,7 +177,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/pruners/pattern_lock/index.html b/latest/autoapi/neural_compressor/compression/pruner/pruners/pattern_lock/index.html index fb6b0e68436..081a9280533 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/pruners/pattern_lock/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/pruners/pattern_lock/index.html @@ -141,7 +141,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/pruners/progressive/index.html b/latest/autoapi/neural_compressor/compression/pruner/pruners/progressive/index.html index 0dc78250f8f..32394f7c253 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/pruners/progressive/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/pruners/progressive/index.html @@ -143,7 +143,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/pruners/retrain_free/index.html b/latest/autoapi/neural_compressor/compression/pruner/pruners/retrain_free/index.html index bf2b394b2b8..023b2c6de32 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/pruners/retrain_free/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/pruners/retrain_free/index.html @@ -170,7 +170,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/pruning/index.html b/latest/autoapi/neural_compressor/compression/pruner/pruning/index.html index 166018b7fae..3e6869e8942 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/pruning/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/pruning/index.html @@ -288,7 +288,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/regs/index.html b/latest/autoapi/neural_compressor/compression/pruner/regs/index.html index 91ca6aba761..9bb5f0b1f91 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/regs/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/regs/index.html @@ -226,7 +226,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/schedulers/index.html b/latest/autoapi/neural_compressor/compression/pruner/schedulers/index.html index 15b9c1cd313..3695c2dfe0b 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/schedulers/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/schedulers/index.html @@ -236,7 +236,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/tf_criteria/index.html b/latest/autoapi/neural_compressor/compression/pruner/tf_criteria/index.html index b79a3b76e0a..3d785df4b68 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/tf_criteria/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/tf_criteria/index.html @@ -189,7 +189,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/utils/index.html b/latest/autoapi/neural_compressor/compression/pruner/utils/index.html index 4e014834282..d8acf4de6f4 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/utils/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/utils/index.html @@ -395,7 +395,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/wanda/index.html b/latest/autoapi/neural_compressor/compression/pruner/wanda/index.html index 4020a6158ca..c284e596eaa 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/wanda/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/wanda/index.html @@ -114,7 +114,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/compression/pruner/wanda/utils/index.html b/latest/autoapi/neural_compressor/compression/pruner/wanda/utils/index.html index 4a0f2d4f5cb..d27b8eaf8a9 100644 --- a/latest/autoapi/neural_compressor/compression/pruner/wanda/utils/index.html +++ b/latest/autoapi/neural_compressor/compression/pruner/wanda/utils/index.html @@ -140,7 +140,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/config/index.html b/latest/autoapi/neural_compressor/config/index.html index 35878dda374..31fbd2ab456 100644 --- a/latest/autoapi/neural_compressor/config/index.html +++ b/latest/autoapi/neural_compressor/config/index.html @@ -1061,7 +1061,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/contrib/index.html b/latest/autoapi/neural_compressor/contrib/index.html index 5197447a738..c65221c7d69 100644 --- a/latest/autoapi/neural_compressor/contrib/index.html +++ b/latest/autoapi/neural_compressor/contrib/index.html @@ -114,7 +114,7 @@

SubpackagesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/contrib/strategy/index.html b/latest/autoapi/neural_compressor/contrib/strategy/index.html index bcb933d9a37..63bc9114826 100644 --- a/latest/autoapi/neural_compressor/contrib/strategy/index.html +++ b/latest/autoapi/neural_compressor/contrib/strategy/index.html @@ -115,7 +115,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/contrib/strategy/sigopt/index.html b/latest/autoapi/neural_compressor/contrib/strategy/sigopt/index.html index a37154bb88d..0e6fb1219f7 100644 --- a/latest/autoapi/neural_compressor/contrib/strategy/sigopt/index.html +++ b/latest/autoapi/neural_compressor/contrib/strategy/sigopt/index.html @@ -170,7 +170,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/contrib/strategy/tpe/index.html b/latest/autoapi/neural_compressor/contrib/strategy/tpe/index.html index 3ae9d111b78..870fe87346f 100644 --- a/latest/autoapi/neural_compressor/contrib/strategy/tpe/index.html +++ b/latest/autoapi/neural_compressor/contrib/strategy/tpe/index.html @@ -170,7 +170,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/dataloaders/base_dataloader/index.html b/latest/autoapi/neural_compressor/data/dataloaders/base_dataloader/index.html index 577abded725..7f7d246c1b3 100644 --- a/latest/autoapi/neural_compressor/data/dataloaders/base_dataloader/index.html +++ b/latest/autoapi/neural_compressor/data/dataloaders/base_dataloader/index.html @@ -128,7 +128,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/dataloaders/dataloader/index.html b/latest/autoapi/neural_compressor/data/dataloaders/dataloader/index.html index 7fa711379ec..b3be5468529 100644 --- a/latest/autoapi/neural_compressor/data/dataloaders/dataloader/index.html +++ b/latest/autoapi/neural_compressor/data/dataloaders/dataloader/index.html @@ -141,7 +141,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/dataloaders/default_dataloader/index.html b/latest/autoapi/neural_compressor/data/dataloaders/default_dataloader/index.html index ddbfa718e7a..52ab9f7f3c5 100644 --- a/latest/autoapi/neural_compressor/data/dataloaders/default_dataloader/index.html +++ b/latest/autoapi/neural_compressor/data/dataloaders/default_dataloader/index.html @@ -141,7 +141,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/dataloaders/fetcher/index.html b/latest/autoapi/neural_compressor/data/dataloaders/fetcher/index.html index 7e1db0638e9..115eca22837 100644 --- a/latest/autoapi/neural_compressor/data/dataloaders/fetcher/index.html +++ b/latest/autoapi/neural_compressor/data/dataloaders/fetcher/index.html @@ -143,7 +143,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/dataloaders/mxnet_dataloader/index.html b/latest/autoapi/neural_compressor/data/dataloaders/mxnet_dataloader/index.html index 21a12aafdef..19b44fa9228 100644 --- a/latest/autoapi/neural_compressor/data/dataloaders/mxnet_dataloader/index.html +++ b/latest/autoapi/neural_compressor/data/dataloaders/mxnet_dataloader/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/dataloaders/onnxrt_dataloader/index.html b/latest/autoapi/neural_compressor/data/dataloaders/onnxrt_dataloader/index.html index d4388411b98..83bed897f4e 100644 --- a/latest/autoapi/neural_compressor/data/dataloaders/onnxrt_dataloader/index.html +++ b/latest/autoapi/neural_compressor/data/dataloaders/onnxrt_dataloader/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/dataloaders/pytorch_dataloader/index.html b/latest/autoapi/neural_compressor/data/dataloaders/pytorch_dataloader/index.html index 453c864d93b..d9a47434a2b 100644 --- a/latest/autoapi/neural_compressor/data/dataloaders/pytorch_dataloader/index.html +++ b/latest/autoapi/neural_compressor/data/dataloaders/pytorch_dataloader/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/dataloaders/sampler/index.html b/latest/autoapi/neural_compressor/data/dataloaders/sampler/index.html index 423e4c06b82..fb16b5786b7 100644 --- a/latest/autoapi/neural_compressor/data/dataloaders/sampler/index.html +++ b/latest/autoapi/neural_compressor/data/dataloaders/sampler/index.html @@ -158,7 +158,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/dataloaders/tensorflow_dataloader/index.html b/latest/autoapi/neural_compressor/data/dataloaders/tensorflow_dataloader/index.html index ed50b52ce2b..66a963b2429 100644 --- a/latest/autoapi/neural_compressor/data/dataloaders/tensorflow_dataloader/index.html +++ b/latest/autoapi/neural_compressor/data/dataloaders/tensorflow_dataloader/index.html @@ -167,7 +167,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/datasets/bert_dataset/index.html b/latest/autoapi/neural_compressor/data/datasets/bert_dataset/index.html index 5cf7e29cd97..fff1db21063 100644 --- a/latest/autoapi/neural_compressor/data/datasets/bert_dataset/index.html +++ b/latest/autoapi/neural_compressor/data/datasets/bert_dataset/index.html @@ -305,7 +305,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/datasets/coco_dataset/index.html b/latest/autoapi/neural_compressor/data/datasets/coco_dataset/index.html index aa874aee33d..2c7364795a5 100644 --- a/latest/autoapi/neural_compressor/data/datasets/coco_dataset/index.html +++ b/latest/autoapi/neural_compressor/data/datasets/coco_dataset/index.html @@ -199,7 +199,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/datasets/dataset/index.html b/latest/autoapi/neural_compressor/data/datasets/dataset/index.html index fd195a9ad28..e8f8a0b8446 100644 --- a/latest/autoapi/neural_compressor/data/datasets/dataset/index.html +++ b/latest/autoapi/neural_compressor/data/datasets/dataset/index.html @@ -723,7 +723,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/datasets/dummy_dataset/index.html b/latest/autoapi/neural_compressor/data/datasets/dummy_dataset/index.html index eb00f826832..5de282856b6 100644 --- a/latest/autoapi/neural_compressor/data/datasets/dummy_dataset/index.html +++ b/latest/autoapi/neural_compressor/data/datasets/dummy_dataset/index.html @@ -128,7 +128,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/datasets/dummy_dataset_v2/index.html b/latest/autoapi/neural_compressor/data/datasets/dummy_dataset_v2/index.html index 9018e0bce11..b2cba9a0691 100644 --- a/latest/autoapi/neural_compressor/data/datasets/dummy_dataset_v2/index.html +++ b/latest/autoapi/neural_compressor/data/datasets/dummy_dataset_v2/index.html @@ -138,7 +138,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/datasets/imagenet_dataset/index.html b/latest/autoapi/neural_compressor/data/datasets/imagenet_dataset/index.html index bb03c2a4715..d3e49da064d 100644 --- a/latest/autoapi/neural_compressor/data/datasets/imagenet_dataset/index.html +++ b/latest/autoapi/neural_compressor/data/datasets/imagenet_dataset/index.html @@ -179,7 +179,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/datasets/index.html b/latest/autoapi/neural_compressor/data/datasets/index.html index 71ae52ad5ad..490650789fe 100644 --- a/latest/autoapi/neural_compressor/data/datasets/index.html +++ b/latest/autoapi/neural_compressor/data/datasets/index.html @@ -120,7 +120,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/datasets/style_transfer_dataset/index.html b/latest/autoapi/neural_compressor/data/datasets/style_transfer_dataset/index.html index 8512ee17032..2b68f0afa33 100644 --- a/latest/autoapi/neural_compressor/data/datasets/style_transfer_dataset/index.html +++ b/latest/autoapi/neural_compressor/data/datasets/style_transfer_dataset/index.html @@ -129,7 +129,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/filters/coco_filter/index.html b/latest/autoapi/neural_compressor/data/filters/coco_filter/index.html index 332d13f5208..134f1180312 100644 --- a/latest/autoapi/neural_compressor/data/filters/coco_filter/index.html +++ b/latest/autoapi/neural_compressor/data/filters/coco_filter/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/filters/filter/index.html b/latest/autoapi/neural_compressor/data/filters/filter/index.html index 7d98dee35e6..85835faf20f 100644 --- a/latest/autoapi/neural_compressor/data/filters/filter/index.html +++ b/latest/autoapi/neural_compressor/data/filters/filter/index.html @@ -219,7 +219,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/filters/index.html b/latest/autoapi/neural_compressor/data/filters/index.html index 30cadf410f6..51025508167 100644 --- a/latest/autoapi/neural_compressor/data/filters/index.html +++ b/latest/autoapi/neural_compressor/data/filters/index.html @@ -115,7 +115,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/index.html b/latest/autoapi/neural_compressor/data/index.html index 879ed0d5cac..9cd1249fa05 100644 --- a/latest/autoapi/neural_compressor/data/index.html +++ b/latest/autoapi/neural_compressor/data/index.html @@ -116,7 +116,7 @@

SubpackagesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/transforms/imagenet_transform/index.html b/latest/autoapi/neural_compressor/data/transforms/imagenet_transform/index.html index a605455b739..5c513ceb4e9 100644 --- a/latest/autoapi/neural_compressor/data/transforms/imagenet_transform/index.html +++ b/latest/autoapi/neural_compressor/data/transforms/imagenet_transform/index.html @@ -317,7 +317,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/transforms/index.html b/latest/autoapi/neural_compressor/data/transforms/index.html index 0659bd17838..01fb969f298 100644 --- a/latest/autoapi/neural_compressor/data/transforms/index.html +++ b/latest/autoapi/neural_compressor/data/transforms/index.html @@ -117,7 +117,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/transforms/postprocess/index.html b/latest/autoapi/neural_compressor/data/transforms/postprocess/index.html index 62ba446f0b5..cd3d6720184 100644 --- a/latest/autoapi/neural_compressor/data/transforms/postprocess/index.html +++ b/latest/autoapi/neural_compressor/data/transforms/postprocess/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/transforms/tokenization/index.html b/latest/autoapi/neural_compressor/data/transforms/tokenization/index.html index 260fca983e8..61c4c99ae11 100644 --- a/latest/autoapi/neural_compressor/data/transforms/tokenization/index.html +++ b/latest/autoapi/neural_compressor/data/transforms/tokenization/index.html @@ -186,7 +186,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/data/transforms/transform/index.html b/latest/autoapi/neural_compressor/data/transforms/transform/index.html index 6c3f83fef6f..78ec3aa7ab0 100644 --- a/latest/autoapi/neural_compressor/data/transforms/transform/index.html +++ b/latest/autoapi/neural_compressor/data/transforms/transform/index.html @@ -1267,7 +1267,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/index.html b/latest/autoapi/neural_compressor/index.html index fe7e8b6a188..91960517890 100644 --- a/latest/autoapi/neural_compressor/index.html +++ b/latest/autoapi/neural_compressor/index.html @@ -138,7 +138,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/metric/bleu/index.html b/latest/autoapi/neural_compressor/metric/bleu/index.html index 875d417c943..d7fa3c82f7d 100644 --- a/latest/autoapi/neural_compressor/metric/bleu/index.html +++ b/latest/autoapi/neural_compressor/metric/bleu/index.html @@ -203,7 +203,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/metric/bleu_util/index.html b/latest/autoapi/neural_compressor/metric/bleu_util/index.html index 8b30d3e895b..a3f233d37d0 100644 --- a/latest/autoapi/neural_compressor/metric/bleu_util/index.html +++ b/latest/autoapi/neural_compressor/metric/bleu_util/index.html @@ -145,7 +145,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/metric/coco_label_map/index.html b/latest/autoapi/neural_compressor/metric/coco_label_map/index.html index 43fa447939c..e265b7d2a61 100644 --- a/latest/autoapi/neural_compressor/metric/coco_label_map/index.html +++ b/latest/autoapi/neural_compressor/metric/coco_label_map/index.html @@ -106,7 +106,7 @@ Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/metric/coco_tools/index.html b/latest/autoapi/neural_compressor/metric/coco_tools/index.html index 88503f54f19..1034068e43b 100644 --- a/latest/autoapi/neural_compressor/metric/coco_tools/index.html +++ b/latest/autoapi/neural_compressor/metric/coco_tools/index.html @@ -315,7 +315,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/metric/evaluate_squad/index.html b/latest/autoapi/neural_compressor/metric/evaluate_squad/index.html index 92736f0483f..80f5d1265f3 100644 --- a/latest/autoapi/neural_compressor/metric/evaluate_squad/index.html +++ b/latest/autoapi/neural_compressor/metric/evaluate_squad/index.html @@ -204,7 +204,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/metric/f1/index.html b/latest/autoapi/neural_compressor/metric/f1/index.html index cbee6fe9973..422727c3a00 100644 --- a/latest/autoapi/neural_compressor/metric/f1/index.html +++ b/latest/autoapi/neural_compressor/metric/f1/index.html @@ -215,7 +215,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/metric/index.html b/latest/autoapi/neural_compressor/metric/index.html index 4809d128b5d..3fe822bffe9 100644 --- a/latest/autoapi/neural_compressor/metric/index.html +++ b/latest/autoapi/neural_compressor/metric/index.html @@ -120,7 +120,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/metric/metric/index.html b/latest/autoapi/neural_compressor/metric/metric/index.html index a8cf764ef17..7a4db5f8c8d 100644 --- a/latest/autoapi/neural_compressor/metric/metric/index.html +++ b/latest/autoapi/neural_compressor/metric/metric/index.html @@ -643,7 +643,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/mix_precision/index.html b/latest/autoapi/neural_compressor/mix_precision/index.html index dc9f66cdd35..60aac00c0c9 100644 --- a/latest/autoapi/neural_compressor/mix_precision/index.html +++ b/latest/autoapi/neural_compressor/mix_precision/index.html @@ -176,7 +176,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/model/base_model/index.html b/latest/autoapi/neural_compressor/model/base_model/index.html index 394ac998770..d76f7e73fed 100644 --- a/latest/autoapi/neural_compressor/model/base_model/index.html +++ b/latest/autoapi/neural_compressor/model/base_model/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/model/index.html b/latest/autoapi/neural_compressor/model/index.html index f6084be45c3..5bad60f3e62 100644 --- a/latest/autoapi/neural_compressor/model/index.html +++ b/latest/autoapi/neural_compressor/model/index.html @@ -121,7 +121,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/model/keras_model/index.html b/latest/autoapi/neural_compressor/model/keras_model/index.html index 6084fa21912..6741b048d4a 100644 --- a/latest/autoapi/neural_compressor/model/keras_model/index.html +++ b/latest/autoapi/neural_compressor/model/keras_model/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/model/model/index.html b/latest/autoapi/neural_compressor/model/model/index.html index 05a83fe3762..f016afd1e53 100644 --- a/latest/autoapi/neural_compressor/model/model/index.html +++ b/latest/autoapi/neural_compressor/model/model/index.html @@ -147,7 +147,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/model/mxnet_model/index.html b/latest/autoapi/neural_compressor/model/mxnet_model/index.html index bf2c558ea14..ce96f6e8caa 100644 --- a/latest/autoapi/neural_compressor/model/mxnet_model/index.html +++ b/latest/autoapi/neural_compressor/model/mxnet_model/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/model/nets_factory/index.html b/latest/autoapi/neural_compressor/model/nets_factory/index.html index eae1a4037db..59420533d50 100644 --- a/latest/autoapi/neural_compressor/model/nets_factory/index.html +++ b/latest/autoapi/neural_compressor/model/nets_factory/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/model/onnx_model/index.html b/latest/autoapi/neural_compressor/model/onnx_model/index.html index b626069deb9..2876ddaa703 100644 --- a/latest/autoapi/neural_compressor/model/onnx_model/index.html +++ b/latest/autoapi/neural_compressor/model/onnx_model/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/model/tensorflow_model/index.html b/latest/autoapi/neural_compressor/model/tensorflow_model/index.html index 8a3bc1d3dfd..db8e64c25a7 100644 --- a/latest/autoapi/neural_compressor/model/tensorflow_model/index.html +++ b/latest/autoapi/neural_compressor/model/tensorflow_model/index.html @@ -500,7 +500,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/model/torch_model/index.html b/latest/autoapi/neural_compressor/model/torch_model/index.html index ada89dd8246..323d475d186 100644 --- a/latest/autoapi/neural_compressor/model/torch_model/index.html +++ b/latest/autoapi/neural_compressor/model/torch_model/index.html @@ -152,7 +152,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/objective/index.html b/latest/autoapi/neural_compressor/objective/index.html index f79005abd47..6548c865d4d 100644 --- a/latest/autoapi/neural_compressor/objective/index.html +++ b/latest/autoapi/neural_compressor/objective/index.html @@ -233,7 +233,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/index.html b/latest/autoapi/neural_compressor/profiling/index.html index c6bd709dd8b..12bfd9b1aa0 100644 --- a/latest/autoapi/neural_compressor/profiling/index.html +++ b/latest/autoapi/neural_compressor/profiling/index.html @@ -106,7 +106,7 @@ Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/parser/factory/index.html b/latest/autoapi/neural_compressor/profiling/parser/factory/index.html index 6cdec25e0a5..50ee6418489 100644 --- a/latest/autoapi/neural_compressor/profiling/parser/factory/index.html +++ b/latest/autoapi/neural_compressor/profiling/parser/factory/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/parser/onnx_parser/factory/index.html b/latest/autoapi/neural_compressor/profiling/parser/onnx_parser/factory/index.html index 68fc6e9b4a1..ba612e721f0 100644 --- a/latest/autoapi/neural_compressor/profiling/parser/onnx_parser/factory/index.html +++ b/latest/autoapi/neural_compressor/profiling/parser/onnx_parser/factory/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/parser/onnx_parser/parser/index.html b/latest/autoapi/neural_compressor/profiling/parser/onnx_parser/parser/index.html index 2aa3d77aa23..91420f3f41f 100644 --- a/latest/autoapi/neural_compressor/profiling/parser/onnx_parser/parser/index.html +++ b/latest/autoapi/neural_compressor/profiling/parser/onnx_parser/parser/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/parser/parser/index.html b/latest/autoapi/neural_compressor/profiling/parser/parser/index.html index 244d5018fe2..ea2a1e56ec2 100644 --- a/latest/autoapi/neural_compressor/profiling/parser/parser/index.html +++ b/latest/autoapi/neural_compressor/profiling/parser/parser/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/parser/result/index.html b/latest/autoapi/neural_compressor/profiling/parser/result/index.html index 8b76c064243..efa26713d4b 100644 --- a/latest/autoapi/neural_compressor/profiling/parser/result/index.html +++ b/latest/autoapi/neural_compressor/profiling/parser/result/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/parser/tensorflow_parser/factory/index.html b/latest/autoapi/neural_compressor/profiling/parser/tensorflow_parser/factory/index.html index 3162640656b..aceacb5ade5 100644 --- a/latest/autoapi/neural_compressor/profiling/parser/tensorflow_parser/factory/index.html +++ b/latest/autoapi/neural_compressor/profiling/parser/tensorflow_parser/factory/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/parser/tensorflow_parser/parser/index.html b/latest/autoapi/neural_compressor/profiling/parser/tensorflow_parser/parser/index.html index 0df8dddd9cf..1c7c6cc509c 100644 --- a/latest/autoapi/neural_compressor/profiling/parser/tensorflow_parser/parser/index.html +++ b/latest/autoapi/neural_compressor/profiling/parser/tensorflow_parser/parser/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/profiler/factory/index.html b/latest/autoapi/neural_compressor/profiling/profiler/factory/index.html index 06254b7a793..4464583fd17 100644 --- a/latest/autoapi/neural_compressor/profiling/profiler/factory/index.html +++ b/latest/autoapi/neural_compressor/profiling/profiler/factory/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/factory/index.html b/latest/autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/factory/index.html index 2bc4cd5c811..c1db9dc25d0 100644 --- a/latest/autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/factory/index.html +++ b/latest/autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/factory/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/profiler/index.html b/latest/autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/profiler/index.html index 90c61af1f74..16046707cc5 100644 --- a/latest/autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/profiler/index.html +++ b/latest/autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/profiler/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/utils/index.html b/latest/autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/utils/index.html index 848b02991fd..f794e302ae8 100644 --- a/latest/autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/utils/index.html +++ b/latest/autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/utils/index.html @@ -137,7 +137,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/profiler/profiler/index.html b/latest/autoapi/neural_compressor/profiling/profiler/profiler/index.html index b86bac1535c..dc8d025af0d 100644 --- a/latest/autoapi/neural_compressor/profiling/profiler/profiler/index.html +++ b/latest/autoapi/neural_compressor/profiling/profiler/profiler/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/factory/index.html b/latest/autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/factory/index.html index 245bfaab5ce..c152a8e4278 100644 --- a/latest/autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/factory/index.html +++ b/latest/autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/factory/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/profiler/index.html b/latest/autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/profiler/index.html index a1c40d568b3..0c124a614d9 100644 --- a/latest/autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/profiler/index.html +++ b/latest/autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/profiler/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/utils/index.html b/latest/autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/utils/index.html index 68e059aed21..c62f65ee549 100644 --- a/latest/autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/utils/index.html +++ b/latest/autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/utils/index.html @@ -169,7 +169,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/quantization/index.html b/latest/autoapi/neural_compressor/quantization/index.html index f949f06e230..89dbb6ba734 100644 --- a/latest/autoapi/neural_compressor/quantization/index.html +++ b/latest/autoapi/neural_compressor/quantization/index.html @@ -245,7 +245,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/auto/index.html b/latest/autoapi/neural_compressor/strategy/auto/index.html index d09922c9779..ad765aabb8a 100644 --- a/latest/autoapi/neural_compressor/strategy/auto/index.html +++ b/latest/autoapi/neural_compressor/strategy/auto/index.html @@ -127,7 +127,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/auto_mixed_precision/index.html b/latest/autoapi/neural_compressor/strategy/auto_mixed_precision/index.html index f5fc4041a0e..fbcf896e2ea 100644 --- a/latest/autoapi/neural_compressor/strategy/auto_mixed_precision/index.html +++ b/latest/autoapi/neural_compressor/strategy/auto_mixed_precision/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/basic/index.html b/latest/autoapi/neural_compressor/strategy/basic/index.html index ae56dac84ac..a52357efdc7 100644 --- a/latest/autoapi/neural_compressor/strategy/basic/index.html +++ b/latest/autoapi/neural_compressor/strategy/basic/index.html @@ -127,7 +127,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/bayesian/index.html b/latest/autoapi/neural_compressor/strategy/bayesian/index.html index 293c91b7a22..12369b4e9b1 100644 --- a/latest/autoapi/neural_compressor/strategy/bayesian/index.html +++ b/latest/autoapi/neural_compressor/strategy/bayesian/index.html @@ -181,7 +181,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/conservative/index.html b/latest/autoapi/neural_compressor/strategy/conservative/index.html index d2a0f070017..175b9b49754 100644 --- a/latest/autoapi/neural_compressor/strategy/conservative/index.html +++ b/latest/autoapi/neural_compressor/strategy/conservative/index.html @@ -128,7 +128,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/exhaustive/index.html b/latest/autoapi/neural_compressor/strategy/exhaustive/index.html index 8f73928df05..f7e1aa2acf1 100644 --- a/latest/autoapi/neural_compressor/strategy/exhaustive/index.html +++ b/latest/autoapi/neural_compressor/strategy/exhaustive/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/hawq_v2/index.html b/latest/autoapi/neural_compressor/strategy/hawq_v2/index.html index c196b0585c6..3d36ef130df 100644 --- a/latest/autoapi/neural_compressor/strategy/hawq_v2/index.html +++ b/latest/autoapi/neural_compressor/strategy/hawq_v2/index.html @@ -128,7 +128,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/index.html b/latest/autoapi/neural_compressor/strategy/index.html index 0ffd0b062c0..a0b8b6e33aa 100644 --- a/latest/autoapi/neural_compressor/strategy/index.html +++ b/latest/autoapi/neural_compressor/strategy/index.html @@ -132,7 +132,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/mse/index.html b/latest/autoapi/neural_compressor/strategy/mse/index.html index 36c96f2fe11..2f47add76de 100644 --- a/latest/autoapi/neural_compressor/strategy/mse/index.html +++ b/latest/autoapi/neural_compressor/strategy/mse/index.html @@ -128,7 +128,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/mse_v2/index.html b/latest/autoapi/neural_compressor/strategy/mse_v2/index.html index fbfe5c985d9..2f205127e20 100644 --- a/latest/autoapi/neural_compressor/strategy/mse_v2/index.html +++ b/latest/autoapi/neural_compressor/strategy/mse_v2/index.html @@ -128,7 +128,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/random/index.html b/latest/autoapi/neural_compressor/strategy/random/index.html index 18049ebb672..e8eb17441cd 100644 --- a/latest/autoapi/neural_compressor/strategy/random/index.html +++ b/latest/autoapi/neural_compressor/strategy/random/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/strategy/index.html b/latest/autoapi/neural_compressor/strategy/strategy/index.html index a880f7e5b3e..9d093508dbd 100644 --- a/latest/autoapi/neural_compressor/strategy/strategy/index.html +++ b/latest/autoapi/neural_compressor/strategy/strategy/index.html @@ -161,7 +161,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/utils/constant/index.html b/latest/autoapi/neural_compressor/strategy/utils/constant/index.html index bf099cd124f..0be788a0ff1 100644 --- a/latest/autoapi/neural_compressor/strategy/utils/constant/index.html +++ b/latest/autoapi/neural_compressor/strategy/utils/constant/index.html @@ -106,7 +106,7 @@ Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/utils/index.html b/latest/autoapi/neural_compressor/strategy/utils/index.html index d8465e62a7c..dfc7f9f0a81 100644 --- a/latest/autoapi/neural_compressor/strategy/utils/index.html +++ b/latest/autoapi/neural_compressor/strategy/utils/index.html @@ -118,7 +118,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/utils/tuning_sampler/index.html b/latest/autoapi/neural_compressor/strategy/utils/tuning_sampler/index.html index 8a73eb706d9..8bea147827c 100644 --- a/latest/autoapi/neural_compressor/strategy/utils/tuning_sampler/index.html +++ b/latest/autoapi/neural_compressor/strategy/utils/tuning_sampler/index.html @@ -207,7 +207,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/utils/tuning_space/index.html b/latest/autoapi/neural_compressor/strategy/utils/tuning_space/index.html index d1f4ed98372..5b4e9d73316 100644 --- a/latest/autoapi/neural_compressor/strategy/utils/tuning_space/index.html +++ b/latest/autoapi/neural_compressor/strategy/utils/tuning_space/index.html @@ -207,7 +207,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/utils/tuning_structs/index.html b/latest/autoapi/neural_compressor/strategy/utils/tuning_structs/index.html index f9c97f9242e..a60809190d5 100644 --- a/latest/autoapi/neural_compressor/strategy/utils/tuning_structs/index.html +++ b/latest/autoapi/neural_compressor/strategy/utils/tuning_structs/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/strategy/utils/utility/index.html b/latest/autoapi/neural_compressor/strategy/utils/utility/index.html index 29e2d1a7d85..67a58093364 100644 --- a/latest/autoapi/neural_compressor/strategy/utils/utility/index.html +++ b/latest/autoapi/neural_compressor/strategy/utils/utility/index.html @@ -245,7 +245,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/template/api_doc_example/index.html b/latest/autoapi/neural_compressor/template/api_doc_example/index.html index 5e00b676380..7c5ae3b30be 100644 --- a/latest/autoapi/neural_compressor/template/api_doc_example/index.html +++ b/latest/autoapi/neural_compressor/template/api_doc_example/index.html @@ -349,7 +349,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/algorithms/index.html b/latest/autoapi/neural_compressor/tensorflow/algorithms/index.html index 70aeda72150..520adb71670 100644 --- a/latest/autoapi/neural_compressor/tensorflow/algorithms/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/algorithms/index.html @@ -115,7 +115,7 @@

SubpackagesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/calibration/index.html b/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/calibration/index.html index b42afe1fcc8..bb12c4b1e24 100644 --- a/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/calibration/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/calibration/index.html @@ -158,7 +158,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/core/index.html b/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/core/index.html index 23f348339ce..f2181ebff5f 100644 --- a/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/core/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/core/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/index.html b/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/index.html index 8950942cbaa..f5e490a6aac 100644 --- a/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/index.html @@ -116,7 +116,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/scaler/index.html b/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/scaler/index.html index a669034a90a..0d7dd8afa50 100644 --- a/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/scaler/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/algorithms/smoother/scaler/index.html @@ -156,7 +156,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/algorithms/static_quant/index.html b/latest/autoapi/neural_compressor/tensorflow/algorithms/static_quant/index.html index 681cde5a1c3..c75302182c4 100644 --- a/latest/autoapi/neural_compressor/tensorflow/algorithms/static_quant/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/algorithms/static_quant/index.html @@ -115,7 +115,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/algorithms/static_quant/keras/index.html b/latest/autoapi/neural_compressor/tensorflow/algorithms/static_quant/keras/index.html index a5e9ea872fe..3efdf6ddaaa 100644 --- a/latest/autoapi/neural_compressor/tensorflow/algorithms/static_quant/keras/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/algorithms/static_quant/keras/index.html @@ -152,7 +152,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/algorithms/static_quant/tensorflow/index.html b/latest/autoapi/neural_compressor/tensorflow/algorithms/static_quant/tensorflow/index.html index 7e7612da55a..df5e1616c02 100644 --- a/latest/autoapi/neural_compressor/tensorflow/algorithms/static_quant/tensorflow/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/algorithms/static_quant/tensorflow/index.html @@ -161,7 +161,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/index.html b/latest/autoapi/neural_compressor/tensorflow/index.html index 470e73d5a02..37d05a94ca5 100644 --- a/latest/autoapi/neural_compressor/tensorflow/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/index.html @@ -117,7 +117,7 @@

SubpackagesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/keras/index.html b/latest/autoapi/neural_compressor/tensorflow/keras/index.html index 663b6e28715..2c6d0e6dfcc 100644 --- a/latest/autoapi/neural_compressor/tensorflow/keras/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/keras/index.html @@ -115,7 +115,7 @@

SubpackagesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/keras/layers/conv2d/index.html b/latest/autoapi/neural_compressor/tensorflow/keras/layers/conv2d/index.html index 692b358a257..d1a14589a7c 100644 --- a/latest/autoapi/neural_compressor/tensorflow/keras/layers/conv2d/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/keras/layers/conv2d/index.html @@ -141,7 +141,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/keras/layers/dense/index.html b/latest/autoapi/neural_compressor/tensorflow/keras/layers/dense/index.html index 191ad3cc8eb..eb65e714f63 100644 --- a/latest/autoapi/neural_compressor/tensorflow/keras/layers/dense/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/keras/layers/dense/index.html @@ -141,7 +141,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/keras/layers/depthwise_conv2d/index.html b/latest/autoapi/neural_compressor/tensorflow/keras/layers/depthwise_conv2d/index.html index 05479ca2b9e..640fd54f9a4 100644 --- a/latest/autoapi/neural_compressor/tensorflow/keras/layers/depthwise_conv2d/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/keras/layers/depthwise_conv2d/index.html @@ -141,7 +141,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/keras/layers/index.html b/latest/autoapi/neural_compressor/tensorflow/keras/layers/index.html index 89a6c978c78..9d8e4ff0800 100644 --- a/latest/autoapi/neural_compressor/tensorflow/keras/layers/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/keras/layers/index.html @@ -119,7 +119,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/keras/layers/layer_initializer/index.html b/latest/autoapi/neural_compressor/tensorflow/keras/layers/layer_initializer/index.html index a0b8000c2c8..fabdd205880 100644 --- a/latest/autoapi/neural_compressor/tensorflow/keras/layers/layer_initializer/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/keras/layers/layer_initializer/index.html @@ -106,7 +106,7 @@ Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/keras/layers/pool2d/index.html b/latest/autoapi/neural_compressor/tensorflow/keras/layers/pool2d/index.html index eb2fa73b151..5577c48e515 100644 --- a/latest/autoapi/neural_compressor/tensorflow/keras/layers/pool2d/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/keras/layers/pool2d/index.html @@ -159,7 +159,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/keras/layers/separable_conv2d/index.html b/latest/autoapi/neural_compressor/tensorflow/keras/layers/separable_conv2d/index.html index b00b09c4de5..ca9854053aa 100644 --- a/latest/autoapi/neural_compressor/tensorflow/keras/layers/separable_conv2d/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/keras/layers/separable_conv2d/index.html @@ -141,7 +141,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/keras/quantization/config/index.html b/latest/autoapi/neural_compressor/tensorflow/keras/quantization/config/index.html index 976ccd3ce1a..176cfc6d8bb 100644 --- a/latest/autoapi/neural_compressor/tensorflow/keras/quantization/config/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/keras/quantization/config/index.html @@ -164,7 +164,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/keras/quantization/index.html b/latest/autoapi/neural_compressor/tensorflow/keras/quantization/index.html index acd91f4e824..65a823b2f42 100644 --- a/latest/autoapi/neural_compressor/tensorflow/keras/quantization/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/keras/quantization/index.html @@ -114,7 +114,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/algorithm_entry/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/algorithm_entry/index.html index 52acabeb23c..d55ff37a415 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/algorithm_entry/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/algorithm_entry/index.html @@ -170,7 +170,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/autotune/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/autotune/index.html index da027f50043..a8d1243db8f 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/autotune/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/autotune/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/config/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/config/index.html index 58996e63114..c30b3332022 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/config/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/config/index.html @@ -169,7 +169,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/index.html index e7828080d74..ec8b9c5d982 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/index.html @@ -124,7 +124,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/quantize/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/quantize/index.html index 7105a3e037f..61567fb0f60 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/quantize/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/quantize/index.html @@ -179,7 +179,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_converter/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_converter/index.html index df0dfd2dfb6..33ca9d248c6 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_converter/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_converter/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/bf16_convert/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/bf16_convert/index.html index 07aa6d1dbc7..bcc84f4954f 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/bf16_convert/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/bf16_convert/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/dequantize_cast_optimizer/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/dequantize_cast_optimizer/index.html index b4d20441135..eb5df5d259d 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/dequantize_cast_optimizer/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/dequantize_cast_optimizer/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/index.html index 07a8cd420cd..a12132e7d68 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/index.html @@ -115,7 +115,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_add_to_biasadd/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_add_to_biasadd/index.html index 0592bf502fe..abb34a02858 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_add_to_biasadd/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_add_to_biasadd/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_layout/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_layout/index.html index f2539c6b1fa..9634b72033b 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_layout/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_layout/index.html @@ -131,7 +131,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_leakyrelu/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_leakyrelu/index.html index e434b1bc5c2..c30f4f5fb4f 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_leakyrelu/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_leakyrelu/index.html @@ -141,7 +141,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_nan_to_random/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_nan_to_random/index.html index 762f3d68d2c..148db5e938c 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_nan_to_random/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_nan_to_random/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_placeholder_to_const/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_placeholder_to_const/index.html index e218d539fa1..60a5ac8661b 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_placeholder_to_const/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_placeholder_to_const/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dilated_contraction/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dilated_contraction/index.html index e806ff48084..8a2ce048587 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dilated_contraction/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dilated_contraction/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dummy_biasadd/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dummy_biasadd/index.html index 9dace5960db..74c5227f8a3 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dummy_biasadd/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dummy_biasadd/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/expanddims_optimizer/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/expanddims_optimizer/index.html index 18def618349..30307144a30 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/expanddims_optimizer/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/expanddims_optimizer/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fetch_weight_from_reshape/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fetch_weight_from_reshape/index.html index 5061290cb04..0bd851eb214 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fetch_weight_from_reshape/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fetch_weight_from_reshape/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_batch_norm/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_batch_norm/index.html index 3c207f71621..da8dcb45088 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_batch_norm/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_batch_norm/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_constant/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_constant/index.html index 3db9774427b..a03542dda8f 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_constant/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_constant/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_biasadd_add/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_biasadd_add/index.html index 02766c0564e..535768a5ede 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_biasadd_add/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_biasadd_add/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_column_wise_mul/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_column_wise_mul/index.html index d0fcd073d5a..f3055ddf02b 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_column_wise_mul/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_column_wise_mul/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_conv_with_math/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_conv_with_math/index.html index 4944bf985af..0884360bb71 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_conv_with_math/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_conv_with_math/index.html @@ -140,7 +140,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_bn/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_bn/index.html index 44a5b6b481c..b4e43c090fd 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_bn/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_bn/index.html @@ -219,7 +219,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_in/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_in/index.html index ecbeec979ec..b69542e83b7 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_in/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_in/index.html @@ -219,7 +219,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_gelu/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_gelu/index.html index 2cf67549451..b18e981edbc 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_gelu/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_gelu/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_layer_norm/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_layer_norm/index.html index 553d14be5a8..96fe5dfd81c 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_layer_norm/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_layer_norm/index.html @@ -186,7 +186,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_conv/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_conv/index.html index 015e6db8294..56e1a868b68 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_conv/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_conv/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index.html index 5b1d066d88a..d64535dcb0e 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_reshape_transpose/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_reshape_transpose/index.html index 9329c0db346..be6581f086c 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_reshape_transpose/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_reshape_transpose/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/graph_cse_optimizer/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/graph_cse_optimizer/index.html index d14a1988e5f..a1ac6ddc12e 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/graph_cse_optimizer/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/graph_cse_optimizer/index.html @@ -181,7 +181,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/grappler_pass/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/grappler_pass/index.html index eb00917fc66..0e641f6b9d3 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/grappler_pass/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/grappler_pass/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/index.html index d3f1c3fbcf2..eab77e6f853 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/index.html @@ -145,7 +145,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/insert_print_node/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/insert_print_node/index.html index 17fb9bfeb0a..ab2f4bfe990 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/insert_print_node/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/insert_print_node/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/move_squeeze_after_relu/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/move_squeeze_after_relu/index.html index e34fcfba27c..834442ddd43 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/move_squeeze_after_relu/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/move_squeeze_after_relu/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/pre_optimize/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/pre_optimize/index.html index 807fa37e6fd..01e2c989d41 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/pre_optimize/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/pre_optimize/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/remove_training_nodes/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/remove_training_nodes/index.html index 0939578705c..d79d5023261 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/remove_training_nodes/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/remove_training_nodes/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/rename_batch_norm/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/rename_batch_norm/index.html index bbe8716f8d5..098116bc937 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/rename_batch_norm/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/rename_batch_norm/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/split_shared_input/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/split_shared_input/index.html index e182e4bdf65..32af614c00a 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/split_shared_input/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/split_shared_input/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_equivalent_nodes/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_equivalent_nodes/index.html index bcccc98d2ec..2df2834dbaf 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_equivalent_nodes/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_equivalent_nodes/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_unused_nodes/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_unused_nodes/index.html index a16f6415d9a..d99f2d6a493 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_unused_nodes/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_unused_nodes/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/switch_optimizer/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/switch_optimizer/index.html index fe0d43eed2e..9dea252314f 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/switch_optimizer/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/switch_optimizer/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/graph_base/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/graph_base/index.html index a9ab6a4eae3..fbc384a2b1c 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/graph_base/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/graph_base/index.html @@ -131,7 +131,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/index.html index fc742fb82cb..a589b7fa202 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/index.html @@ -125,7 +125,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_fake_quant/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_fake_quant/index.html index fa805112ed7..56504e103cc 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_fake_quant/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_fake_quant/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_value/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_value/index.html index 1dc8481e869..1161a512388 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_value/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_value/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index.html index cbcc8c74599..e9b67a65383 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_requantize/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_requantize/index.html index c89a1a923ef..68953098d9c 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_requantize/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_requantize/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index.html index 5bfdddf1571..8ffbc8f4cc1 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_requantize/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_requantize/index.html index deecb8f369c..34f3983c50c 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_requantize/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_requantize/index.html @@ -152,7 +152,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/index.html index 430dd328795..724b62ba5fd 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/index.html @@ -123,7 +123,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/meta_op_optimizer/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/meta_op_optimizer/index.html index 5e25b6cb129..d09ab742df4 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/meta_op_optimizer/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/meta_op_optimizer/index.html @@ -126,7 +126,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_hostconst_converter/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_hostconst_converter/index.html index bb0eba9306a..f3038844e26 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_hostconst_converter/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_hostconst_converter/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_quantized_op_cse/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_quantized_op_cse/index.html index 61c752d1090..836e4e50868 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_quantized_op_cse/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_quantized_op_cse/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/scale_propagation/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/scale_propagation/index.html index c7fa234bf19..1ad0c8d3d7c 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/scale_propagation/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/scale_propagation/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/index.html index 2bbebcdfed5..c80ff303f65 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/index.html @@ -116,7 +116,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/insert_qdq_pattern/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/insert_qdq_pattern/index.html index 30102d1ffb1..a078c4e4846 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/insert_qdq_pattern/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/insert_qdq_pattern/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/merge_duplicated_qdq/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/merge_duplicated_qdq/index.html index 338ae3aa47f..7fb070207a7 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/merge_duplicated_qdq/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/merge_duplicated_qdq/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/share_qdq_y_pattern/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/share_qdq_y_pattern/index.html index 378edb8443c..7850d98735a 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/share_qdq_y_pattern/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/share_qdq_y_pattern/index.html @@ -126,7 +126,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_util/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_util/index.html index 7722ec5d722..9e588072c79 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_util/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/graph_util/index.html @@ -137,7 +137,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/index.html index 868c2f10063..78cc1e5189b 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/index.html @@ -127,7 +127,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/index.html index cfceb08c010..60c01a6e229 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/index.html @@ -128,7 +128,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_bn/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_bn/index.html index 997a6989a1e..1e297089dac 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_bn/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_bn/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_concatv2/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_concatv2/index.html index bccd5d9c5ab..1a2e2f975b0 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_concatv2/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_concatv2/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_conv/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_conv/index.html index 2cc1c52f265..bb6a914dbe9 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_conv/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_conv/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_deconv/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_deconv/index.html index 7eb0b4704df..57169551533 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_deconv/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_deconv/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_in/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_in/index.html index e4173ea56d3..fc4645d6e7e 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_in/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_in/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_matmul/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_matmul/index.html index 5bf4d832323..7b9397c111a 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_matmul/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_matmul/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_pooling/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_pooling/index.html index 9ff2c05068d..63dfae828af 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_pooling/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_pooling/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/index.html index 60c9908137a..5444109bb5a 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/index.html @@ -121,7 +121,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/optimize_qdq/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/optimize_qdq/index.html index f5bac38715c..74f30ba9fdd 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/optimize_qdq/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/optimize_qdq/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_base/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_base/index.html index a24a192bcec..c47408c136d 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_base/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_base/index.html @@ -139,7 +139,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_bn/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_bn/index.html index 7ef9640a390..85760d89117 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_bn/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_bn/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_concatv2/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_concatv2/index.html index 9f750da0b52..ca7f1571d76 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_concatv2/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_concatv2/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_conv/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_conv/index.html index 05ef5f4d158..56a2bea5f7f 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_conv/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_conv/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_for_intel_cpu/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_for_intel_cpu/index.html index f92ef59b842..8cbe4189a29 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_for_intel_cpu/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_for_intel_cpu/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_matmul/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_matmul/index.html index 49a474a7767..81feac6dcab 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_matmul/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_matmul/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_pooling/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_pooling/index.html index 85d632d821b..b7037ac264c 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_pooling/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_pooling/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph_common/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph_common/index.html index c7111f40c97..1283602050b 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph_common/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph_common/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/bias_correction/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/bias_correction/index.html index be85a28547e..cb1cc628df6 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/bias_correction/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/bias_correction/index.html @@ -135,7 +135,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/graph_transform_base/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/graph_transform_base/index.html index 30fe89f21f5..23cdfb6ce8c 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/graph_transform_base/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/graph_transform_base/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/index.html index a8a7cb6566f..3aa4294fe8a 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/index.html @@ -117,7 +117,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/insert_logging/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/insert_logging/index.html index 4f4b0ae74a0..95dfbecf539 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/insert_logging/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/insert_logging/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/rerange_quantized_concat/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/rerange_quantized_concat/index.html index 0405dcfce00..d4999bcfec9 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/rerange_quantized_concat/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/rerange_quantized_concat/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/utility/index.html b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/utility/index.html index aca83082d55..f4a09c85ba3 100644 --- a/latest/autoapi/neural_compressor/tensorflow/quantization/utils/utility/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/quantization/utils/utility/index.html @@ -408,7 +408,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/utils/constants/index.html b/latest/autoapi/neural_compressor/tensorflow/utils/constants/index.html index 307113941e6..5cc801f59d1 100644 --- a/latest/autoapi/neural_compressor/tensorflow/utils/constants/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/utils/constants/index.html @@ -106,7 +106,7 @@ Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/utils/data/index.html b/latest/autoapi/neural_compressor/tensorflow/utils/data/index.html index c869bb55294..814160d4cee 100644 --- a/latest/autoapi/neural_compressor/tensorflow/utils/data/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/utils/data/index.html @@ -213,7 +213,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/utils/index.html b/latest/autoapi/neural_compressor/tensorflow/utils/index.html index 572c60e5463..bb055c421d8 100644 --- a/latest/autoapi/neural_compressor/tensorflow/utils/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/utils/index.html @@ -118,7 +118,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/utils/model/index.html b/latest/autoapi/neural_compressor/tensorflow/utils/model/index.html index dcbe08629f1..b18f1ffc47d 100644 --- a/latest/autoapi/neural_compressor/tensorflow/utils/model/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/utils/model/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/utils/model_wrappers/index.html b/latest/autoapi/neural_compressor/tensorflow/utils/model_wrappers/index.html index 4968ae540d4..7e1983412b5 100644 --- a/latest/autoapi/neural_compressor/tensorflow/utils/model_wrappers/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/utils/model_wrappers/index.html @@ -520,7 +520,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/tensorflow/utils/utility/index.html b/latest/autoapi/neural_compressor/tensorflow/utils/utility/index.html index 5629648a9b2..9a6e6b346fb 100644 --- a/latest/autoapi/neural_compressor/tensorflow/utils/utility/index.html +++ b/latest/autoapi/neural_compressor/tensorflow/utils/utility/index.html @@ -331,7 +331,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/base_algorithm/index.html b/latest/autoapi/neural_compressor/torch/algorithms/base_algorithm/index.html index f576edbdcd3..faa191e806d 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/base_algorithm/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/base_algorithm/index.html @@ -135,7 +135,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/fp8_quant/utils/logger/index.html b/latest/autoapi/neural_compressor/torch/algorithms/fp8_quant/utils/logger/index.html index f564f97fc76..bd7aa792215 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/fp8_quant/utils/logger/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/fp8_quant/utils/logger/index.html @@ -106,7 +106,7 @@ Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/index.html b/latest/autoapi/neural_compressor/torch/algorithms/index.html index f64ac24b9bc..fe58348438a 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/index.html @@ -128,7 +128,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/index.html b/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/index.html index 511e04aaa74..48219fb8329 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/index.html @@ -116,7 +116,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/load/index.html b/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/load/index.html index 05a44b3f0aa..d95fe8dd47d 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/load/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/load/index.html @@ -212,7 +212,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/modified_pickle/index.html b/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/modified_pickle/index.html index 69517d88eb5..45fbe4d5765 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/modified_pickle/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/modified_pickle/index.html @@ -166,7 +166,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/utils/index.html b/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/utils/index.html index 484ceeba1d2..b0db95ca1f5 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/utils/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/layer_wise/utils/index.html @@ -308,7 +308,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/mixed_precision/half_precision_convert/index.html b/latest/autoapi/neural_compressor/torch/algorithms/mixed_precision/half_precision_convert/index.html index b24f08deae3..fc44397381d 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/mixed_precision/half_precision_convert/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/mixed_precision/half_precision_convert/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/mixed_precision/index.html b/latest/autoapi/neural_compressor/torch/algorithms/mixed_precision/index.html index fba5b26a184..3a1f0ce7279 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/mixed_precision/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/mixed_precision/index.html @@ -115,7 +115,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/mixed_precision/module_wrappers/index.html b/latest/autoapi/neural_compressor/torch/algorithms/mixed_precision/module_wrappers/index.html index c8eb89e63a0..42654be342f 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/mixed_precision/module_wrappers/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/mixed_precision/module_wrappers/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/mx_quant/index.html b/latest/autoapi/neural_compressor/torch/algorithms/mx_quant/index.html index 9c631f5bd37..50da9c11a31 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/mx_quant/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/mx_quant/index.html @@ -115,7 +115,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/mx_quant/mx/index.html b/latest/autoapi/neural_compressor/torch/algorithms/mx_quant/mx/index.html index 9111645299f..1b2cc0addcd 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/mx_quant/mx/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/mx_quant/mx/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/mx_quant/utils/index.html b/latest/autoapi/neural_compressor/torch/algorithms/mx_quant/utils/index.html index b4e7e68115d..5b76e5c1b21 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/mx_quant/utils/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/mx_quant/utils/index.html @@ -173,7 +173,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/core/index.html b/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/core/index.html index 206b1633e1b..eb5ecf9cb21 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/core/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/core/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/half_precision_rewriter/index.html b/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/half_precision_rewriter/index.html index 4914dadfd78..17dbea55c41 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/half_precision_rewriter/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/half_precision_rewriter/index.html @@ -274,7 +274,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/index.html b/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/index.html index 00fdc14b1f8..534e3b1d0b7 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/index.html @@ -117,7 +117,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/save_load/index.html b/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/save_load/index.html index 9cfa968c010..085c2400f06 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/save_load/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/save_load/index.html @@ -154,7 +154,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/utility/index.html b/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/utility/index.html index 4c53570659e..d7c416ee9df 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/utility/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/pt2e_quant/utility/index.html @@ -162,7 +162,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/index.html b/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/index.html index 16b1d01b8fe..1dc8df67833 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/index.html @@ -116,7 +116,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/save_load/index.html b/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/save_load/index.html index f3440b4aed8..c831dbb2845 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/save_load/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/save_load/index.html @@ -140,7 +140,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/smooth_quant/index.html b/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/smooth_quant/index.html index c7d09161f80..1b35658c8d7 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/smooth_quant/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/smooth_quant/index.html @@ -159,7 +159,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/utility/index.html b/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/utility/index.html index 588d7ff9037..464c0015121 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/utility/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/smooth_quant/utility/index.html @@ -684,7 +684,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/static_quant/index.html b/latest/autoapi/neural_compressor/torch/algorithms/static_quant/index.html index 760d449033d..3ab89e39715 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/static_quant/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/static_quant/index.html @@ -116,7 +116,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/static_quant/save_load/index.html b/latest/autoapi/neural_compressor/torch/algorithms/static_quant/save_load/index.html index eb95cff8b1a..3d64a03dbd7 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/static_quant/save_load/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/static_quant/save_load/index.html @@ -150,7 +150,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/static_quant/static_quant/index.html b/latest/autoapi/neural_compressor/torch/algorithms/static_quant/static_quant/index.html index 4f30529fcaa..34d84662172 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/static_quant/static_quant/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/static_quant/static_quant/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/static_quant/utility/index.html b/latest/autoapi/neural_compressor/torch/algorithms/static_quant/utility/index.html index 0657bb4bcdb..d17eacb185a 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/static_quant/utility/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/static_quant/utility/index.html @@ -345,7 +345,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/autoround/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/autoround/index.html index 2904c2ca2b7..ef58bf7bb0c 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/autoround/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/autoround/index.html @@ -114,7 +114,7 @@

Functions

-class neural_compressor.torch.algorithms.weight_only.autoround.AutoRoundQuantizer(quant_config: dict = {}, enable_full_range: bool = False, batch_size: int = 8, amp: bool = True, device: str = None, lr_scheduler=None, dataset: str | list | tuple | torch.utils.data.DataLoader = 'NeelNanda/pile-10k', enable_quanted_input: bool = True, enable_minmax_tuning: bool = True, lr: float = None, minmax_lr: float = None, low_gpu_mem_usage: bool = False, iters: int = 200, seqlen: int = 2048, nsamples: int = 128, sampler: str = 'rand', seed: int = 42, nblocks: int = 1, gradient_accumulate_steps: int = 1, not_use_best_mse: bool = False, dynamic_max_gap: int = -1, data_type: str = 'int', scale_dtype: str = 'fp16', quant_block_list: list = None, act_bits: int = 32, act_group_size: int = None, act_sym: bool = None, act_dynamic: bool = True, low_cpu_mem_usage: bool = False, **kwargs)[source]
+class neural_compressor.torch.algorithms.weight_only.autoround.AutoRoundQuantizer(quant_config: dict = {}, enable_full_range: bool = False, batch_size: int = 8, amp: bool = True, device: str = None, lr_scheduler=None, dataset: str | list | tuple | torch.utils.data.DataLoader = 'NeelNanda/pile-10k', enable_quanted_input: bool = True, enable_minmax_tuning: bool = True, lr: float = None, minmax_lr: float = None, low_gpu_mem_usage: bool = False, iters: int = 200, seqlen: int = 2048, nsamples: int = 128, sampler: str = 'rand', seed: int = 42, nblocks: int = 1, gradient_accumulate_steps: int = 1, not_use_best_mse: bool = False, dynamic_max_gap: int = -1, data_type: str = 'int', scale_dtype: str = 'fp16', quant_block_list: list = None, act_bits: int = 32, act_group_size: int = None, act_sym: bool = None, act_dynamic: bool = True, low_cpu_mem_usage: bool = False, export_format: str = 'itrex', **kwargs)[source]

AutoRound Quantizer.

@@ -162,7 +162,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/awq/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/awq/index.html index 2b4331f0c1c..253444295bd 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/awq/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/awq/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/gptq/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/gptq/index.html index 5c50b965a78..da478a42860 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/gptq/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/gptq/index.html @@ -239,7 +239,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/bitpack/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/bitpack/index.html index 37ccd8a828b..5128a374151 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/bitpack/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/bitpack/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/config/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/config/index.html index 0169088914c..d4e30025cb5 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/config/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/config/index.html @@ -143,7 +143,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/core/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/core/index.html index a0a19a190b7..9cc1c7834c0 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/core/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/core/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/index.html index 3cdd61b51f9..de4997c40da 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/index.html @@ -119,7 +119,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/optimizer/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/optimizer/index.html index 16292074caf..d66f3340bc4 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/optimizer/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/optimizer/index.html @@ -146,7 +146,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/qtensor/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/qtensor/index.html index c46fe3af1ba..723a47d6c69 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/qtensor/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/qtensor/index.html @@ -201,7 +201,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/quantizer/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/quantizer/index.html index d62a50b4209..4bf31cc46f2 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/quantizer/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/hqq/quantizer/index.html @@ -203,7 +203,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/index.html index 7b8d65a5b70..76a505d7c4e 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/index.html @@ -129,7 +129,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/modules/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/modules/index.html index ea43e880373..1755f473f38 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/modules/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/modules/index.html @@ -188,7 +188,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/rtn/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/rtn/index.html index 65591ca3d3b..40ae1d163e6 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/rtn/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/rtn/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/save_load/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/save_load/index.html index 998a42394a3..596207d425e 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/save_load/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/save_load/index.html @@ -104,7 +104,7 @@

Classes

Functions

- + @@ -117,13 +117,18 @@

Functions

-neural_compressor.torch.algorithms.weight_only.save_load.save(model, output_dir='./saved_results')[source]
+neural_compressor.torch.algorithms.weight_only.save_load.save(model, output_dir='./saved_results', format=LoadFormat.DEFAULT, **kwargs)[source]

Save the quantized model and config to the output path.

Parameters:

  • model (torch.nn.module) – raw fp32 model or prepared model.

  • output_dir (str, optional) – output path to save.

    • +

  • format (str, optional) – The format in which to save the model. Options include “default” and “huggingface”. Defaults to “default”.

    • +

  • kwargs – Additional arguments for specific formats. For example: +- safe_serialization (bool): Whether to use safe serialization when saving (only applicable for ‘huggingface’ format). Defaults to True. +- tokenizer (Tokenizer, optional): The tokenizer to be saved along with the model (only applicable for ‘huggingface’ format). +- max_shard_size (str, optional): The maximum size for each shard (only applicable for ‘huggingface’ format). Defaults to “5GB”.

@@ -196,7 +201,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/teq/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/teq/index.html index 70469005075..14f91a07092 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/teq/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/teq/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/utility/index.html b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/utility/index.html index 599ba1c8472..652c0cd16cf 100644 --- a/latest/autoapi/neural_compressor/torch/algorithms/weight_only/utility/index.html +++ b/latest/autoapi/neural_compressor/torch/algorithms/weight_only/utility/index.html @@ -558,7 +558,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/export/index.html b/latest/autoapi/neural_compressor/torch/export/index.html index e26e3937992..dcda6cba850 100644 --- a/latest/autoapi/neural_compressor/torch/export/index.html +++ b/latest/autoapi/neural_compressor/torch/export/index.html @@ -114,7 +114,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/export/pt2e_export/index.html b/latest/autoapi/neural_compressor/torch/export/pt2e_export/index.html index 83040e1f8da..c9cee305475 100644 --- a/latest/autoapi/neural_compressor/torch/export/pt2e_export/index.html +++ b/latest/autoapi/neural_compressor/torch/export/pt2e_export/index.html @@ -167,7 +167,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/index.html b/latest/autoapi/neural_compressor/torch/index.html index 8cbae364f92..620230c3fe1 100644 --- a/latest/autoapi/neural_compressor/torch/index.html +++ b/latest/autoapi/neural_compressor/torch/index.html @@ -117,7 +117,7 @@

SubpackagesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/quantization/algorithm_entry/index.html b/latest/autoapi/neural_compressor/torch/quantization/algorithm_entry/index.html index 4f6e4c713ac..29b6f5d41ad 100644 --- a/latest/autoapi/neural_compressor/torch/quantization/algorithm_entry/index.html +++ b/latest/autoapi/neural_compressor/torch/quantization/algorithm_entry/index.html @@ -413,7 +413,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/quantization/autotune/index.html b/latest/autoapi/neural_compressor/torch/quantization/autotune/index.html index 1eb81148b85..c16d9b9f52f 100644 --- a/latest/autoapi/neural_compressor/torch/quantization/autotune/index.html +++ b/latest/autoapi/neural_compressor/torch/quantization/autotune/index.html @@ -175,7 +175,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/quantization/config/index.html b/latest/autoapi/neural_compressor/torch/quantization/config/index.html index 1ade1b515d2..ef87f107fef 100644 --- a/latest/autoapi/neural_compressor/torch/quantization/config/index.html +++ b/latest/autoapi/neural_compressor/torch/quantization/config/index.html @@ -318,7 +318,7 @@

Module Contents
-class neural_compressor.torch.quantization.config.AutoRoundConfig(dtype: str = 'int', bits: int = 4, use_sym: bool = False, group_size: int = 128, act_bits: int = 32, act_group_size: int = None, act_sym: bool = None, act_dynamic: bool = True, enable_full_range: bool = False, batch_size: int = 8, lr_scheduler=None, enable_quanted_input: bool = True, enable_minmax_tuning: bool = True, lr: float = None, minmax_lr: float = None, low_gpu_mem_usage: bool = False, iters: int = 200, seqlen: int = 2048, nsamples: int = 128, sampler: str = 'rand', seed: int = 42, nblocks: int = 1, gradient_accumulate_steps: int = 1, not_use_best_mse: bool = False, dynamic_max_gap: int = -1, scale_dtype: str = 'fp16', use_layer_wise: bool = False, quant_block_list: list = None, white_list: List[neural_compressor.common.utils.OP_NAME_OR_MODULE_TYPE] | None = DEFAULT_WHITE_LIST)[source]
+class neural_compressor.torch.quantization.config.AutoRoundConfig(dtype: str = 'int', bits: int = 4, use_sym: bool = False, group_size: int = 128, act_bits: int = 32, act_group_size: int = None, act_sym: bool = None, act_dynamic: bool = True, enable_full_range: bool = False, batch_size: int = 8, lr_scheduler=None, enable_quanted_input: bool = True, enable_minmax_tuning: bool = True, lr: float = None, minmax_lr: float = None, low_gpu_mem_usage: bool = False, iters: int = 200, seqlen: int = 2048, nsamples: int = 128, sampler: str = 'rand', seed: int = 42, nblocks: int = 1, gradient_accumulate_steps: int = 1, not_use_best_mse: bool = False, dynamic_max_gap: int = -1, scale_dtype: str = 'fp16', use_layer_wise: bool = False, quant_block_list: list = None, export_format: str = 'itrex', white_list: List[neural_compressor.common.utils.OP_NAME_OR_MODULE_TYPE] | None = DEFAULT_WHITE_LIST)[source]

Config class for AUTOROUND.

AUTOROUND: Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs. https://arxiv.org/abs/2309.05516 @@ -521,7 +521,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/quantization/index.html b/latest/autoapi/neural_compressor/torch/quantization/index.html index 01d232f307f..9a7c3d62e53 100644 --- a/latest/autoapi/neural_compressor/torch/quantization/index.html +++ b/latest/autoapi/neural_compressor/torch/quantization/index.html @@ -116,7 +116,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/quantization/load_entry/index.html b/latest/autoapi/neural_compressor/torch/quantization/load_entry/index.html index 280330f94a7..0e7ee9e6487 100644 --- a/latest/autoapi/neural_compressor/torch/quantization/load_entry/index.html +++ b/latest/autoapi/neural_compressor/torch/quantization/load_entry/index.html @@ -173,7 +173,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/quantization/quantize/index.html b/latest/autoapi/neural_compressor/torch/quantization/quantize/index.html index 4cec08ea99a..6ae60ed17a9 100644 --- a/latest/autoapi/neural_compressor/torch/quantization/quantize/index.html +++ b/latest/autoapi/neural_compressor/torch/quantization/quantize/index.html @@ -215,7 +215,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/utils/auto_accelerator/index.html b/latest/autoapi/neural_compressor/torch/utils/auto_accelerator/index.html index a822b0d0fdf..68e06f96945 100644 --- a/latest/autoapi/neural_compressor/torch/utils/auto_accelerator/index.html +++ b/latest/autoapi/neural_compressor/torch/utils/auto_accelerator/index.html @@ -215,7 +215,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/utils/constants/index.html b/latest/autoapi/neural_compressor/torch/utils/constants/index.html index 147555e269d..177c9b71071 100644 --- a/latest/autoapi/neural_compressor/torch/utils/constants/index.html +++ b/latest/autoapi/neural_compressor/torch/utils/constants/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/utils/environ/index.html b/latest/autoapi/neural_compressor/torch/utils/environ/index.html index 8768343437e..27be96d6f05 100644 --- a/latest/autoapi/neural_compressor/torch/utils/environ/index.html +++ b/latest/autoapi/neural_compressor/torch/utils/environ/index.html @@ -202,7 +202,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/utils/index.html b/latest/autoapi/neural_compressor/torch/utils/index.html index ef3ef876854..3056c0aff99 100644 --- a/latest/autoapi/neural_compressor/torch/utils/index.html +++ b/latest/autoapi/neural_compressor/torch/utils/index.html @@ -117,7 +117,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/torch/utils/utility/index.html b/latest/autoapi/neural_compressor/torch/utils/utility/index.html index f7d76018589..6cb76e29ec5 100644 --- a/latest/autoapi/neural_compressor/torch/utils/utility/index.html +++ b/latest/autoapi/neural_compressor/torch/utils/utility/index.html @@ -334,7 +334,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/training/index.html b/latest/autoapi/neural_compressor/training/index.html index cc6d90873a8..449daf6b562 100644 --- a/latest/autoapi/neural_compressor/training/index.html +++ b/latest/autoapi/neural_compressor/training/index.html @@ -304,7 +304,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/transformers/quantization/utils/index.html b/latest/autoapi/neural_compressor/transformers/quantization/utils/index.html index f1ed9d8168d..30bc6073322 100644 --- a/latest/autoapi/neural_compressor/transformers/quantization/utils/index.html +++ b/latest/autoapi/neural_compressor/transformers/quantization/utils/index.html @@ -106,7 +106,7 @@ Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/transformers/utils/index.html b/latest/autoapi/neural_compressor/transformers/utils/index.html index 5a4d47ffcb3..955c43c53e0 100644 --- a/latest/autoapi/neural_compressor/transformers/utils/index.html +++ b/latest/autoapi/neural_compressor/transformers/utils/index.html @@ -114,7 +114,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/transformers/utils/quantization_config/index.html b/latest/autoapi/neural_compressor/transformers/utils/quantization_config/index.html index d5db2873eca..e42b7a0759d 100644 --- a/latest/autoapi/neural_compressor/transformers/utils/quantization_config/index.html +++ b/latest/autoapi/neural_compressor/transformers/utils/quantization_config/index.html @@ -187,7 +187,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/collect_layer_histogram/index.html b/latest/autoapi/neural_compressor/utils/collect_layer_histogram/index.html index 03d939de4dc..32077ff8a2b 100644 --- a/latest/autoapi/neural_compressor/utils/collect_layer_histogram/index.html +++ b/latest/autoapi/neural_compressor/utils/collect_layer_histogram/index.html @@ -128,7 +128,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/constant/index.html b/latest/autoapi/neural_compressor/utils/constant/index.html index 3dde1ec8e42..a3694cedde6 100644 --- a/latest/autoapi/neural_compressor/utils/constant/index.html +++ b/latest/autoapi/neural_compressor/utils/constant/index.html @@ -106,7 +106,7 @@ Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/create_obj_from_config/index.html b/latest/autoapi/neural_compressor/utils/create_obj_from_config/index.html index 0050589fa45..a32d7a046e3 100644 --- a/latest/autoapi/neural_compressor/utils/create_obj_from_config/index.html +++ b/latest/autoapi/neural_compressor/utils/create_obj_from_config/index.html @@ -242,7 +242,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/export/index.html b/latest/autoapi/neural_compressor/utils/export/index.html index 0d2b34ebdc0..25de34ebb82 100644 --- a/latest/autoapi/neural_compressor/utils/export/index.html +++ b/latest/autoapi/neural_compressor/utils/export/index.html @@ -116,7 +116,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/export/qlinear2qdq/index.html b/latest/autoapi/neural_compressor/utils/export/qlinear2qdq/index.html index 87b78297ac8..6cdd360c47a 100644 --- a/latest/autoapi/neural_compressor/utils/export/qlinear2qdq/index.html +++ b/latest/autoapi/neural_compressor/utils/export/qlinear2qdq/index.html @@ -147,7 +147,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/export/tf2onnx/index.html b/latest/autoapi/neural_compressor/utils/export/tf2onnx/index.html index 7494377a6d6..f964a06a5d0 100644 --- a/latest/autoapi/neural_compressor/utils/export/tf2onnx/index.html +++ b/latest/autoapi/neural_compressor/utils/export/tf2onnx/index.html @@ -158,7 +158,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/export/torch2onnx/index.html b/latest/autoapi/neural_compressor/utils/export/torch2onnx/index.html index f1f46a03df6..727beae3c23 100644 --- a/latest/autoapi/neural_compressor/utils/export/torch2onnx/index.html +++ b/latest/autoapi/neural_compressor/utils/export/torch2onnx/index.html @@ -268,7 +268,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/index.html b/latest/autoapi/neural_compressor/utils/index.html index 2debf9cfb85..7902012c582 100644 --- a/latest/autoapi/neural_compressor/utils/index.html +++ b/latest/autoapi/neural_compressor/utils/index.html @@ -131,7 +131,7 @@

SubmodulesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/kl_divergence/index.html b/latest/autoapi/neural_compressor/utils/kl_divergence/index.html index b11ca7290a7..35c9389574b 100644 --- a/latest/autoapi/neural_compressor/utils/kl_divergence/index.html +++ b/latest/autoapi/neural_compressor/utils/kl_divergence/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/load_huggingface/index.html b/latest/autoapi/neural_compressor/utils/load_huggingface/index.html index aa84f11278e..108c5691c69 100644 --- a/latest/autoapi/neural_compressor/utils/load_huggingface/index.html +++ b/latest/autoapi/neural_compressor/utils/load_huggingface/index.html @@ -168,7 +168,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/logger/index.html b/latest/autoapi/neural_compressor/utils/logger/index.html index 12a2c742865..c7c856df073 100644 --- a/latest/autoapi/neural_compressor/utils/logger/index.html +++ b/latest/autoapi/neural_compressor/utils/logger/index.html @@ -195,7 +195,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/options/index.html b/latest/autoapi/neural_compressor/utils/options/index.html index abd3668b10d..1ec499d4884 100644 --- a/latest/autoapi/neural_compressor/utils/options/index.html +++ b/latest/autoapi/neural_compressor/utils/options/index.html @@ -125,7 +125,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/pytorch/index.html b/latest/autoapi/neural_compressor/utils/pytorch/index.html index 614b75aad39..1ef54139147 100644 --- a/latest/autoapi/neural_compressor/utils/pytorch/index.html +++ b/latest/autoapi/neural_compressor/utils/pytorch/index.html @@ -214,7 +214,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/utility/index.html b/latest/autoapi/neural_compressor/utils/utility/index.html index a23bf5ac9fa..00feb690885 100644 --- a/latest/autoapi/neural_compressor/utils/utility/index.html +++ b/latest/autoapi/neural_compressor/utils/utility/index.html @@ -838,7 +838,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/utils/weights_details/index.html b/latest/autoapi/neural_compressor/utils/weights_details/index.html index 9ed7e442abf..1556cb54f28 100644 --- a/latest/autoapi/neural_compressor/utils/weights_details/index.html +++ b/latest/autoapi/neural_compressor/utils/weights_details/index.html @@ -134,7 +134,7 @@

Module ContentsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/autoapi/neural_compressor/version/index.html b/latest/autoapi/neural_compressor/version/index.html index 0434ba64cba..b52d8669006 100644 --- a/latest/autoapi/neural_compressor/version/index.html +++ b/latest/autoapi/neural_compressor/version/index.html @@ -106,7 +106,7 @@ Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/build_docs/source/index.html b/latest/docs/build_docs/source/index.html index 22e2a959a4f..563b3263952 100644 --- a/latest/docs/build_docs/source/index.html +++ b/latest/docs/build_docs/source/index.html @@ -114,7 +114,7 @@

Sections Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/2x_user_guide.html b/latest/docs/source/2x_user_guide.html index 105c30ab13e..df9c10b156e 100644 --- a/latest/docs/source/2x_user_guide.html +++ b/latest/docs/source/2x_user_guide.html @@ -176,7 +176,7 @@

Advanced TopicsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/PT_DynamicQuant.html b/latest/docs/source/3x/PT_DynamicQuant.html index cd320cc5512..75a29672397 100644 --- a/latest/docs/source/3x/PT_DynamicQuant.html +++ b/latest/docs/source/3x/PT_DynamicQuant.html @@ -146,7 +146,7 @@

Examples Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/PT_FP8Quant.html b/latest/docs/source/3x/PT_FP8Quant.html index ebd2405ec76..5fe9cd92e34 100644 --- a/latest/docs/source/3x/PT_FP8Quant.html +++ b/latest/docs/source/3x/PT_FP8Quant.html @@ -226,7 +226,7 @@

Examples Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/PT_MXQuant.html b/latest/docs/source/3x/PT_MXQuant.html index ecd7e28b5f7..b95af68f910 100644 --- a/latest/docs/source/3x/PT_MXQuant.html +++ b/latest/docs/source/3x/PT_MXQuant.html @@ -222,7 +222,7 @@

ReferenceSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/PT_MixedPrecision.html b/latest/docs/source/3x/PT_MixedPrecision.html index acee0af7d60..61db1c74f8c 100644 --- a/latest/docs/source/3x/PT_MixedPrecision.html +++ b/latest/docs/source/3x/PT_MixedPrecision.html @@ -218,7 +218,7 @@

Examples Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/PT_SmoothQuant.html b/latest/docs/source/3x/PT_SmoothQuant.html index 1dee97b35cb..e26a1e5be73 100644 --- a/latest/docs/source/3x/PT_SmoothQuant.html +++ b/latest/docs/source/3x/PT_SmoothQuant.html @@ -402,7 +402,7 @@

Supported Framework MatrixSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/PT_StaticQuant.html b/latest/docs/source/3x/PT_StaticQuant.html index 899c65982f0..4e7500d006a 100644 --- a/latest/docs/source/3x/PT_StaticQuant.html +++ b/latest/docs/source/3x/PT_StaticQuant.html @@ -208,7 +208,7 @@

Model Examples with PT2ESphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/PT_WeightOnlyQuant.html b/latest/docs/source/3x/PT_WeightOnlyQuant.html index 32a88000c65..faffe37f64a 100644 --- a/latest/docs/source/3x/PT_WeightOnlyQuant.html +++ b/latest/docs/source/3x/PT_WeightOnlyQuant.html @@ -737,7 +737,7 @@

ReferenceSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/PyTorch.html b/latest/docs/source/3x/PyTorch.html index 7ac26c27d57..87d0ab9fef9 100644 --- a/latest/docs/source/3x/PyTorch.html +++ b/latest/docs/source/3x/PyTorch.html @@ -382,7 +382,7 @@

Common ProblemsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/TF_Quant.html b/latest/docs/source/3x/TF_Quant.html index 05ccdb960f0..fc60ebc5602 100644 --- a/latest/docs/source/3x/TF_Quant.html +++ b/latest/docs/source/3x/TF_Quant.html @@ -222,7 +222,7 @@

Examples Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/TF_SQ.html b/latest/docs/source/3x/TF_SQ.html index 28f4c4f7381..b9f755ce514 100644 --- a/latest/docs/source/3x/TF_SQ.html +++ b/latest/docs/source/3x/TF_SQ.html @@ -162,7 +162,7 @@

Examples Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/TensorFlow.html b/latest/docs/source/3x/TensorFlow.html index 3386ccd4fd7..6eefb7541f9 100644 --- a/latest/docs/source/3x/TensorFlow.html +++ b/latest/docs/source/3x/TensorFlow.html @@ -331,7 +331,7 @@

Backend and DeviceSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/autotune.html b/latest/docs/source/3x/autotune.html index e6321da7c0e..86468dc0788 100644 --- a/latest/docs/source/3x/autotune.html +++ b/latest/docs/source/3x/autotune.html @@ -187,7 +187,7 @@

Working with Tensorflow ModelSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/benchmark.html b/latest/docs/source/3x/benchmark.html index 744982168b0..e1a48ca223a 100644 --- a/latest/docs/source/3x/benchmark.html +++ b/latest/docs/source/3x/benchmark.html @@ -202,7 +202,7 @@

Demo usageSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/client_quant.html b/latest/docs/source/3x/client_quant.html index 0e820ed0a35..994a6ff58b6 100644 --- a/latest/docs/source/3x/client_quant.html +++ b/latest/docs/source/3x/client_quant.html @@ -140,7 +140,7 @@

Get StartedSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/design.html b/latest/docs/source/3x/design.html index 99039a29267..2864cb41b4a 100644 --- a/latest/docs/source/3x/design.html +++ b/latest/docs/source/3x/design.html @@ -116,7 +116,7 @@

WorkflowsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/gaudi_version_map.html b/latest/docs/source/3x/gaudi_version_map.html index bc0e631a374..5202fd6d284 100644 --- a/latest/docs/source/3x/gaudi_version_map.html +++ b/latest/docs/source/3x/gaudi_version_map.html @@ -118,7 +118,7 @@

Version mapping between Intel Neural Compressor to Gaudi Software StackSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/llm_recipes.html b/latest/docs/source/3x/llm_recipes.html index 5db1414363b..5c38dffc8f4 100644 --- a/latest/docs/source/3x/llm_recipes.html +++ b/latest/docs/source/3x/llm_recipes.html @@ -102,7 +102,7 @@ Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/3x/quantization.html b/latest/docs/source/3x/quantization.html index 255b151beeb..6a33f81635f 100644 --- a/latest/docs/source/3x/quantization.html +++ b/latest/docs/source/3x/quantization.html @@ -435,7 +435,7 @@

ReferenceSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/CODE_OF_CONDUCT.html b/latest/docs/source/CODE_OF_CONDUCT.html index ca3d66dfe7f..a9005a88772 100644 --- a/latest/docs/source/CODE_OF_CONDUCT.html +++ b/latest/docs/source/CODE_OF_CONDUCT.html @@ -182,7 +182,7 @@

AttributionSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/CONTRIBUTING.html b/latest/docs/source/CONTRIBUTING.html index 19178e41ac4..504f76bad97 100644 --- a/latest/docs/source/CONTRIBUTING.html +++ b/latest/docs/source/CONTRIBUTING.html @@ -175,7 +175,7 @@

Contributor Covenant Code of ConductSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/FX.html b/latest/docs/source/FX.html index dccee9c6bc6..2556b327afe 100644 --- a/latest/docs/source/FX.html +++ b/latest/docs/source/FX.html @@ -252,7 +252,7 @@

Static Quantization & Quantization Aware TrainingSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/SECURITY.html b/latest/docs/source/SECURITY.html index 94ebc7c0246..bb7a2990ffc 100644 --- a/latest/docs/source/SECURITY.html +++ b/latest/docs/source/SECURITY.html @@ -117,7 +117,7 @@

Report a VulnerabilitySphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/Welcome.html b/latest/docs/source/Welcome.html index f1d2385a23c..0ef2f214ba9 100644 --- a/latest/docs/source/Welcome.html +++ b/latest/docs/source/Welcome.html @@ -324,7 +324,7 @@

CommunicationSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/adaptor.html b/latest/docs/source/adaptor.html index ee251bd9cf1..be3d88937f9 100644 --- a/latest/docs/source/adaptor.html +++ b/latest/docs/source/adaptor.html @@ -273,7 +273,7 @@

Implement ONNXRTAdaptor ClassSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/add_new_adaptor.html b/latest/docs/source/add_new_adaptor.html index 008c468a90a..756fc12621d 100644 --- a/latest/docs/source/add_new_adaptor.html +++ b/latest/docs/source/add_new_adaptor.html @@ -263,7 +263,7 @@

Calculate the data range and generate quantized modelSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/add_new_data_type.html b/latest/docs/source/add_new_data_type.html index e970f8d3861..d1fec10862f 100644 --- a/latest/docs/source/add_new_data_type.html +++ b/latest/docs/source/add_new_data_type.html @@ -264,7 +264,7 @@

Summary Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/adaptor.html b/latest/docs/source/api-doc/adaptor.html index 0a1386651b9..c33a11d205b 100644 --- a/latest/docs/source/api-doc/adaptor.html +++ b/latest/docs/source/api-doc/adaptor.html @@ -112,7 +112,7 @@

Adaptor Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/adaptor/onnxrt.html b/latest/docs/source/api-doc/adaptor/onnxrt.html index e07696d257b..a6322195b36 100644 --- a/latest/docs/source/api-doc/adaptor/onnxrt.html +++ b/latest/docs/source/api-doc/adaptor/onnxrt.html @@ -118,7 +118,7 @@

ONNX RuntimeSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/adaptor/torch_utils.html b/latest/docs/source/api-doc/adaptor/torch_utils.html index 4753020046a..884daabce6e 100644 --- a/latest/docs/source/api-doc/adaptor/torch_utils.html +++ b/latest/docs/source/api-doc/adaptor/torch_utils.html @@ -122,7 +122,7 @@

Torch UtilsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/api_2.html b/latest/docs/source/api-doc/api_2.html index 9dbc38ddf67..abe29d2d1ed 100644 --- a/latest/docs/source/api-doc/api_2.html +++ b/latest/docs/source/api-doc/api_2.html @@ -152,7 +152,7 @@

2.0 APISphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/api_3.html b/latest/docs/source/api-doc/api_3.html index f5fd3f94366..1aa3036ce28 100644 --- a/latest/docs/source/api-doc/api_3.html +++ b/latest/docs/source/api-doc/api_3.html @@ -146,7 +146,7 @@

3.0 APISphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/api_doc_example.html b/latest/docs/source/api-doc/api_doc_example.html index 683d317189a..3cf378b7f84 100644 --- a/latest/docs/source/api-doc/api_doc_example.html +++ b/latest/docs/source/api-doc/api_doc_example.html @@ -135,7 +135,7 @@

API Document ExampleSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/apis.html b/latest/docs/source/api-doc/apis.html index 8f70a8f08ec..655022a29e1 100644 --- a/latest/docs/source/api-doc/apis.html +++ b/latest/docs/source/api-doc/apis.html @@ -124,7 +124,7 @@

APIs< Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/benchmark.html b/latest/docs/source/api-doc/benchmark.html index 2bfe10ee1ce..95be1498c12 100644 --- a/latest/docs/source/api-doc/benchmark.html +++ b/latest/docs/source/api-doc/benchmark.html @@ -132,7 +132,7 @@

BenchmarkSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/compression.html b/latest/docs/source/api-doc/compression.html index 2d122ce7897..8a8b6909b74 100644 --- a/latest/docs/source/api-doc/compression.html +++ b/latest/docs/source/api-doc/compression.html @@ -139,7 +139,7 @@

CompressionSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/config.html b/latest/docs/source/api-doc/config.html index 66f23b85f7c..110fd6280a4 100644 --- a/latest/docs/source/api-doc/config.html +++ b/latest/docs/source/api-doc/config.html @@ -135,7 +135,7 @@

Config< Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/mix_precision.html b/latest/docs/source/api-doc/mix_precision.html index 6106f32880a..1071c2f4674 100644 --- a/latest/docs/source/api-doc/mix_precision.html +++ b/latest/docs/source/api-doc/mix_precision.html @@ -135,7 +135,7 @@

Mix PrecisionSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/model.html b/latest/docs/source/api-doc/model.html index 706b0dca056..d51c5f9d379 100644 --- a/latest/docs/source/api-doc/model.html +++ b/latest/docs/source/api-doc/model.html @@ -145,7 +145,7 @@

ModelSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/objective.html b/latest/docs/source/api-doc/objective.html index 9e5e0539a77..615ffb205cc 100644 --- a/latest/docs/source/api-doc/objective.html +++ b/latest/docs/source/api-doc/objective.html @@ -135,7 +135,7 @@

ObjectiveSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/quantization.html b/latest/docs/source/api-doc/quantization.html index 7b4467ab2b7..21043856853 100644 --- a/latest/docs/source/api-doc/quantization.html +++ b/latest/docs/source/api-doc/quantization.html @@ -135,7 +135,7 @@

QuantizationSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/strategy.html b/latest/docs/source/api-doc/strategy.html index f5cdcb6fc7b..d5442975160 100644 --- a/latest/docs/source/api-doc/strategy.html +++ b/latest/docs/source/api-doc/strategy.html @@ -145,7 +145,7 @@

Strategy Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/tf_quantization_autotune.html b/latest/docs/source/api-doc/tf_quantization_autotune.html index bbb7a54bb36..f23211af798 100644 --- a/latest/docs/source/api-doc/tf_quantization_autotune.html +++ b/latest/docs/source/api-doc/tf_quantization_autotune.html @@ -132,7 +132,7 @@

Tensorflow Quantization AutoTuneSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/tf_quantization_common.html b/latest/docs/source/api-doc/tf_quantization_common.html index db72bb953ec..131ca5c6df8 100644 --- a/latest/docs/source/api-doc/tf_quantization_common.html +++ b/latest/docs/source/api-doc/tf_quantization_common.html @@ -132,7 +132,7 @@

Tensorflow Quantization Base APISphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/tf_quantization_config.html b/latest/docs/source/api-doc/tf_quantization_config.html index 8283f2eded0..4d8dbdc5128 100644 --- a/latest/docs/source/api-doc/tf_quantization_config.html +++ b/latest/docs/source/api-doc/tf_quantization_config.html @@ -132,7 +132,7 @@

Tensorflow Quantization ConfigSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/torch_quantization_autotune.html b/latest/docs/source/api-doc/torch_quantization_autotune.html index fb11e9fcb39..210921b2dac 100644 --- a/latest/docs/source/api-doc/torch_quantization_autotune.html +++ b/latest/docs/source/api-doc/torch_quantization_autotune.html @@ -132,7 +132,7 @@

Pytorch Quantization AutoTuneSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/torch_quantization_common.html b/latest/docs/source/api-doc/torch_quantization_common.html index d4f1e4e3fdf..87aa585251d 100644 --- a/latest/docs/source/api-doc/torch_quantization_common.html +++ b/latest/docs/source/api-doc/torch_quantization_common.html @@ -132,7 +132,7 @@

Pytorch Quantization Base APISphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/torch_quantization_config.html b/latest/docs/source/api-doc/torch_quantization_config.html index 0ec07b8491c..8a02efa35cf 100644 --- a/latest/docs/source/api-doc/torch_quantization_config.html +++ b/latest/docs/source/api-doc/torch_quantization_config.html @@ -132,7 +132,7 @@

Pytorch Quantization ConfigSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/api-doc/training.html b/latest/docs/source/api-doc/training.html index a23ce50045c..5fb3e3892c5 100644 --- a/latest/docs/source/api-doc/training.html +++ b/latest/docs/source/api-doc/training.html @@ -135,7 +135,7 @@

Training Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/benchmark.html b/latest/docs/source/benchmark.html index ae8af44d3f5..26bdaeb8d42 100644 --- a/latest/docs/source/benchmark.html +++ b/latest/docs/source/benchmark.html @@ -163,7 +163,7 @@

Examples Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/calibration.html b/latest/docs/source/calibration.html index 493ce23ae90..cd4aedf122f 100644 --- a/latest/docs/source/calibration.html +++ b/latest/docs/source/calibration.html @@ -169,7 +169,7 @@

ReferenceSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/coding_style.html b/latest/docs/source/coding_style.html index 7f297028d3c..41bcfaf0d7b 100644 --- a/latest/docs/source/coding_style.html +++ b/latest/docs/source/coding_style.html @@ -351,7 +351,7 @@

ReferenceSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/dataloader.html b/latest/docs/source/dataloader.html index ccebe98b446..5822b2f4967 100644 --- a/latest/docs/source/dataloader.html +++ b/latest/docs/source/dataloader.html @@ -258,7 +258,7 @@

Examples Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/design.html b/latest/docs/source/design.html index b83c0913e36..c3641b6b8ea 100644 --- a/latest/docs/source/design.html +++ b/latest/docs/source/design.html @@ -116,7 +116,7 @@

Workflow Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/distillation_quantization.html b/latest/docs/source/distillation_quantization.html index f277866afd9..c50984db6e4 100644 --- a/latest/docs/source/distillation_quantization.html +++ b/latest/docs/source/distillation_quantization.html @@ -186,7 +186,7 @@

Examples Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/distributed.html b/latest/docs/source/distributed.html index af70c654e86..5288a69b17c 100644 --- a/latest/docs/source/distributed.html +++ b/latest/docs/source/distributed.html @@ -344,7 +344,7 @@

TensorFlow Examples:Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/examples_readme.html b/latest/docs/source/examples_readme.html index 330b6045055..9ba52f6e39f 100644 --- a/latest/docs/source/examples_readme.html +++ b/latest/docs/source/examples_readme.html @@ -128,7 +128,7 @@

Release DataSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/export.html b/latest/docs/source/export.html index b0fb16ed122..698f2cac5d9 100644 --- a/latest/docs/source/export.html +++ b/latest/docs/source/export.html @@ -325,7 +325,7 @@

Supported quantized opsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/faq.html b/latest/docs/source/faq.html index 80cbc2832d5..d4b96712f13 100644 --- a/latest/docs/source/faq.html +++ b/latest/docs/source/faq.html @@ -139,7 +139,7 @@

Issue 5: Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/framework_yaml.html b/latest/docs/source/framework_yaml.html index 2479b3b9e65..dca4c35057f 100644 --- a/latest/docs/source/framework_yaml.html +++ b/latest/docs/source/framework_yaml.html @@ -323,7 +323,7 @@

Get started with Framework YAML FilesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/get_started.html b/latest/docs/source/get_started.html index 8787cbc98b6..543894de997 100644 --- a/latest/docs/source/get_started.html +++ b/latest/docs/source/get_started.html @@ -201,7 +201,7 @@

Feature MatrixSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/incompatible_changes.html b/latest/docs/source/incompatible_changes.html index f53b95ceacf..cc122e9ee50 100644 --- a/latest/docs/source/incompatible_changes.html +++ b/latest/docs/source/incompatible_changes.html @@ -143,7 +143,7 @@

Built-in transform/dataset/metric APIsSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/infrastructure.html b/latest/docs/source/infrastructure.html index 0876c386e2f..52431c2fcf1 100644 --- a/latest/docs/source/infrastructure.html +++ b/latest/docs/source/infrastructure.html @@ -283,7 +283,7 @@

Supported Feature MatrixSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/installation_guide.html b/latest/docs/source/installation_guide.html index 41f5b960317..a3bf11652bf 100644 --- a/latest/docs/source/installation_guide.html +++ b/latest/docs/source/installation_guide.html @@ -327,7 +327,7 @@

Validated Software EnvironmentSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/legal_information.html b/latest/docs/source/legal_information.html index 88e6075bcc0..6600f6883a3 100644 --- a/latest/docs/source/legal_information.html +++ b/latest/docs/source/legal_information.html @@ -147,7 +147,7 @@

TrademarksSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/llm_recipes.html b/latest/docs/source/llm_recipes.html index 2d781306565..b286f2751fe 100644 --- a/latest/docs/source/llm_recipes.html +++ b/latest/docs/source/llm_recipes.html @@ -470,7 +470,7 @@

Large Language Models AccuracySphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/metric.html b/latest/docs/source/metric.html index 75b5dd99ec5..e23aa573037 100644 --- a/latest/docs/source/metric.html +++ b/latest/docs/source/metric.html @@ -466,7 +466,7 @@

Example Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/migration.html b/latest/docs/source/migration.html index 4eb7e2e9463..79709f3a92e 100644 --- a/latest/docs/source/migration.html +++ b/latest/docs/source/migration.html @@ -782,7 +782,7 @@

Examples Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/mixed_precision.html b/latest/docs/source/mixed_precision.html index 113953d7eb1..b6f98424028 100644 --- a/latest/docs/source/mixed_precision.html +++ b/latest/docs/source/mixed_precision.html @@ -296,7 +296,7 @@

Examples Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/model.html b/latest/docs/source/model.html index f480f509d60..b183b4e3b94 100644 --- a/latest/docs/source/model.html +++ b/latest/docs/source/model.html @@ -221,7 +221,7 @@

Examples Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/mx_quantization.html b/latest/docs/source/mx_quantization.html index 30da2a0da1c..8f0d29adda9 100644 --- a/latest/docs/source/mx_quantization.html +++ b/latest/docs/source/mx_quantization.html @@ -242,7 +242,7 @@

ReferenceSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/objective.html b/latest/docs/source/objective.html index a50d3ebda2e..a2fd148aa0d 100644 --- a/latest/docs/source/objective.html +++ b/latest/docs/source/objective.html @@ -185,7 +185,7 @@

Example Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/orchestration.html b/latest/docs/source/orchestration.html index c56126971cb..df7d99a9ba9 100644 --- a/latest/docs/source/orchestration.html +++ b/latest/docs/source/orchestration.html @@ -195,7 +195,7 @@

Examples Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/pruning.html b/latest/docs/source/pruning.html index b6b12c0e2fc..37891d58e6d 100644 --- a/latest/docs/source/pruning.html +++ b/latest/docs/source/pruning.html @@ -518,7 +518,7 @@

ReferenceSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/publication_list.html b/latest/docs/source/publication_list.html index 36953ad5e7b..93945ba434d 100644 --- a/latest/docs/source/publication_list.html +++ b/latest/docs/source/publication_list.html @@ -214,7 +214,7 @@

2018 - 2020 (4)Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/quantization.html b/latest/docs/source/quantization.html index 5568b42ef0f..a0b21bcc505 100644 --- a/latest/docs/source/quantization.html +++ b/latest/docs/source/quantization.html @@ -771,7 +771,7 @@

Examples Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/quantization_layer_wise.html b/latest/docs/source/quantization_layer_wise.html index 3cd860ff7dd..aa9144ce1b8 100644 --- a/latest/docs/source/quantization_layer_wise.html +++ b/latest/docs/source/quantization_layer_wise.html @@ -192,7 +192,7 @@

ONNX Runtime framework exampleSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/quantization_mixed_precision.html b/latest/docs/source/quantization_mixed_precision.html index 8401cb840a4..05c087cc8b8 100644 --- a/latest/docs/source/quantization_mixed_precision.html +++ b/latest/docs/source/quantization_mixed_precision.html @@ -165,7 +165,7 @@

PyTorch Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/quantization_weight_only.html b/latest/docs/source/quantization_weight_only.html index 1e3355a0502..fc6cd1ab2b7 100644 --- a/latest/docs/source/quantization_weight_only.html +++ b/latest/docs/source/quantization_weight_only.html @@ -468,7 +468,7 @@

ReferenceSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/releases_info.html b/latest/docs/source/releases_info.html index 114755a338b..64e68e138fb 100644 --- a/latest/docs/source/releases_info.html +++ b/latest/docs/source/releases_info.html @@ -140,7 +140,7 @@

Incompatible ChangesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/sigopt_strategy.html b/latest/docs/source/sigopt_strategy.html index 7b0dba559d6..c8d0b88068b 100644 --- a/latest/docs/source/sigopt_strategy.html +++ b/latest/docs/source/sigopt_strategy.html @@ -186,7 +186,7 @@

Performance Comparison of Different StrategiesSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/smooth_quant.html b/latest/docs/source/smooth_quant.html index 0b5dc48faf3..9a34e7c11fe 100644 --- a/latest/docs/source/smooth_quant.html +++ b/latest/docs/source/smooth_quant.html @@ -726,7 +726,7 @@

ReferenceSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/transform.html b/latest/docs/source/transform.html index 7390a176a04..8ee8fa9d80e 100644 --- a/latest/docs/source/transform.html +++ b/latest/docs/source/transform.html @@ -639,7 +639,7 @@

ONNXRT< Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/tuning_strategies.html b/latest/docs/source/tuning_strategies.html index 277fa5224b1..284120a71f8 100644 --- a/latest/docs/source/tuning_strategies.html +++ b/latest/docs/source/tuning_strategies.html @@ -583,7 +583,7 @@

Customize a New Tuning StrategySphinx using a theme provided by Read the Docs. - +

diff --git a/latest/docs/source/validated_model_list.html b/latest/docs/source/validated_model_list.html index 2f38503c323..0765e16fb42 100644 --- a/latest/docs/source/validated_model_list.html +++ b/latest/docs/source/validated_model_list.html @@ -2968,7 +2968,7 @@

Validated ONNX QDQ INT8 Models on Multiple Hardware through ONNX RuntimeSphinx using a theme provided by Read the Docs. - +

diff --git a/latest/genindex.html b/latest/genindex.html index 8ccbae762bc..ae25df29ff6 100644 --- a/latest/genindex.html +++ b/latest/genindex.html @@ -8372,7 +8372,7 @@

X

Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/py-modindex.html b/latest/py-modindex.html index 6d625b3baf1..8b8cf6cf3b4 100644 --- a/latest/py-modindex.html +++ b/latest/py-modindex.html @@ -2456,7 +2456,7 @@

Python Module Index

Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/search.html b/latest/search.html index 9d986d75874..028394f33cf 100644 --- a/latest/search.html +++ b/latest/search.html @@ -123,7 +123,7 @@ Built with Sphinx using a theme provided by Read the Docs. - +

diff --git a/latest/searchindex.js b/latest/searchindex.js index 30786d6c84a..1efec778450 100644 --- a/latest/searchindex.js +++ b/latest/searchindex.js @@ -1 +1 @@ -Search.setIndex({"alltitles": {"2.0 API": [[499, "api"]], "2.X API User Guide": [[469, "x-api-user-guide"]], "2018 - 2020 (4)": [[543, "id5"]], "2021 (15)": [[543, "id4"]], "2022 (35)": [[543, "id3"]], "2023 (25)": [[543, "id2"]], "2024 (5)": [[543, "id1"]], "3.0 API": [[500, "api"]], "API Document Example": [[501, "api-document-example"]], "API List that Need to Implement": [[494, "api-list-that-need-to-implement"]], "API for TensorFlow": [[480, "api-for-tensorflow"]], "APIs": [[502, "apis"]], "AWQ": [[476, "awq"]], "Accuracy Aware Tuning": [[487, "accuracy-aware-tuning"], [544, "accuracy-aware-tuning"]], "Accuracy Criteria": [[552, "accuracy-criteria"]], "Accuracy-driven mixed precision": [[473, "accuracy-driven-mixed-precision"], [537, "accuracy-driven-mixed-precision"]], "Adaptor": [[493, "adaptor"], [496, "adaptor"]], "Adaptor Support Matrix": [[493, "adaptor-support-matrix"]], "Add quantize API according to tune_cfg": [[494, "add-quantize-api-according-to-tune-cfg"]], "Add query_fw_capability to Adaptor": [[494, "add-query-fw-capability-to-adaptor"]], "Additional Content": [[492, "additional-content"]], "Advanced Topics": [[469, "advanced-topics"]], "Algorithm: Auto-tuning of $\\alpha$.": [[550, "algorithm-auto-tuning-of-alpha"]], "Appendix": [[526, "appendix"]], "Architecture": [[484, "architecture"], [522, "architecture"], [531, "architecture"]], "Attributes": [[211, "attributes"], [281, "attributes"]], "Attribution": [[488, "attribution"]], "Auto": [[552, "auto"]], "Auto-tune the alpha for each layer/block": [[550, "auto-tune-the-alpha-for-each-layer-block"]], "Auto-tune the alpha for the entire model": [[550, "auto-tune-the-alpha-for-the-entire-model"]], "AutoRound": [[476, "autoround"]], "AutoTune": [[481, "autotune"]], "Autotune API": [[477, "autotune-api"]], "Backend and Device": [[480, "backend-and-device"]], "Background": [[493, "background"], [520, "background"]], "Basic": [[552, "basic"]], "Bayesian": [[552, "bayesian"]], "Benchmark": [[482, "benchmark"], [503, "benchmark"], [536, "benchmark"]], "Benchmark Support Matrix": [[518, "benchmark-support-matrix"]], "Benchmarking": [[518, "benchmarking"]], "Benefit of SigOpt Strategy": [[549, "benefit-of-sigopt-strategy"]], "Build Custom Dataloader with Python API": [[521, "build-custom-dataloader-with-python-api"]], "Build Custom Metric with Python API": [[535, "build-custom-metric-with-python-api"]], "Built-in transform/dataset/metric APIs": [[530, "built-in-transform-dataset-metric-apis"]], "Calculate the data range and generate quantized model": [[494, "calculate-the-data-range-and-generate-quantized-model"]], "Calibration Algorithms": [[519, "calibration-algorithms"]], "Calibration Algorithms in Quantization": [[519, "calibration-algorithms-in-quantization"]], "Capability": [[493, "capability"]], "Citation": [[533, "citation"]], "Classes": [[1, "classes"], [2, "classes"], [3, "classes"], [5, "classes"], [6, "classes"], [7, "classes"], [8, "classes"], [9, "classes"], [10, "classes"], [11, "classes"], [12, "classes"], [13, "classes"], [14, "classes"], [15, "classes"], [17, "classes"], [18, "classes"], [19, "classes"], [20, "classes"], [21, "classes"], [22, "classes"], [23, "classes"], [24, "classes"], [25, "classes"], [26, "classes"], [27, "classes"], [28, "classes"], [29, "classes"], [30, "classes"], [32, "classes"], [33, "classes"], [34, "classes"], [35, "classes"], [36, "classes"], [38, "classes"], [39, "classes"], [40, "classes"], [41, "classes"], [42, "classes"], [43, "classes"], [44, "classes"], [45, "classes"], [46, "classes"], [47, "classes"], [48, "classes"], [49, "classes"], [50, "classes"], [51, "classes"], [52, "classes"], [53, "classes"], [54, "classes"], [55, "classes"], [56, "classes"], [57, "classes"], [58, "classes"], [59, "classes"], [60, "classes"], [62, "classes"], [63, "classes"], [64, "classes"], [65, "classes"], [66, "classes"], [67, "classes"], [68, "classes"], [69, "classes"], [70, "classes"], [71, "classes"], [73, "classes"], [74, "classes"], [75, "classes"], [76, "classes"], [77, "classes"], [78, "classes"], [79, "classes"], [81, "classes"], [82, "classes"], [83, "classes"], [84, "classes"], [85, "classes"], [87, "classes"], [88, "classes"], [89, "classes"], [90, "classes"], [92, "classes"], [93, "classes"], [94, "classes"], [95, "classes"], [98, "classes"], [100, "classes"], [104, "classes"], [105, "classes"], [106, "classes"], [107, "classes"], [108, "classes"], [109, "classes"], [110, "classes"], [111, "classes"], [112, "classes"], [113, "classes"], [114, "classes"], [116, "classes"], [117, "classes"], [118, "classes"], [119, "classes"], [120, "classes"], [121, "classes"], [122, "classes"], [123, "classes"], [124, "classes"], [125, "classes"], [126, "classes"], [127, "classes"], [128, "classes"], [129, "classes"], [131, "classes"], [132, "classes"], [134, "classes"], [135, "classes"], [139, "classes"], [142, "classes"], [143, "classes"], [146, "classes"], [147, "classes"], [149, "classes"], [150, "classes"], [152, "classes"], [153, "classes"], [156, "classes"], [157, "classes"], [159, "classes"], [161, "classes"], [162, "classes"], [163, "classes"], [165, "classes"], [169, "classes"], [173, "classes"], [174, "classes"], [175, "classes"], [177, "classes"], [178, "classes"], [179, "classes"], [180, "classes"], [181, "classes"], [182, "classes"], [184, "classes"], [185, "classes"], [186, "classes"], [187, "classes"], [188, "classes"], [189, "classes"], [190, "classes"], [191, "classes"], [195, "classes"], [198, "classes"], [199, "classes"], [200, "classes"], [201, "classes"], [202, "classes"], [203, "classes"], [204, "classes"], [205, "classes"], [206, "classes"], [207, "classes"], [208, "classes"], [209, "classes"], [210, "classes"], [211, "classes"], [212, "classes"], [213, "classes"], [214, "classes"], [216, "classes"], [217, "classes"], [218, "classes"], [221, "classes"], [223, "classes"], [224, "classes"], [225, "classes"], [227, "classes"], [230, "classes"], [234, "classes"], [236, "classes"], [238, "classes"], [239, "classes"], [240, "classes"], [241, "classes"], [242, "classes"], [243, "classes"], [244, "classes"], [245, "classes"], [247, "classes"], [248, "classes"], [249, "classes"], [250, "classes"], [251, "classes"], [252, "classes"], [253, "classes"], [254, "classes"], [255, "classes"], [256, "classes"], [258, "classes"], [259, "classes"], [260, "classes"], [263, "classes"], [264, "classes"], [265, "classes"], [266, "classes"], [267, "classes"], [268, "classes"], [269, "classes"], [271, "classes"], [272, "classes"], [273, "classes"], [274, "classes"], [277, "classes"], [278, "classes"], [279, "classes"], [280, "classes"], [281, "classes"], [283, "classes"], [284, "classes"], [286, "classes"], [288, "classes"], [289, "classes"], [292, "classes"], [293, "classes"], [294, "classes"], [297, "classes"], [298, "classes"], [299, "classes"], [303, "classes"], [306, "classes"], [307, "classes"], [308, "classes"], [310, "classes"], [311, "classes"], [312, "classes"], [313, "classes"], [314, "classes"], [315, "classes"], [316, "classes"], [317, "classes"], [318, "classes"], [319, "classes"], [320, "classes"], [321, "classes"], [322, "classes"], [323, "classes"], [324, "classes"], [325, "classes"], [326, "classes"], [327, "classes"], [328, "classes"], [329, "classes"], [330, "classes"], [331, "classes"], [332, "classes"], [334, "classes"], [335, "classes"], [336, "classes"], [337, "classes"], [338, "classes"], [339, "classes"], [340, "classes"], [341, "classes"], [342, "classes"], [343, "classes"], [345, "classes"], [346, "classes"], [347, "classes"], [348, "classes"], [349, "classes"], [350, "classes"], [352, "classes"], [353, "classes"], [354, "classes"], [355, "classes"], [357, "classes"], [358, "classes"], [359, "classes"], [360, "classes"], [363, "classes"], [364, "classes"], [365, "classes"], [366, "classes"], [367, "classes"], [368, "classes"], [369, "classes"], [371, "classes"], [372, "classes"], [373, "classes"], [374, "classes"], [375, "classes"], [376, "classes"], [377, "classes"], [378, "classes"], [379, "classes"], [380, "classes"], [381, "classes"], [383, "classes"], [384, "classes"], [387, "classes"], [389, "classes"], [390, "classes"], [391, "classes"], [392, "classes"], [398, "classes"], [399, "classes"], [401, "classes"], [403, "classes"], [404, "classes"], [405, "classes"], [406, "classes"], [412, "classes"], [413, "classes"], [416, "classes"], [417, "classes"], [418, "classes"], [419, "classes"], [420, "classes"], [421, "classes"], [422, "classes"], [423, "classes"], [426, "classes"], [427, "classes"], [429, "classes"], [430, "classes"], [431, "classes"], [432, "classes"], [433, "classes"], [439, "classes"], [443, "classes"], [444, "classes"], [448, "classes"], [451, "classes"], [452, "classes"], [460, "classes"], [461, "classes"], [462, "classes"], [463, "classes"], [465, "classes"], [466, "classes"]], "Code Migration from Intel Neural Compressor 1.X to Intel Neural Compressor 2.X": [[536, "code-migration-from-intel-neural-compressor-1-x-to-intel-neural-compressor-2-x"]], "Comments": [[520, "comments"]], "Common Build Issues": [[527, "common-build-issues"]], "Common Problem": [[490, "common-problem"]], "Common Problems": [[477, "common-problems"]], "Common arguments": [[476, "common-arguments"]], "Communication": [[492, "communication"]], "Compression": [[504, "compression"]], "Config": [[505, "config"]], "Config Multiple Objectives": [[540, "config-multiple-objectives"]], "Config Single Objective": [[540, "config-single-objective"]], "Conservative Tuning": [[552, "conservative-tuning"]], "Contribution Guidelines": [[489, "contribution-guidelines"]], "Contributor Covenant Code of Conduct": [[488, "contributor-covenant-code-of-conduct"], [489, "contributor-covenant-code-of-conduct"]], "Create Pull Request": [[489, "create-pull-request"]], "Customize a New Tuning Strategy": [[552, "customize-a-new-tuning-strategy"]], "DataLoader": [[521, "dataloader"]], "Define the Quantization Ability of the Specific Operator": [[495, "define-the-quantization-ability-of-the-specific-operator"]], "Demo Usage": [[471, "demo-usage"]], "Demo usage": [[482, "demo-usage"]], "Design": [[484, "design"], [522, "design"], [552, "design"], [552, "id1"], [552, "id3"], [552, "id5"], [552, "id7"], [552, "id9"], [552, "id11"], [552, "id13"], [552, "id15"], [552, "id17"], [552, "id19"], [552, "id21"]], "Design the framework YAML": [[494, "design-the-framework-yaml"]], "Details": [[490, "details"]], "Determining the alpha through auto-tuning": [[479, "determining-the-alpha-through-auto-tuning"], [550, "determining-the-alpha-through-auto-tuning"]], "Distillation": [[536, "distillation"]], "Distillation for Quantization": [[523, "distillation-for-quantization"]], "Distillation for Quantization Support Matrix": [[523, "distillation-for-quantization-support-matrix"]], "Distributed Training and Inference (Evaluation)": [[524, "distributed-training-and-inference-evaluation"]], "Distributed Tuning": [[552, "distributed-tuning"]], "Documentation": [[492, "documentation"]], "Dump Throughput and Latency Summary": [[482, "dump-throughput-and-latency-summary"]], "During quantization mixed precision": [[537, "during-quantization-mixed-precision"]], "Dynamic Quantization": [[470, "dynamic-quantization"], [487, "dynamic-quantization"], [490, "dynamic-quantization"]], "Efficient Usage on Client-Side": [[476, "efficient-usage-on-client-side"]], "Enforcement": [[488, "enforcement"]], "Engineering": [[550, "engineering"]], "Example": [[535, "example"], [540, "example"]], "Example List": [[525, "example-list"]], "Example of Adding a New Backend Support": [[493, "example-of-adding-a-new-backend-support"]], "Examples": [[470, "examples"], [471, "examples"], [472, "examples"], [473, "examples"], [476, "examples"], [478, "examples"], [479, "examples"], [490, "examples"], [518, "examples"], [521, "examples"], [523, "examples"], [524, "examples"], [525, "examples"], [526, "examples"], [536, "examples"], [537, "examples"], [538, "examples"], [539, "examples"], [541, "examples"], [542, "examples"], [544, "examples"], [545, "examples"], [547, "examples"]], "Exceptions": [[138, "exceptions"], [397, "exceptions"]], "Exhaustive": [[552, "exhaustive"]], "Exit Policy": [[552, "exit-policy"]], "Export": [[526, "export"]], "Export Compressed Model": [[547, "export-compressed-model"]], "FP32 Model Export": [[526, "fp32-model-export"], [526, "id1"]], "FP8 Quantization": [[471, "fp8-quantization"], [492, "fp8-quantization"]], "FX": [[490, "fx"]], "FX Mode Support Matrix in Neural Compressor": [[490, "fx-mode-support-matrix-in-neural-compressor"]], "Feature Matrix": [[529, "feature-matrix"]], "Fixed Alpha": [[474, "fixed-alpha"]], "Folder structure": [[520, "folder-structure"]], "Framework YAML Configuration Files": [[528, "framework-yaml-configuration-files"]], "Frequently Asked Questions": [[527, "frequently-asked-questions"]], "Full Publications/Events (84)": [[543, "full-publications-events-84"]], "Functions": [[1, "functions"], [3, "functions"], [21, "functions"], [29, "functions"], [30, "functions"], [31, "functions"], [52, "functions"], [53, "functions"], [55, "functions"], [89, "functions"], [90, "functions"], [101, "functions"], [103, "functions"], [133, "functions"], [134, "functions"], [135, "functions"], [140, "functions"], [141, "functions"], [144, "functions"], [145, "functions"], [146, "functions"], [151, "functions"], [152, "functions"], [153, "functions"], [154, "functions"], [160, "functions"], [161, "functions"], [163, "functions"], [165, "functions"], [166, "functions"], [169, "functions"], [170, "functions"], [171, "functions"], [173, "functions"], [175, "functions"], [176, "functions"], [180, "functions"], [183, "functions"], [188, "functions"], [189, "functions"], [190, "functions"], [191, "functions"], [192, "functions"], [194, "functions"], [201, "functions"], [202, "functions"], [209, "functions"], [211, "functions"], [218, "functions"], [224, "functions"], [225, "functions"], [227, "functions"], [228, "functions"], [230, "functions"], [231, "functions"], [232, "functions"], [234, "functions"], [235, "functions"], [239, "functions"], [243, "functions"], [245, "functions"], [257, "functions"], [261, "functions"], [262, "functions"], [266, "functions"], [274, "functions"], [278, "functions"], [280, "functions"], [281, "functions"], [292, "functions"], [293, "functions"], [294, "functions"], [297, "functions"], [298, "functions"], [299, "functions"], [301, "functions"], [302, "functions"], [303, "functions"], [305, "functions"], [324, "functions"], [325, "functions"], [327, "functions"], [385, "functions"], [387, "functions"], [390, "functions"], [391, "functions"], [396, "functions"], [398, "functions"], [404, "functions"], [406, "functions"], [408, "functions"], [409, "functions"], [411, "functions"], [412, "functions"], [413, "functions"], [415, "functions"], [417, "functions"], [418, "functions"], [420, "functions"], [425, "functions"], [427, "functions"], [431, "functions"], [433, "functions"], [435, "functions"], [437, "functions"], [438, "functions"], [439, "functions"], [441, "functions"], [442, "functions"], [443, "functions"], [445, "functions"], [447, "functions"], [448, "functions"], [454, "functions"], [456, "functions"], [457, "functions"], [458, "functions"], [461, "functions"], [462, "functions"], [464, "functions"], [465, "functions"]], "GPTQ": [[476, "gptq"]], "General Use Cases": [[482, "general-use-cases"]], "Get Start with FP8 Quantization": [[471, "get-start-with-fp8-quantization"]], "Get Started": [[475, "get-started"], [476, "get-started"], [478, "get-started"], [483, "get-started"], [490, "get-started"], [544, "get-started"]], "Get Started with Adaptor API": [[493, "get-started-with-adaptor-api"]], "Get Started with Benchmark API": [[518, "get-started-with-benchmark-api"]], "Get Started with DataLoader": [[521, "get-started-with-dataloader"]], "Get Started with Distillation for Quantization API": [[523, "get-started-with-distillation-for-quantization-api"]], "Get Started with Distributed Training and Inference API": [[524, "get-started-with-distributed-training-and-inference-api"]], "Get Started with Metric": [[535, "get-started-with-metric"]], "Get Started with Microscaling Quantization API": [[472, "get-started-with-microscaling-quantization-api"], [539, "get-started-with-microscaling-quantization-api"]], "Get Started with Mixed Precision API": [[537, "get-started-with-mixed-precision-api"]], "Get Started with Objective API": [[540, "get-started-with-objective-api"]], "Get Started with Orchestration API": [[541, "get-started-with-orchestration-api"]], "Get Started with Pruning API": [[542, "get-started-with-pruning-api"]], "Get Started with autotune API": [[473, "get-started-with-autotune-api"]], "Get started with Framework YAML Files": [[528, "get-started-with-framework-yaml-files"]], "Getting Started": [[492, "getting-started"], [529, "getting-started"]], "Getting Started with Dynamic Quantization": [[470, "getting-started-with-dynamic-quantization"]], "HAWQ_V2": [[552, "hawq-v2"]], "HQQ": [[476, "hqq"]], "Hardware and Software requests for BF16": [[473, "hardware-and-software-requests-for-bf16"], [537, "hardware-and-software-requests-for-bf16"]], "Hardware and Software requests for FP16": [[473, "hardware-and-software-requests-for-fp16"], [537, "hardware-and-software-requests-for-fp16"]], "Horovodrun Execution": [[524, "horovodrun-execution"]], "How it Works": [[481, "how-it-works"]], "How to Add An Adaptor": [[494, "how-to-add-an-adaptor"]], "How to Support New Data Type, Like Int4, with a Few Line Changes": [[495, "how-to-support-new-data-type-like-int4-with-a-few-line-changes"]], "INC Coding Conventions": [[520, "inc-coding-conventions"]], "INT8 Model Export": [[526, "int8-model-export"], [526, "id2"]], "Implement ONNXRTAdaptor Class": [[493, "implement-onnxrtadaptor-class"]], "Imports": [[520, "imports"]], "Incompatible Changes": [[548, "incompatible-changes"]], "Incompatible changes between v1.2 and v1.1": [[530, "incompatible-changes-between-v1-2-and-v1-1"]], "Infrastructure of Intel\u00ae Neural Compressor": [[531, "infrastructure-of-intel-neural-compressor"]], "Install Framework": [[492, "install-framework"], [532, "install-framework"]], "Install from AI Kit": [[532, "install-from-ai-kit"]], "Install from Binary": [[532, "install-from-binary"]], "Install from Source": [[532, "install-from-source"]], "Install from pypi": [[492, "install-from-pypi"]], "Install tensorflow": [[492, "install-tensorflow"], [532, "install-tensorflow"]], "Install torch for CPU": [[492, "install-torch-for-cpu"], [532, "install-torch-for-cpu"]], "Install torch for other platform": [[492, "install-torch-for-other-platform"], [532, "install-torch-for-other-platform"]], "Install torch/intel_extension_for_pytorch for Intel GPU": [[492, "install-torch-intel-extension-for-pytorch-for-intel-gpu"], [532, "install-torch-intel-extension-for-pytorch-for-intel-gpu"]], "Installation": [[492, "installation"], [532, "installation"], [532, "id1"]], "Intel\u00ae Neural Compressor": [[492, "intel-neural-compressor"]], "Intel\u00ae Neural Compressor Documentation": [[468, "intel-neural-compressor-documentation"], [554, "intel-neural-compressor-documentation"]], "Intel\u00ae Neural Compressor quantized ONNX models support multiple hardware vendors through ONNX Runtime:": [[532, "intel-neural-compressor-quantized-onnx-models-support-multiple-hardware-vendors-through-onnx-runtime"]], "Intel\u00ae Neural Compressor supports CPUs based on Intel 64 architecture or compatible processors:": [[532, "intel-neural-compressor-supports-cpus-based-on-intel-64-architecture-or-compatible-processors"]], "Intel\u00ae Neural Compressor supports GPUs built on Intel\u2019s Xe architecture:": [[532, "intel-neural-compressor-supports-gpus-built-on-intel-s-xe-architecture"]], "Intel\u00ae Neural Compressor supports HPUs based on heterogeneous architecture with two compute engines (MME and TPC):": [[532, "intel-neural-compressor-supports-hpus-based-on-heterogeneous-architecture-with-two-compute-engines-mme-and-tpc"]], "Introduction": [[470, "introduction"], [471, "introduction"], [472, "introduction"], [473, "introduction"], [474, "introduction"], [475, "introduction"], [476, "introduction"], [477, "introduction"], [478, "introduction"], [479, "introduction"], [480, "introduction"], [482, "introduction"], [483, "introduction"], [487, "introduction"], [490, "introduction"], [493, "introduction"], [494, "introduction"], [495, "introduction"], [518, "introduction"], [519, "introduction"], [521, "introduction"], [523, "introduction"], [524, "introduction"], [526, "introduction"], [528, "introduction"], [531, "introduction"], [535, "introduction"], [537, "introduction"], [538, "introduction"], [539, "introduction"], [540, "introduction"], [541, "introduction"], [542, "introduction"], [545, "introduction"], [547, "introduction"], [549, "introduction"], [550, "introduction"], [551, "introduction"], [552, "introduction"]], "Invoke the Operator Kernel According to the Tuning Configuration": [[495, "invoke-the-operator-kernel-according-to-the-tuning-configuration"]], "Issue 1:": [[527, "issue-1"]], "Issue 2:": [[527, "issue-2"]], "Issue 3:": [[527, "issue-3"]], "Issue 4:": [[527, "issue-4"]], "Issue 5:": [[527, "issue-5"]], "Known Issues": [[548, "known-issues"]], "LLMs Quantization Recipes": [[534, "llms-quantization-recipes"]], "Large Language Model Pruning": [[542, "large-language-model-pruning"]], "Large Language Models Accuracy": [[534, "large-language-models-accuracy"]], "Large Language Models Recipes": [[534, "large-language-models-recipes"]], "Layer Wise Quantization": [[476, "layer-wise-quantization"]], "Layer Wise Quantization (LWQ)": [[545, "layer-wise-quantization-lwq"]], "Legal Information": [[533, "legal-information"]], "License": [[533, "license"]], "Load API": [[477, "load-api"]], "Logger": [[520, "logger"]], "MSE": [[552, "mse"]], "MSE_V2": [[552, "mse-v2"]], "MXNet": [[535, "mxnet"], [551, "mxnet"]], "Matmul quantization example": [[487, "matmul-quantization-example"], [550, "matmul-quantization-example"]], "Metrics": [[535, "metrics"]], "Microscaling Quantization": [[472, "microscaling-quantization"], [539, "microscaling-quantization"]], "Mix Precision": [[506, "mix-precision"], [536, "mix-precision"]], "Mixed Precision": [[480, "mixed-precision"], [537, "mixed-precision"]], "Mixed Precision Support Matrix": [[473, "mixed-precision-support-matrix"], [537, "mixed-precision-support-matrix"]], "Model": [[507, "model"], [538, "model"]], "Model Examples": [[475, "model-examples"]], "Model Examples with PT2E": [[475, "model-examples-with-pt2e"]], "Model Quantization": [[536, "model-quantization"]], "Module Contents": [[1, "module-contents"], [2, "module-contents"], [3, "module-contents"], [5, "module-contents"], [6, "module-contents"], [7, "module-contents"], [8, "module-contents"], [9, "module-contents"], [10, "module-contents"], [11, "module-contents"], [12, "module-contents"], [13, "module-contents"], [14, "module-contents"], [15, "module-contents"], [17, "module-contents"], [18, "module-contents"], [19, "module-contents"], [20, "module-contents"], [21, "module-contents"], [22, "module-contents"], [23, "module-contents"], [24, "module-contents"], [25, "module-contents"], [26, "module-contents"], [27, "module-contents"], [28, "module-contents"], [29, "module-contents"], [30, "module-contents"], [31, "module-contents"], [32, "module-contents"], [33, "module-contents"], [34, "module-contents"], [35, "module-contents"], [36, "module-contents"], [38, "module-contents"], [39, "module-contents"], [40, "module-contents"], [41, "module-contents"], [42, "module-contents"], [43, "module-contents"], [44, "module-contents"], [45, "module-contents"], [46, "module-contents"], [47, "module-contents"], [48, "module-contents"], [49, "module-contents"], [50, "module-contents"], [51, "module-contents"], [52, "module-contents"], [53, "module-contents"], [54, "module-contents"], [55, "module-contents"], [56, "module-contents"], [57, "module-contents"], [58, "module-contents"], [59, "module-contents"], [60, "module-contents"], [62, "module-contents"], [63, "module-contents"], [64, "module-contents"], [65, "module-contents"], [66, "module-contents"], [67, "module-contents"], [68, "module-contents"], [69, "module-contents"], [70, "module-contents"], [71, "module-contents"], [73, "module-contents"], [74, "module-contents"], [75, "module-contents"], [76, "module-contents"], [77, "module-contents"], [78, "module-contents"], [79, "module-contents"], [81, "module-contents"], [82, "module-contents"], [83, "module-contents"], [84, "module-contents"], [85, "module-contents"], [87, "module-contents"], [88, "module-contents"], [89, "module-contents"], [90, "module-contents"], [92, "module-contents"], [93, "module-contents"], [94, "module-contents"], [95, "module-contents"], [98, "module-contents"], [100, "module-contents"], [101, "module-contents"], [103, "module-contents"], [104, "module-contents"], [105, "module-contents"], [106, "module-contents"], [107, "module-contents"], [108, "module-contents"], [109, "module-contents"], [110, "module-contents"], [111, "module-contents"], [112, "module-contents"], [113, "module-contents"], [114, "module-contents"], [116, "module-contents"], [117, "module-contents"], [118, "module-contents"], [119, "module-contents"], [120, "module-contents"], [121, "module-contents"], [122, "module-contents"], [123, "module-contents"], [124, "module-contents"], [125, "module-contents"], [126, "module-contents"], [127, "module-contents"], [128, "module-contents"], [129, "module-contents"], [131, "module-contents"], [132, "module-contents"], [133, "module-contents"], [134, "module-contents"], [135, "module-contents"], [138, "module-contents"], [139, "module-contents"], [140, "module-contents"], [141, "module-contents"], [142, "module-contents"], [143, "module-contents"], [144, "module-contents"], [145, "module-contents"], [146, "module-contents"], [147, "module-contents"], [149, "module-contents"], [150, "module-contents"], [151, "module-contents"], [152, "module-contents"], [153, "module-contents"], [154, "module-contents"], [156, "module-contents"], [157, "module-contents"], [159, "module-contents"], [160, "module-contents"], [161, "module-contents"], [162, "module-contents"], [163, "module-contents"], [165, "module-contents"], [166, "module-contents"], [169, "module-contents"], [171, "module-contents"], [173, "module-contents"], [174, "module-contents"], [175, "module-contents"], [177, "module-contents"], [178, "module-contents"], [179, "module-contents"], [180, "module-contents"], [181, "module-contents"], [182, "module-contents"], [184, "module-contents"], [185, "module-contents"], [186, "module-contents"], [187, "module-contents"], [188, "module-contents"], [189, "module-contents"], [190, "module-contents"], [191, "module-contents"], [192, "module-contents"], [194, "module-contents"], [195, "module-contents"], [198, "module-contents"], [199, "module-contents"], [200, "module-contents"], [201, "module-contents"], [202, "module-contents"], [203, "module-contents"], [204, "module-contents"], [205, "module-contents"], [206, "module-contents"], [207, "module-contents"], [208, "module-contents"], [209, "module-contents"], [210, "module-contents"], [211, "module-contents"], [212, "module-contents"], [213, "module-contents"], [214, "module-contents"], [216, "module-contents"], [217, "module-contents"], [218, "module-contents"], [221, "module-contents"], [223, "module-contents"], [224, "module-contents"], [225, "module-contents"], [227, "module-contents"], [228, "module-contents"], [230, "module-contents"], [231, "module-contents"], [232, "module-contents"], [234, "module-contents"], [235, "module-contents"], [236, "module-contents"], [238, "module-contents"], [239, "module-contents"], [240, "module-contents"], [241, "module-contents"], [242, "module-contents"], [243, "module-contents"], [244, "module-contents"], [245, "module-contents"], [247, "module-contents"], [248, "module-contents"], [249, "module-contents"], [250, "module-contents"], [251, "module-contents"], [252, "module-contents"], [253, "module-contents"], [254, "module-contents"], [255, "module-contents"], [256, "module-contents"], [257, "module-contents"], [258, "module-contents"], [259, "module-contents"], [260, "module-contents"], [261, "module-contents"], [262, "module-contents"], [263, "module-contents"], [264, "module-contents"], [265, "module-contents"], [266, "module-contents"], [267, "module-contents"], [268, "module-contents"], [269, "module-contents"], [271, "module-contents"], [272, "module-contents"], [273, "module-contents"], [274, "module-contents"], [277, "module-contents"], [278, "module-contents"], [279, "module-contents"], [280, "module-contents"], [281, "module-contents"], [283, "module-contents"], [284, "module-contents"], [286, "module-contents"], [288, "module-contents"], [289, "module-contents"], [292, "module-contents"], [293, "module-contents"], [294, "module-contents"], [297, "module-contents"], [298, "module-contents"], [299, "module-contents"], [301, "module-contents"], [302, "module-contents"], [303, "module-contents"], [305, "module-contents"], [306, "module-contents"], [307, "module-contents"], [308, "module-contents"], [310, "module-contents"], [311, "module-contents"], [312, "module-contents"], [313, "module-contents"], [314, "module-contents"], [315, "module-contents"], [316, "module-contents"], [317, "module-contents"], [318, "module-contents"], [319, "module-contents"], [320, "module-contents"], [321, "module-contents"], [322, "module-contents"], [323, "module-contents"], [324, "module-contents"], [325, "module-contents"], [326, "module-contents"], [327, "module-contents"], [328, "module-contents"], [329, "module-contents"], [330, "module-contents"], [331, "module-contents"], [332, "module-contents"], [334, "module-contents"], [335, "module-contents"], [336, "module-contents"], [337, "module-contents"], [338, "module-contents"], [339, "module-contents"], [340, "module-contents"], [341, "module-contents"], [342, "module-contents"], [343, "module-contents"], [345, "module-contents"], [346, "module-contents"], [347, "module-contents"], [348, "module-contents"], [349, "module-contents"], [350, "module-contents"], [352, "module-contents"], [353, "module-contents"], [354, "module-contents"], [355, "module-contents"], [357, "module-contents"], [358, "module-contents"], [359, "module-contents"], [360, "module-contents"], [363, "module-contents"], [364, "module-contents"], [365, "module-contents"], [366, "module-contents"], [367, "module-contents"], [368, "module-contents"], [369, "module-contents"], [371, "module-contents"], [372, "module-contents"], [373, "module-contents"], [374, "module-contents"], [375, "module-contents"], [376, "module-contents"], [377, "module-contents"], [378, "module-contents"], [379, "module-contents"], [380, "module-contents"], [381, "module-contents"], [383, "module-contents"], [384, "module-contents"], [385, "module-contents"], [387, "module-contents"], [389, "module-contents"], [390, "module-contents"], [391, "module-contents"], [392, "module-contents"], [396, "module-contents"], [397, "module-contents"], [398, "module-contents"], [399, "module-contents"], [401, "module-contents"], [403, "module-contents"], [404, "module-contents"], [405, "module-contents"], [406, "module-contents"], [408, "module-contents"], [409, "module-contents"], [411, "module-contents"], [412, "module-contents"], [413, "module-contents"], [415, "module-contents"], [416, "module-contents"], [417, "module-contents"], [418, "module-contents"], [419, "module-contents"], [420, "module-contents"], [421, "module-contents"], [422, "module-contents"], [423, "module-contents"], [425, "module-contents"], [426, "module-contents"], [427, "module-contents"], [429, "module-contents"], [430, "module-contents"], [431, "module-contents"], [432, "module-contents"], [433, "module-contents"], [435, "module-contents"], [437, "module-contents"], [438, "module-contents"], [439, "module-contents"], [441, "module-contents"], [442, "module-contents"], [443, "module-contents"], [444, "module-contents"], [445, "module-contents"], [447, "module-contents"], [448, "module-contents"], [451, "module-contents"], [452, "module-contents"], [454, "module-contents"], [456, "module-contents"], [457, "module-contents"], [458, "module-contents"], [460, "module-contents"], [461, "module-contents"], [462, "module-contents"], [463, "module-contents"], [464, "module-contents"], [465, "module-contents"], [466, "module-contents"]], "Multiple Objectives": [[540, "multiple-objectives"]], "Neural Compressor Configuration": [[549, "neural-compressor-configuration"]], "Neural Network Pruning": [[542, "neural-network-pruning"]], "Note": [[490, "note"]], "ONNX Models with ONNX Runtime 1.15.0 in WOQ Mode": [[553, "onnx-models-with-onnx-runtime-1-15-0-in-woq-mode"]], "ONNX Models with ONNX Runtime 1.17.1": [[553, "onnx-models-with-onnx-runtime-1-17-1"]], "ONNX Runtime": [[497, "onnx-runtime"]], "ONNX Runtime framework example": [[545, "onnx-runtime-framework-example"]], "ONNXRT": [[535, "onnxrt"], [551, "onnxrt"]], "Objective": [[508, "objective"], [540, "objective"]], "Objective Support Matrix": [[540, "objective-support-matrix"]], "One-shot": [[541, "one-shot"]], "Optimization Orchestration": [[541, "optimization-orchestration"]], "Option 1: Pure Yaml Configuration": [[524, "option-1-pure-yaml-configuration"]], "Option 2: User Defined Training Function": [[524, "option-2-user-defined-training-function"]], "Orchestration": [[536, "orchestration"]], "Orchestration Support Matrix": [[541, "orchestration-support-matrix"]], "Our Pledge": [[488, "our-pledge"]], "Our Responsibilities": [[488, "our-responsibilities"]], "Our Standards": [[488, "our-standards"]], "Our enhancement:": [[550, "our-enhancement"]], "Overview": [[469, "overview"], [481, "overview"]], "Package Contents": [[170, "package-contents"], [176, "package-contents"], [183, "package-contents"]], "Per-channel example": [[487, "per-channel-example"], [550, "per-channel-example"]], "Per-channel limitation": [[487, "per-channel-limitation"], [550, "per-channel-limitation"]], "Per-tensor & Per-channel": [[487, "per-tensor-per-channel"], [550, "per-tensor-per-channel"]], "Per-tensor example": [[487, "per-tensor-example"], [550, "per-tensor-example"]], "Performance": [[549, "performance"]], "Performance Comparison of Different Strategies": [[549, "performance-comparison-of-different-strategies"]], "Post Training Dynamic Quantization": [[490, "post-training-dynamic-quantization"], [544, "post-training-dynamic-quantization"]], "Post Training Quantization": [[544, "post-training-quantization"]], "Post Training Static Quantization": [[480, "post-training-static-quantization"], [490, "post-training-static-quantization"], [544, "post-training-static-quantization"]], "Post-training Quantization": [[536, "post-training-quantization"]], "Preparation": [[549, "preparation"]], "Prepare calibration model from fp32 graph": [[494, "prepare-calibration-model-from-fp32-graph"]], "Prerequisites": [[532, "prerequisites"]], "Pruning": [[536, "pruning"], [542, "pruning"]], "Pruning Criteria": [[542, "pruning-criteria"]], "Pruning Patterns": [[542, "pruning-patterns"]], "Pruning Schedules": [[542, "pruning-schedules"]], "Pruning Scope": [[542, "pruning-scope"]], "Pruning Support Matrix": [[542, "pruning-support-matrix"]], "Pruning Types": [[542, "pruning-types"]], "Pruning with Hyperparameter Optimization": [[542, "pruning-with-hyperparameter-optimization"]], "Public and Internal Interfaces": [[520, "public-and-internal-interfaces"]], "Pull Request Acceptance Criteria": [[489, "pull-request-acceptance-criteria"]], "Pull Request Checklist": [[489, "pull-request-checklist"]], "Pull Request Status Checks Overview": [[489, "pull-request-status-checks-overview"]], "Pull Request Template": [[489, "pull-request-template"]], "PyTorch": [[535, "pytorch"], [546, "pytorch"]], "PyTorch Examples:": [[524, "pytorch-examples"]], "PyTorch Mixed Precision": [[473, "pytorch-mixed-precision"]], "PyTorch Model": [[526, "pytorch-model"]], "PyTorch Models with Torch 2.0.1+cpu in WOQ Mode": [[553, "pytorch-models-with-torch-2-0-1-cpu-in-woq-mode"]], "PyTorch Models with Torch 2.2.1+cpu in PTQ Mode": [[553, "pytorch-models-with-torch-2-2-1-cpu-in-ptq-mode"]], "PyTorch Models with Torch 2.2.1+cpu in QAT Mode": [[553, "pytorch-models-with-torch-2-2-1-cpu-in-qat-mode"]], "PyTorch Smooth Quantization": [[474, "pytorch-smooth-quantization"]], "PyTorch Static Quantization": [[475, "pytorch-static-quantization"]], "PyTorch Weight Only Quantization": [[476, "pytorch-weight-only-quantization"]], "PyTorch framework example": [[545, "pytorch-framework-example"]], "Python-based APIs": [[469, "python-based-apis"]], "Pytorch": [[551, "pytorch"]], "Pytorch Quantization AutoTune": [[514, "pytorch-quantization-autotune"]], "Pytorch Quantization Base API": [[515, "pytorch-quantization-base-api"]], "Pytorch Quantization Config": [[516, "pytorch-quantization-config"]], "Quantization": [[487, "quantization"], [509, "quantization"], [544, "quantization"]], "Quantization APIs": [[477, "quantization-apis"]], "Quantization Approaches": [[480, "quantization-approaches"], [544, "quantization-approaches"]], "Quantization Aware Training": [[487, "quantization-aware-training"], [536, "quantization-aware-training"], [544, "quantization-aware-training"], [544, "id1"]], "Quantization Capability": [[547, "quantization-capability"]], "Quantization Fundamentals": [[487, "quantization-fundamentals"], [544, "quantization-fundamentals"], [550, "quantization-fundamentals"]], "Quantization Introduction": [[544, "quantization-introduction"]], "Quantization Scheme": [[480, "quantization-scheme"]], "Quantization Scheme in IPEX": [[487, "quantization-scheme-in-ipex"], [544, "quantization-scheme-in-ipex"]], "Quantization Scheme in MXNet": [[544, "quantization-scheme-in-mxnet"]], "Quantization Scheme in ONNX Runtime": [[544, "quantization-scheme-in-onnx-runtime"]], "Quantization Scheme in PyTorch": [[487, "quantization-scheme-in-pytorch"], [544, "quantization-scheme-in-pytorch"]], "Quantization Scheme in TensorFlow": [[487, "quantization-scheme-in-tensorflow"], [544, "quantization-scheme-in-tensorflow"]], "Quantization Support Matrix": [[544, "quantization-support-matrix"]], "Quantization on Client": [[483, "quantization-on-client"]], "Quantization-Aware Training": [[490, "quantization-aware-training"]], "Query API": [[493, "query-api"]], "Query API Introduction": [[493, "query-api-introduction"]], "Quick Samples": [[529, "quick-samples"]], "RTN": [[476, "rtn"]], "Random": [[552, "random"]], "Recommend VS Code settings.json": [[520, "recommend-vs-code-settings-json"]], "Reference": [[472, "reference"], [476, "reference"], [487, "reference"], [519, "reference"], [520, "reference"], [539, "reference"], [542, "reference"], [544, "reference"], [547, "reference"], [550, "reference"]], "Regularization": [[542, "regularization"]], "Release": [[548, "release"]], "Release Data": [[525, "release-data"]], "Release Notes": [[548, "release-notes"]], "Report a Vulnerability": [[491, "report-a-vulnerability"]], "Retrain-free Pruning API": [[542, "retrain-free-pruning-api"]], "Rules": [[520, "rules"]], "Run sampling iterations of the fp32 graph to calibrate quantizable operators.": [[494, "run-sampling-iterations-of-the-fp32-graph-to-calibrate-quantizable-operators"]], "Saving and Loading": [[476, "saving-and-loading"]], "Scope": [[488, "scope"]], "Sections": [[468, "sections"], [554, "sections"]], "Security": [[524, "security"]], "Security Policy": [[491, "security-policy"]], "Selected Publications/Events": [[492, "selected-publications-events"]], "SigOpt": [[552, "sigopt"]], "SigOpt Platform": [[549, "sigopt-platform"]], "SigOpt Strategy": [[549, "sigopt-strategy"]], "Single Objective": [[540, "single-objective"]], "Smooth Quant": [[479, "smooth-quant"], [550, "smooth-quant"]], "Smooth Quantization": [[480, "smooth-quantization"], [487, "smooth-quantization"]], "SmoothQuant": [[550, "smoothquant"]], "SmoothQuant and Our Enhancement": [[550, "smoothquant-and-our-enhancement"]], "Sparse Model Deployment": [[542, "sparse-model-deployment"]], "Sparsity Decay Types": [[542, "sparsity-decay-types"]], "Specify Quantization Backend and Device": [[544, "specify-quantization-backend-and-device"]], "Specify Quantization Recipes": [[544, "specify-quantization-recipes"]], "Specify Quantization Rules": [[474, "specify-quantization-rules"], [475, "specify-quantization-rules"], [476, "specify-quantization-rules"], [478, "specify-quantization-rules"], [544, "specify-quantization-rules"]], "Static Quantization": [[487, "static-quantization"]], "Static Quantization & Quantization Aware Training": [[490, "static-quantization-quantization-aware-training"]], "Static Quantization with IPEX Backend": [[475, "static-quantization-with-ipex-backend"]], "Static Quantization with PT2E Backend": [[475, "static-quantization-with-pt2e-backend"]], "Step-by-Step guidelines": [[489, "step-by-step-guidelines"]], "Strategy": [[510, "strategy"]], "Strategy Design": [[552, "strategy-design"]], "Strings": [[520, "strings"]], "Submodules": [[0, "submodules"], [4, "submodules"], [16, "submodules"], [37, "submodules"], [61, "submodules"], [72, "submodules"], [80, "submodules"], [86, "submodules"], [91, "submodules"], [96, "submodules"], [97, "submodules"], [99, "submodules"], [102, "submodules"], [115, "submodules"], [130, "submodules"], [136, "submodules"], [137, "submodules"], [148, "submodules"], [155, "submodules"], [158, "submodules"], [164, "submodules"], [167, "submodules"], [170, "submodules"], [172, "submodules"], [176, "submodules"], [183, "submodules"], [193, "submodules"], [197, "submodules"], [215, "submodules"], [219, "submodules"], [222, "submodules"], [226, "submodules"], [233, "submodules"], [237, "submodules"], [270, "submodules"], [276, "submodules"], [285, "submodules"], [287, "submodules"], [295, "submodules"], [300, "submodules"], [304, "submodules"], [309, "submodules"], [333, "submodules"], [344, "submodules"], [351, "submodules"], [356, "submodules"], [361, "submodules"], [362, "submodules"], [370, "submodules"], [382, "submodules"], [388, "submodules"], [394, "submodules"], [395, "submodules"], [400, "submodules"], [402, "submodules"], [407, "submodules"], [410, "submodules"], [414, "submodules"], [424, "submodules"], [428, "submodules"], [434, "submodules"], [440, "submodules"], [446, "submodules"], [450, "submodules"], [455, "submodules"], [459, "submodules"]], "Subpackages": [[4, "subpackages"], [72, "subpackages"], [96, "subpackages"], [97, "subpackages"], [99, "subpackages"], [136, "subpackages"], [155, "subpackages"], [170, "subpackages"], [196, "subpackages"], [220, "subpackages"], [226, "subpackages"], [270, "subpackages"], [282, "subpackages"], [290, "subpackages"], [291, "subpackages"], [304, "subpackages"], [344, "subpackages"], [361, "subpackages"], [362, "subpackages"], [394, "subpackages"], [428, "subpackages"], [436, "subpackages"], [459, "subpackages"]], "Summary": [[495, "summary"]], "Support": [[489, "support"]], "Support Matrix": [[480, "support-matrix"], [519, "support-matrix"]], "Supported Built-in Metric Matrix": [[535, "supported-built-in-metric-matrix"]], "Supported Feature Matrix": [[524, "supported-feature-matrix"], [528, "supported-feature-matrix"], [531, "supported-feature-matrix"], [544, "supported-feature-matrix"]], "Supported Framework Dataloader Matrix": [[521, "supported-framework-dataloader-matrix"]], "Supported Framework Matrix": [[474, "supported-framework-matrix"], [550, "supported-framework-matrix"]], "Supported Framework Model Matrix": [[526, "supported-framework-model-matrix"], [538, "supported-framework-model-matrix"], [539, "supported-framework-model-matrix"], [545, "supported-framework-model-matrix"], [547, "supported-framework-model-matrix"]], "Supported Matrix": [[476, "supported-matrix"], [477, "supported-matrix"], [482, "supported-matrix"]], "Supported Parameters": [[471, "supported-parameters"]], "Supported quantized ops": [[526, "supported-quantized-ops"]], "Symmetric & Asymmetric": [[487, "symmetric-asymmetric"]], "System Requirements": [[532, "system-requirements"]], "TEQ": [[476, "teq"]], "TODO Comments": [[520, "todo-comments"]], "TPE": [[552, "tpe"]], "TensorFlow": [[480, "tensorflow"], [535, "tensorflow"], [551, "tensorflow"]], "TensorFlow Examples:": [[524, "tensorflow-examples"]], "TensorFlow Models with TensorFlow 2.15.0": [[553, "tensorflow-models-with-tensorflow-2-15-0"]], "TensorFlow Quantization": [[478, "tensorflow-quantization"]], "Tensorflow": [[546, "tensorflow"]], "Tensorflow Model": [[526, "tensorflow-model"]], "Tensorflow Quantization AutoTune": [[511, "tensorflow-quantization-autotune"]], "Tensorflow Quantization Base API": [[512, "tensorflow-quantization-base-api"]], "Tensorflow Quantization Config": [[513, "tensorflow-quantization-config"]], "Torch": [[477, "torch"]], "Torch Utils": [[498, "torch-utils"]], "Torch-like APIs": [[477, "torch-like-apis"]], "Trademarks": [[533, "trademarks"]], "Training": [[517, "training"]], "Training-aware pruning API": [[542, "training-aware-pruning-api"]], "Transform": [[551, "transform"]], "Transform Support List": [[551, "transform-support-list"]], "Tuning Algorithms": [[552, "tuning-algorithms"]], "Tuning Process": [[552, "tuning-process"]], "Tuning Space": [[552, "tuning-space"]], "Tuning Strategies": [[552, "tuning-strategies"]], "Turn OFF Auto Mixed Precision during Quantization": [[546, "turn-off-auto-mixed-precision-during-quantization"]], "Type Annotations": [[520, "type-annotations"]], "Usage": [[474, "usage"], [476, "usage"], [479, "usage"], [482, "usage"], [550, "usage"], [552, "usage"], [552, "id2"], [552, "id4"], [552, "id6"], [552, "id8"], [552, "id10"], [552, "id12"], [552, "id14"], [552, "id16"], [552, "id18"], [552, "id20"], [552, "id22"]], "Usage Sample with IPEX": [[475, "usage-sample-with-ipex"]], "Usage Sample with PT2E": [[475, "usage-sample-with-pt2e"]], "Use Docker Image with torch installed for HPU": [[492, "use-docker-image-with-torch-installed-for-hpu"], [532, "use-docker-image-with-torch-installed-for-hpu"]], "Use Intel\u00ae Neural Compressor DataLoader API": [[521, "use-intel-neural-compressor-dataloader-api"]], "Use Intel\u00ae Neural Compressor Metric API": [[535, "use-intel-neural-compressor-metric-api"]], "Use the New Data Type": [[495, "use-the-new-data-type"]], "User Code Example": [[547, "user-code-example"]], "User code example": [[547, "id1"]], "User-facing APIs": [[530, "user-facing-apis"]], "Using a Fixed alpha": [[479, "using-a-fixed-alpha"]], "Using a fixed alpha": [[550, "using-a-fixed-alpha"]], "Validated Hardware Environment": [[532, "validated-hardware-environment"]], "Validated Knowledge Distillation Examples": [[553, "validated-knowledge-distillation-examples"]], "Validated Models": [[474, "validated-models"], [550, "validated-models"], [553, "validated-models"]], "Validated ONNX QDQ INT8 Models on Multiple Hardware through ONNX Runtime": [[553, "validated-onnx-qdq-int8-models-on-multiple-hardware-through-onnx-runtime"]], "Validated Pruning Examples": [[553, "validated-pruning-examples"]], "Validated Quantization Examples": [[553, "validated-quantization-examples"]], "Validated Software Environment": [[532, "validated-software-environment"]], "Version mapping between Intel Neural Compressor to Gaudi Software Stack": [[485, "version-mapping-between-intel-neural-compressor-to-gaudi-software-stack"]], "WOQ Algorithms Tuning": [[547, "woq-algorithms-tuning"]], "Weight Only Quantization": [[487, "weight-only-quantization"]], "Weight Only Quantization (WOQ)": [[547, "weight-only-quantization-woq"]], "Weight-Only Large Language Model Loading (LLMs)": [[492, "weight-only-large-language-model-loading-llms"]], "What\u2019s New": [[492, "what-s-new"]], "With Accuracy Aware Tuning": [[478, "with-accuracy-aware-tuning"]], "Without Accuracy Aware Tuning": [[478, "without-accuracy-aware-tuning"]], "Workflow": [[522, "workflow"]], "Workflows": [[484, "workflows"]], "Working Flow": [[493, "working-flow"], [544, "working-flow"]], "Working with Autotune": [[481, "working-with-autotune"]], "Working with PyTorch Model": [[481, "working-with-pytorch-model"]], "Working with Tensorflow Model": [[481, "working-with-tensorflow-model"]], "neural_compressor": [[226, "module-neural_compressor"]], "neural_compressor.adaptor.mxnet_utils": [[0, "module-neural_compressor.adaptor.mxnet_utils"]], "neural_compressor.adaptor.mxnet_utils.util": [[1, "module-neural_compressor.adaptor.mxnet_utils.util"]], "neural_compressor.adaptor.ox_utils": [[4, "module-neural_compressor.adaptor.ox_utils"]], "neural_compressor.adaptor.ox_utils.calibration": [[2, "module-neural_compressor.adaptor.ox_utils.calibration"]], "neural_compressor.adaptor.ox_utils.calibrator": [[3, "module-neural_compressor.adaptor.ox_utils.calibrator"]], "neural_compressor.adaptor.ox_utils.operators": [[16, "module-neural_compressor.adaptor.ox_utils.operators"]], "neural_compressor.adaptor.ox_utils.operators.activation": [[5, "module-neural_compressor.adaptor.ox_utils.operators.activation"]], "neural_compressor.adaptor.ox_utils.operators.argmax": [[6, "module-neural_compressor.adaptor.ox_utils.operators.argmax"]], "neural_compressor.adaptor.ox_utils.operators.attention": [[7, "module-neural_compressor.adaptor.ox_utils.operators.attention"]], "neural_compressor.adaptor.ox_utils.operators.binary_op": [[8, "module-neural_compressor.adaptor.ox_utils.operators.binary_op"]], "neural_compressor.adaptor.ox_utils.operators.concat": [[9, "module-neural_compressor.adaptor.ox_utils.operators.concat"]], "neural_compressor.adaptor.ox_utils.operators.conv": [[10, "module-neural_compressor.adaptor.ox_utils.operators.conv"]], "neural_compressor.adaptor.ox_utils.operators.direct_q8": [[11, "module-neural_compressor.adaptor.ox_utils.operators.direct_q8"]], "neural_compressor.adaptor.ox_utils.operators.embed_layernorm": [[12, "module-neural_compressor.adaptor.ox_utils.operators.embed_layernorm"]], "neural_compressor.adaptor.ox_utils.operators.gather": [[13, "module-neural_compressor.adaptor.ox_utils.operators.gather"]], "neural_compressor.adaptor.ox_utils.operators.gavgpool": [[14, "module-neural_compressor.adaptor.ox_utils.operators.gavgpool"]], "neural_compressor.adaptor.ox_utils.operators.gemm": [[15, "module-neural_compressor.adaptor.ox_utils.operators.gemm"]], "neural_compressor.adaptor.ox_utils.operators.lstm": [[17, "module-neural_compressor.adaptor.ox_utils.operators.lstm"]], "neural_compressor.adaptor.ox_utils.operators.matmul": [[18, "module-neural_compressor.adaptor.ox_utils.operators.matmul"]], "neural_compressor.adaptor.ox_utils.operators.maxpool": [[19, "module-neural_compressor.adaptor.ox_utils.operators.maxpool"]], "neural_compressor.adaptor.ox_utils.operators.norm": [[20, "module-neural_compressor.adaptor.ox_utils.operators.norm"]], "neural_compressor.adaptor.ox_utils.operators.ops": [[21, "module-neural_compressor.adaptor.ox_utils.operators.ops"]], "neural_compressor.adaptor.ox_utils.operators.pad": [[22, "module-neural_compressor.adaptor.ox_utils.operators.pad"]], "neural_compressor.adaptor.ox_utils.operators.pooling": [[23, "module-neural_compressor.adaptor.ox_utils.operators.pooling"]], "neural_compressor.adaptor.ox_utils.operators.reduce": [[24, "module-neural_compressor.adaptor.ox_utils.operators.reduce"]], "neural_compressor.adaptor.ox_utils.operators.resize": [[25, "module-neural_compressor.adaptor.ox_utils.operators.resize"]], "neural_compressor.adaptor.ox_utils.operators.split": [[26, "module-neural_compressor.adaptor.ox_utils.operators.split"]], "neural_compressor.adaptor.ox_utils.operators.unary_op": [[27, "module-neural_compressor.adaptor.ox_utils.operators.unary_op"]], "neural_compressor.adaptor.ox_utils.quantizer": [[28, "module-neural_compressor.adaptor.ox_utils.quantizer"]], "neural_compressor.adaptor.ox_utils.smooth_quant": [[29, "module-neural_compressor.adaptor.ox_utils.smooth_quant"]], "neural_compressor.adaptor.ox_utils.util": [[30, "module-neural_compressor.adaptor.ox_utils.util"]], "neural_compressor.adaptor.ox_utils.weight_only": [[31, "module-neural_compressor.adaptor.ox_utils.weight_only"]], "neural_compressor.adaptor.tensorflow": [[32, "module-neural_compressor.adaptor.tensorflow"]], "neural_compressor.adaptor.tf_utils": [[96, "module-neural_compressor.adaptor.tf_utils"]], "neural_compressor.adaptor.tf_utils.graph_converter": [[33, "module-neural_compressor.adaptor.tf_utils.graph_converter"]], "neural_compressor.adaptor.tf_utils.graph_converter_without_calib": [[34, "module-neural_compressor.adaptor.tf_utils.graph_converter_without_calib"]], "neural_compressor.adaptor.tf_utils.graph_rewriter": [[72, "module-neural_compressor.adaptor.tf_utils.graph_rewriter"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16": [[37, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert": [[35, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer": [[36, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic": [[61, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd": [[38, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout": [[39, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu": [[40, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random": [[41, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const": [[42, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction": [[43, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd": [[44, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer": [[45, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape": [[46, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm": [[47, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant": [[48, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add": [[49, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul": [[50, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math": [[51, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn": [[52, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in": [[53, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu": [[54, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm": [[55, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv": [[56, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv": [[57, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose": [[58, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer": [[59, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass": [[60, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node": [[62, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu": [[63, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize": [[64, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes": [[65, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm": [[66, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input": [[67, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes": [[68, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes": [[69, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer": [[70, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base": [[71, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8": [[80, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant": [[73, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value": [[74, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib": [[75, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize": [[76, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize": [[77, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize": [[78, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize": [[79, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer": [[81, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter": [[82, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse": [[83, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert": [[84, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation": [[85, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx": [[86, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph": [[87, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node": [[88, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema": [[89, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils": [[90, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq": [[91, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern": [[92, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq": [[93, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern": [[94, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern"]], "neural_compressor.adaptor.tf_utils.graph_util": [[95, "module-neural_compressor.adaptor.tf_utils.graph_util"]], "neural_compressor.adaptor.tf_utils.quantize_graph": [[97, "module-neural_compressor.adaptor.tf_utils.quantize_graph"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat": [[99, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize": [[98, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config": [[100, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper": [[101, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers": [[102, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer": [[103, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add": [[104, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base": [[105, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn": [[106, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper": [[107, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq": [[115, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn": [[108, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2": [[109, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv": [[110, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv": [[111, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in": [[112, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul": [[113, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling": [[114, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq": [[116, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base": [[117, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn": [[118, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2": [[119, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv": [[120, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu": [[121, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul": [[122, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling": [[123, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling"]], "neural_compressor.adaptor.tf_utils.quantize_graph_common": [[124, "module-neural_compressor.adaptor.tf_utils.quantize_graph_common"]], "neural_compressor.adaptor.tf_utils.smooth_quant_calibration": [[125, "module-neural_compressor.adaptor.tf_utils.smooth_quant_calibration"]], "neural_compressor.adaptor.tf_utils.smooth_quant_scaler": [[126, "module-neural_compressor.adaptor.tf_utils.smooth_quant_scaler"]], "neural_compressor.adaptor.tf_utils.tf2onnx_converter": [[127, "module-neural_compressor.adaptor.tf_utils.tf2onnx_converter"]], "neural_compressor.adaptor.tf_utils.transform_graph": [[130, "module-neural_compressor.adaptor.tf_utils.transform_graph"]], "neural_compressor.adaptor.tf_utils.transform_graph.bias_correction": [[128, "module-neural_compressor.adaptor.tf_utils.transform_graph.bias_correction"]], "neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base": [[129, "module-neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base"]], "neural_compressor.adaptor.tf_utils.transform_graph.insert_logging": [[131, "module-neural_compressor.adaptor.tf_utils.transform_graph.insert_logging"]], "neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat": [[132, "module-neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat"]], "neural_compressor.adaptor.tf_utils.util": [[133, "module-neural_compressor.adaptor.tf_utils.util"]], "neural_compressor.adaptor.torch_utils": [[136, "module-neural_compressor.adaptor.torch_utils"]], "neural_compressor.adaptor.torch_utils.bf16_convert": [[134, "module-neural_compressor.adaptor.torch_utils.bf16_convert"]], "neural_compressor.adaptor.torch_utils.hawq_metric": [[135, "module-neural_compressor.adaptor.torch_utils.hawq_metric"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant": [[137, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle": [[138, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize": [[139, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load": [[140, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils": [[141, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.utils"]], "neural_compressor.adaptor.torch_utils.model_wrapper": [[142, "module-neural_compressor.adaptor.torch_utils.model_wrapper"]], "neural_compressor.adaptor.torch_utils.pattern_detector": [[143, "module-neural_compressor.adaptor.torch_utils.pattern_detector"]], "neural_compressor.adaptor.torch_utils.symbolic_trace": [[144, "module-neural_compressor.adaptor.torch_utils.symbolic_trace"]], "neural_compressor.adaptor.torch_utils.util": [[145, "module-neural_compressor.adaptor.torch_utils.util"]], "neural_compressor.algorithm": [[148, "module-neural_compressor.algorithm"]], "neural_compressor.algorithm.algorithm": [[146, "module-neural_compressor.algorithm.algorithm"]], "neural_compressor.algorithm.fast_bias_correction": [[147, "module-neural_compressor.algorithm.fast_bias_correction"]], "neural_compressor.algorithm.smooth_quant": [[149, "module-neural_compressor.algorithm.smooth_quant"]], "neural_compressor.algorithm.weight_correction": [[150, "module-neural_compressor.algorithm.weight_correction"]], "neural_compressor.benchmark": [[151, "module-neural_compressor.benchmark"]], "neural_compressor.common": [[155, "module-neural_compressor.common"]], "neural_compressor.common.base_config": [[152, "module-neural_compressor.common.base_config"]], "neural_compressor.common.base_tuning": [[153, "module-neural_compressor.common.base_tuning"]], "neural_compressor.common.benchmark": [[154, "module-neural_compressor.common.benchmark"]], "neural_compressor.common.tuning_param": [[156, "module-neural_compressor.common.tuning_param"]], "neural_compressor.common.utils": [[158, "module-neural_compressor.common.utils"]], "neural_compressor.common.utils.constants": [[157, "module-neural_compressor.common.utils.constants"]], "neural_compressor.common.utils.logger": [[159, "module-neural_compressor.common.utils.logger"]], "neural_compressor.common.utils.save_load": [[160, "module-neural_compressor.common.utils.save_load"]], "neural_compressor.common.utils.utility": [[161, "module-neural_compressor.common.utils.utility"]], "neural_compressor.compression.callbacks": [[162, "module-neural_compressor.compression.callbacks"]], "neural_compressor.compression.distillation": [[164, "module-neural_compressor.compression.distillation"]], "neural_compressor.compression.distillation.criterions": [[163, "module-neural_compressor.compression.distillation.criterions"]], "neural_compressor.compression.distillation.optimizers": [[165, "module-neural_compressor.compression.distillation.optimizers"]], "neural_compressor.compression.distillation.utility": [[166, "module-neural_compressor.compression.distillation.utility"]], "neural_compressor.compression.hpo": [[167, "module-neural_compressor.compression.hpo"]], "neural_compressor.compression.hpo.sa_optimizer": [[168, "module-neural_compressor.compression.hpo.sa_optimizer"]], "neural_compressor.compression.pruner": [[170, "module-neural_compressor.compression.pruner"]], "neural_compressor.compression.pruner.criteria": [[169, "module-neural_compressor.compression.pruner.criteria"]], "neural_compressor.compression.pruner.model_slim": [[172, "module-neural_compressor.compression.pruner.model_slim"]], "neural_compressor.compression.pruner.model_slim.auto_slim": [[171, "module-neural_compressor.compression.pruner.model_slim.auto_slim"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer": [[173, "module-neural_compressor.compression.pruner.model_slim.pattern_analyzer"]], "neural_compressor.compression.pruner.model_slim.weight_slim": [[174, "module-neural_compressor.compression.pruner.model_slim.weight_slim"]], "neural_compressor.compression.pruner.patterns": [[176, "module-neural_compressor.compression.pruner.patterns"]], "neural_compressor.compression.pruner.patterns.base": [[175, "module-neural_compressor.compression.pruner.patterns.base"]], "neural_compressor.compression.pruner.patterns.mha": [[177, "module-neural_compressor.compression.pruner.patterns.mha"]], "neural_compressor.compression.pruner.patterns.ninm": [[178, "module-neural_compressor.compression.pruner.patterns.ninm"]], "neural_compressor.compression.pruner.patterns.nxm": [[179, "module-neural_compressor.compression.pruner.patterns.nxm"]], "neural_compressor.compression.pruner.pruners": [[183, "module-neural_compressor.compression.pruner.pruners"]], "neural_compressor.compression.pruner.pruners.base": [[180, "module-neural_compressor.compression.pruner.pruners.base"]], "neural_compressor.compression.pruner.pruners.basic": [[181, "module-neural_compressor.compression.pruner.pruners.basic"]], "neural_compressor.compression.pruner.pruners.block_mask": [[182, "module-neural_compressor.compression.pruner.pruners.block_mask"]], "neural_compressor.compression.pruner.pruners.mha": [[184, "module-neural_compressor.compression.pruner.pruners.mha"]], "neural_compressor.compression.pruner.pruners.pattern_lock": [[185, "module-neural_compressor.compression.pruner.pruners.pattern_lock"]], "neural_compressor.compression.pruner.pruners.progressive": [[186, "module-neural_compressor.compression.pruner.pruners.progressive"]], "neural_compressor.compression.pruner.pruners.retrain_free": [[187, "module-neural_compressor.compression.pruner.pruners.retrain_free"]], "neural_compressor.compression.pruner.pruning": [[188, "module-neural_compressor.compression.pruner.pruning"]], "neural_compressor.compression.pruner.regs": [[189, "module-neural_compressor.compression.pruner.regs"]], "neural_compressor.compression.pruner.schedulers": [[190, "module-neural_compressor.compression.pruner.schedulers"]], "neural_compressor.compression.pruner.tf_criteria": [[191, "module-neural_compressor.compression.pruner.tf_criteria"]], "neural_compressor.compression.pruner.utils": [[192, "module-neural_compressor.compression.pruner.utils"]], "neural_compressor.compression.pruner.wanda": [[193, "module-neural_compressor.compression.pruner.wanda"]], "neural_compressor.compression.pruner.wanda.utils": [[194, "module-neural_compressor.compression.pruner.wanda.utils"]], "neural_compressor.config": [[195, "module-neural_compressor.config"]], "neural_compressor.contrib": [[196, "module-neural_compressor.contrib"]], "neural_compressor.contrib.strategy": [[197, "module-neural_compressor.contrib.strategy"]], "neural_compressor.contrib.strategy.sigopt": [[198, "module-neural_compressor.contrib.strategy.sigopt"]], "neural_compressor.contrib.strategy.tpe": [[199, "module-neural_compressor.contrib.strategy.tpe"]], "neural_compressor.data": [[220, "module-neural_compressor.data"]], "neural_compressor.data.dataloaders.base_dataloader": [[200, "module-neural_compressor.data.dataloaders.base_dataloader"]], "neural_compressor.data.dataloaders.dataloader": [[201, "module-neural_compressor.data.dataloaders.dataloader"]], "neural_compressor.data.dataloaders.default_dataloader": [[202, "module-neural_compressor.data.dataloaders.default_dataloader"]], "neural_compressor.data.dataloaders.fetcher": [[203, "module-neural_compressor.data.dataloaders.fetcher"]], "neural_compressor.data.dataloaders.mxnet_dataloader": [[204, "module-neural_compressor.data.dataloaders.mxnet_dataloader"]], "neural_compressor.data.dataloaders.onnxrt_dataloader": [[205, "module-neural_compressor.data.dataloaders.onnxrt_dataloader"]], "neural_compressor.data.dataloaders.pytorch_dataloader": [[206, "module-neural_compressor.data.dataloaders.pytorch_dataloader"]], "neural_compressor.data.dataloaders.sampler": [[207, "module-neural_compressor.data.dataloaders.sampler"]], "neural_compressor.data.dataloaders.tensorflow_dataloader": [[208, "module-neural_compressor.data.dataloaders.tensorflow_dataloader"]], "neural_compressor.data.datasets": [[215, "module-neural_compressor.data.datasets"]], "neural_compressor.data.datasets.bert_dataset": [[209, "module-neural_compressor.data.datasets.bert_dataset"]], "neural_compressor.data.datasets.coco_dataset": [[210, "module-neural_compressor.data.datasets.coco_dataset"]], "neural_compressor.data.datasets.dataset": [[211, "module-neural_compressor.data.datasets.dataset"]], "neural_compressor.data.datasets.dummy_dataset": [[212, "module-neural_compressor.data.datasets.dummy_dataset"]], "neural_compressor.data.datasets.dummy_dataset_v2": [[213, "module-neural_compressor.data.datasets.dummy_dataset_v2"]], "neural_compressor.data.datasets.imagenet_dataset": [[214, "module-neural_compressor.data.datasets.imagenet_dataset"]], "neural_compressor.data.datasets.style_transfer_dataset": [[216, "module-neural_compressor.data.datasets.style_transfer_dataset"]], "neural_compressor.data.filters": [[219, "module-neural_compressor.data.filters"]], "neural_compressor.data.filters.coco_filter": [[217, "module-neural_compressor.data.filters.coco_filter"]], "neural_compressor.data.filters.filter": [[218, "module-neural_compressor.data.filters.filter"]], "neural_compressor.data.transforms": [[222, "module-neural_compressor.data.transforms"]], "neural_compressor.data.transforms.imagenet_transform": [[221, "module-neural_compressor.data.transforms.imagenet_transform"]], "neural_compressor.data.transforms.postprocess": [[223, "module-neural_compressor.data.transforms.postprocess"]], "neural_compressor.data.transforms.tokenization": [[224, "module-neural_compressor.data.transforms.tokenization"]], "neural_compressor.data.transforms.transform": [[225, "module-neural_compressor.data.transforms.transform"]], "neural_compressor.metric": [[233, "module-neural_compressor.metric"]], "neural_compressor.metric.bleu": [[227, "module-neural_compressor.metric.bleu"]], "neural_compressor.metric.bleu_util": [[228, "module-neural_compressor.metric.bleu_util"]], "neural_compressor.metric.coco_label_map": [[229, "module-neural_compressor.metric.coco_label_map"]], "neural_compressor.metric.coco_tools": [[230, "module-neural_compressor.metric.coco_tools"]], "neural_compressor.metric.evaluate_squad": [[231, "module-neural_compressor.metric.evaluate_squad"]], "neural_compressor.metric.f1": [[232, "module-neural_compressor.metric.f1"]], "neural_compressor.metric.metric": [[234, "module-neural_compressor.metric.metric"]], "neural_compressor.mix_precision": [[235, "module-neural_compressor.mix_precision"]], "neural_compressor.model": [[237, "module-neural_compressor.model"]], "neural_compressor.model.base_model": [[236, "module-neural_compressor.model.base_model"]], "neural_compressor.model.keras_model": [[238, "module-neural_compressor.model.keras_model"]], "neural_compressor.model.model": [[239, "module-neural_compressor.model.model"]], "neural_compressor.model.mxnet_model": [[240, "module-neural_compressor.model.mxnet_model"]], "neural_compressor.model.nets_factory": [[241, "module-neural_compressor.model.nets_factory"]], "neural_compressor.model.onnx_model": [[242, "module-neural_compressor.model.onnx_model"]], "neural_compressor.model.tensorflow_model": [[243, "module-neural_compressor.model.tensorflow_model"]], "neural_compressor.model.torch_model": [[244, "module-neural_compressor.model.torch_model"]], "neural_compressor.objective": [[245, "module-neural_compressor.objective"]], "neural_compressor.profiling": [[246, "module-neural_compressor.profiling"]], "neural_compressor.profiling.parser.factory": [[247, "module-neural_compressor.profiling.parser.factory"]], "neural_compressor.profiling.parser.onnx_parser.factory": [[248, "module-neural_compressor.profiling.parser.onnx_parser.factory"]], "neural_compressor.profiling.parser.onnx_parser.parser": [[249, "module-neural_compressor.profiling.parser.onnx_parser.parser"]], "neural_compressor.profiling.parser.parser": [[250, "module-neural_compressor.profiling.parser.parser"]], "neural_compressor.profiling.parser.result": [[251, "module-neural_compressor.profiling.parser.result"]], "neural_compressor.profiling.parser.tensorflow_parser.factory": [[252, "module-neural_compressor.profiling.parser.tensorflow_parser.factory"]], "neural_compressor.profiling.parser.tensorflow_parser.parser": [[253, "module-neural_compressor.profiling.parser.tensorflow_parser.parser"]], "neural_compressor.profiling.profiler.factory": [[254, "module-neural_compressor.profiling.profiler.factory"]], "neural_compressor.profiling.profiler.onnxrt_profiler.factory": [[255, "module-neural_compressor.profiling.profiler.onnxrt_profiler.factory"]], "neural_compressor.profiling.profiler.onnxrt_profiler.profiler": [[256, "module-neural_compressor.profiling.profiler.onnxrt_profiler.profiler"]], "neural_compressor.profiling.profiler.onnxrt_profiler.utils": [[257, "module-neural_compressor.profiling.profiler.onnxrt_profiler.utils"]], "neural_compressor.profiling.profiler.profiler": [[258, "module-neural_compressor.profiling.profiler.profiler"]], "neural_compressor.profiling.profiler.tensorflow_profiler.factory": [[259, "module-neural_compressor.profiling.profiler.tensorflow_profiler.factory"]], "neural_compressor.profiling.profiler.tensorflow_profiler.profiler": [[260, "module-neural_compressor.profiling.profiler.tensorflow_profiler.profiler"]], "neural_compressor.profiling.profiler.tensorflow_profiler.utils": [[261, "module-neural_compressor.profiling.profiler.tensorflow_profiler.utils"]], "neural_compressor.quantization": [[262, "module-neural_compressor.quantization"]], "neural_compressor.strategy": [[270, "module-neural_compressor.strategy"]], "neural_compressor.strategy.auto": [[263, "module-neural_compressor.strategy.auto"]], "neural_compressor.strategy.auto_mixed_precision": [[264, "module-neural_compressor.strategy.auto_mixed_precision"]], "neural_compressor.strategy.basic": [[265, "module-neural_compressor.strategy.basic"]], "neural_compressor.strategy.bayesian": [[266, "module-neural_compressor.strategy.bayesian"]], "neural_compressor.strategy.conservative": [[267, "module-neural_compressor.strategy.conservative"]], "neural_compressor.strategy.exhaustive": [[268, "module-neural_compressor.strategy.exhaustive"]], "neural_compressor.strategy.hawq_v2": [[269, "module-neural_compressor.strategy.hawq_v2"]], "neural_compressor.strategy.mse": [[271, "module-neural_compressor.strategy.mse"]], "neural_compressor.strategy.mse_v2": [[272, "module-neural_compressor.strategy.mse_v2"]], "neural_compressor.strategy.random": [[273, "module-neural_compressor.strategy.random"]], "neural_compressor.strategy.strategy": [[274, "module-neural_compressor.strategy.strategy"]], "neural_compressor.strategy.utils": [[276, "module-neural_compressor.strategy.utils"]], "neural_compressor.strategy.utils.constant": [[275, "module-neural_compressor.strategy.utils.constant"]], "neural_compressor.strategy.utils.tuning_sampler": [[277, "module-neural_compressor.strategy.utils.tuning_sampler"]], "neural_compressor.strategy.utils.tuning_space": [[278, "module-neural_compressor.strategy.utils.tuning_space"]], "neural_compressor.strategy.utils.tuning_structs": [[279, "module-neural_compressor.strategy.utils.tuning_structs"]], "neural_compressor.strategy.utils.utility": [[280, "module-neural_compressor.strategy.utils.utility"]], "neural_compressor.template.api_doc_example": [[281, "module-neural_compressor.template.api_doc_example"]], "neural_compressor.tensorflow": [[290, "module-neural_compressor.tensorflow"]], "neural_compressor.tensorflow.algorithms": [[282, "module-neural_compressor.tensorflow.algorithms"]], "neural_compressor.tensorflow.algorithms.smoother": [[285, "module-neural_compressor.tensorflow.algorithms.smoother"]], "neural_compressor.tensorflow.algorithms.smoother.calibration": [[283, "module-neural_compressor.tensorflow.algorithms.smoother.calibration"]], "neural_compressor.tensorflow.algorithms.smoother.core": [[284, "module-neural_compressor.tensorflow.algorithms.smoother.core"]], "neural_compressor.tensorflow.algorithms.smoother.scaler": [[286, "module-neural_compressor.tensorflow.algorithms.smoother.scaler"]], "neural_compressor.tensorflow.algorithms.static_quant": [[287, "module-neural_compressor.tensorflow.algorithms.static_quant"]], "neural_compressor.tensorflow.algorithms.static_quant.keras": [[288, "module-neural_compressor.tensorflow.algorithms.static_quant.keras"]], "neural_compressor.tensorflow.algorithms.static_quant.tensorflow": [[289, "module-neural_compressor.tensorflow.algorithms.static_quant.tensorflow"]], "neural_compressor.tensorflow.keras": [[291, "module-neural_compressor.tensorflow.keras"]], "neural_compressor.tensorflow.keras.layers": [[295, "module-neural_compressor.tensorflow.keras.layers"]], "neural_compressor.tensorflow.keras.layers.conv2d": [[292, "module-neural_compressor.tensorflow.keras.layers.conv2d"]], "neural_compressor.tensorflow.keras.layers.dense": [[293, "module-neural_compressor.tensorflow.keras.layers.dense"]], "neural_compressor.tensorflow.keras.layers.depthwise_conv2d": [[294, "module-neural_compressor.tensorflow.keras.layers.depthwise_conv2d"]], "neural_compressor.tensorflow.keras.layers.layer_initializer": [[296, "module-neural_compressor.tensorflow.keras.layers.layer_initializer"]], "neural_compressor.tensorflow.keras.layers.pool2d": [[297, "module-neural_compressor.tensorflow.keras.layers.pool2d"]], "neural_compressor.tensorflow.keras.layers.separable_conv2d": [[298, "module-neural_compressor.tensorflow.keras.layers.separable_conv2d"]], "neural_compressor.tensorflow.keras.quantization": [[300, "module-neural_compressor.tensorflow.keras.quantization"]], "neural_compressor.tensorflow.keras.quantization.config": [[299, "module-neural_compressor.tensorflow.keras.quantization.config"]], "neural_compressor.tensorflow.quantization": [[304, "module-neural_compressor.tensorflow.quantization"]], "neural_compressor.tensorflow.quantization.algorithm_entry": [[301, "module-neural_compressor.tensorflow.quantization.algorithm_entry"]], "neural_compressor.tensorflow.quantization.autotune": [[302, "module-neural_compressor.tensorflow.quantization.autotune"]], "neural_compressor.tensorflow.quantization.config": [[303, "module-neural_compressor.tensorflow.quantization.config"]], "neural_compressor.tensorflow.quantization.quantize": [[305, "module-neural_compressor.tensorflow.quantization.quantize"]], "neural_compressor.tensorflow.quantization.utils": [[361, "module-neural_compressor.tensorflow.quantization.utils"]], "neural_compressor.tensorflow.quantization.utils.graph_converter": [[306, "module-neural_compressor.tensorflow.quantization.utils.graph_converter"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter": [[344, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16": [[309, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert": [[307, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer": [[308, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic": [[333, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd": [[310, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout": [[311, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu": [[312, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random": [[313, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const": [[314, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction": [[315, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd": [[316, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer": [[317, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape": [[318, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm": [[319, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant": [[320, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add": [[321, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul": [[322, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math": [[323, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn": [[324, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in": [[325, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu": [[326, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm": [[327, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv": [[328, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv": [[329, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose": [[330, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer": [[331, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass": [[332, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node": [[334, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu": [[335, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize": [[336, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes": [[337, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm": [[338, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input": [[339, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes": [[340, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes": [[341, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer": [[342, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base": [[343, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8": [[351, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant": [[345, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value": [[346, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize": [[347, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize": [[348, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize": [[349, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize": [[350, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer": [[352, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter": [[353, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse": [[354, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation": [[355, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq": [[356, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern": [[357, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq": [[358, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern": [[359, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern"]], "neural_compressor.tensorflow.quantization.utils.graph_util": [[360, "module-neural_compressor.tensorflow.quantization.utils.graph_util"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph": [[362, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq": [[370, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn": [[363, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2": [[364, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv": [[365, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv": [[366, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in": [[367, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul": [[368, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling": [[369, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq": [[371, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base": [[372, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn": [[373, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2": [[374, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv": [[375, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu": [[376, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul": [[377, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling": [[378, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph_common": [[379, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph_common"]], "neural_compressor.tensorflow.quantization.utils.transform_graph": [[382, "module-neural_compressor.tensorflow.quantization.utils.transform_graph"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction": [[380, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base": [[381, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging": [[383, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat": [[384, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat"]], "neural_compressor.tensorflow.quantization.utils.utility": [[385, "module-neural_compressor.tensorflow.quantization.utils.utility"]], "neural_compressor.tensorflow.utils": [[388, "module-neural_compressor.tensorflow.utils"]], "neural_compressor.tensorflow.utils.constants": [[386, "module-neural_compressor.tensorflow.utils.constants"]], "neural_compressor.tensorflow.utils.data": [[387, "module-neural_compressor.tensorflow.utils.data"]], "neural_compressor.tensorflow.utils.model": [[389, "module-neural_compressor.tensorflow.utils.model"]], "neural_compressor.tensorflow.utils.model_wrappers": [[390, "module-neural_compressor.tensorflow.utils.model_wrappers"]], "neural_compressor.tensorflow.utils.utility": [[391, "module-neural_compressor.tensorflow.utils.utility"]], "neural_compressor.torch": [[436, "module-neural_compressor.torch"]], "neural_compressor.torch.algorithms": [[394, "module-neural_compressor.torch.algorithms"]], "neural_compressor.torch.algorithms.base_algorithm": [[392, "module-neural_compressor.torch.algorithms.base_algorithm"]], "neural_compressor.torch.algorithms.fp8_quant.utils.logger": [[393, "module-neural_compressor.torch.algorithms.fp8_quant.utils.logger"]], "neural_compressor.torch.algorithms.layer_wise": [[395, "module-neural_compressor.torch.algorithms.layer_wise"]], "neural_compressor.torch.algorithms.layer_wise.load": [[396, "module-neural_compressor.torch.algorithms.layer_wise.load"]], "neural_compressor.torch.algorithms.layer_wise.modified_pickle": [[397, "module-neural_compressor.torch.algorithms.layer_wise.modified_pickle"]], "neural_compressor.torch.algorithms.layer_wise.utils": [[398, "module-neural_compressor.torch.algorithms.layer_wise.utils"]], "neural_compressor.torch.algorithms.mixed_precision": [[400, "module-neural_compressor.torch.algorithms.mixed_precision"]], "neural_compressor.torch.algorithms.mixed_precision.half_precision_convert": [[399, "module-neural_compressor.torch.algorithms.mixed_precision.half_precision_convert"]], "neural_compressor.torch.algorithms.mixed_precision.module_wrappers": [[401, "module-neural_compressor.torch.algorithms.mixed_precision.module_wrappers"]], "neural_compressor.torch.algorithms.mx_quant": [[402, "module-neural_compressor.torch.algorithms.mx_quant"]], "neural_compressor.torch.algorithms.mx_quant.mx": [[403, "module-neural_compressor.torch.algorithms.mx_quant.mx"]], "neural_compressor.torch.algorithms.mx_quant.utils": [[404, "module-neural_compressor.torch.algorithms.mx_quant.utils"]], "neural_compressor.torch.algorithms.pt2e_quant": [[407, "module-neural_compressor.torch.algorithms.pt2e_quant"]], "neural_compressor.torch.algorithms.pt2e_quant.core": [[405, "module-neural_compressor.torch.algorithms.pt2e_quant.core"]], "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter": [[406, "module-neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter"]], "neural_compressor.torch.algorithms.pt2e_quant.save_load": [[408, "module-neural_compressor.torch.algorithms.pt2e_quant.save_load"]], "neural_compressor.torch.algorithms.pt2e_quant.utility": [[409, "module-neural_compressor.torch.algorithms.pt2e_quant.utility"]], "neural_compressor.torch.algorithms.smooth_quant": [[410, "module-neural_compressor.torch.algorithms.smooth_quant"]], "neural_compressor.torch.algorithms.smooth_quant.save_load": [[411, "module-neural_compressor.torch.algorithms.smooth_quant.save_load"]], "neural_compressor.torch.algorithms.smooth_quant.smooth_quant": [[412, "module-neural_compressor.torch.algorithms.smooth_quant.smooth_quant"]], "neural_compressor.torch.algorithms.smooth_quant.utility": [[413, "module-neural_compressor.torch.algorithms.smooth_quant.utility"]], "neural_compressor.torch.algorithms.static_quant": [[414, "module-neural_compressor.torch.algorithms.static_quant"]], "neural_compressor.torch.algorithms.static_quant.save_load": [[415, "module-neural_compressor.torch.algorithms.static_quant.save_load"]], "neural_compressor.torch.algorithms.static_quant.static_quant": [[416, "module-neural_compressor.torch.algorithms.static_quant.static_quant"]], "neural_compressor.torch.algorithms.static_quant.utility": [[417, "module-neural_compressor.torch.algorithms.static_quant.utility"]], "neural_compressor.torch.algorithms.weight_only": [[428, "module-neural_compressor.torch.algorithms.weight_only"]], "neural_compressor.torch.algorithms.weight_only.autoround": [[418, "module-neural_compressor.torch.algorithms.weight_only.autoround"]], "neural_compressor.torch.algorithms.weight_only.awq": [[419, "module-neural_compressor.torch.algorithms.weight_only.awq"]], "neural_compressor.torch.algorithms.weight_only.gptq": [[420, "module-neural_compressor.torch.algorithms.weight_only.gptq"]], "neural_compressor.torch.algorithms.weight_only.hqq": [[424, "module-neural_compressor.torch.algorithms.weight_only.hqq"]], "neural_compressor.torch.algorithms.weight_only.hqq.bitpack": [[421, "module-neural_compressor.torch.algorithms.weight_only.hqq.bitpack"]], "neural_compressor.torch.algorithms.weight_only.hqq.config": [[422, "module-neural_compressor.torch.algorithms.weight_only.hqq.config"]], "neural_compressor.torch.algorithms.weight_only.hqq.core": [[423, "module-neural_compressor.torch.algorithms.weight_only.hqq.core"]], "neural_compressor.torch.algorithms.weight_only.hqq.optimizer": [[425, "module-neural_compressor.torch.algorithms.weight_only.hqq.optimizer"]], "neural_compressor.torch.algorithms.weight_only.hqq.qtensor": [[426, "module-neural_compressor.torch.algorithms.weight_only.hqq.qtensor"]], "neural_compressor.torch.algorithms.weight_only.hqq.quantizer": [[427, "module-neural_compressor.torch.algorithms.weight_only.hqq.quantizer"]], "neural_compressor.torch.algorithms.weight_only.modules": [[429, "module-neural_compressor.torch.algorithms.weight_only.modules"]], "neural_compressor.torch.algorithms.weight_only.rtn": [[430, "module-neural_compressor.torch.algorithms.weight_only.rtn"]], "neural_compressor.torch.algorithms.weight_only.save_load": [[431, "module-neural_compressor.torch.algorithms.weight_only.save_load"]], "neural_compressor.torch.algorithms.weight_only.teq": [[432, "module-neural_compressor.torch.algorithms.weight_only.teq"]], "neural_compressor.torch.algorithms.weight_only.utility": [[433, "module-neural_compressor.torch.algorithms.weight_only.utility"]], "neural_compressor.torch.export": [[434, "module-neural_compressor.torch.export"]], "neural_compressor.torch.export.pt2e_export": [[435, "module-neural_compressor.torch.export.pt2e_export"]], "neural_compressor.torch.quantization": [[440, "module-neural_compressor.torch.quantization"]], "neural_compressor.torch.quantization.algorithm_entry": [[437, "module-neural_compressor.torch.quantization.algorithm_entry"]], "neural_compressor.torch.quantization.autotune": [[438, "module-neural_compressor.torch.quantization.autotune"]], "neural_compressor.torch.quantization.config": [[439, "module-neural_compressor.torch.quantization.config"]], "neural_compressor.torch.quantization.load_entry": [[441, "module-neural_compressor.torch.quantization.load_entry"]], "neural_compressor.torch.quantization.quantize": [[442, "module-neural_compressor.torch.quantization.quantize"]], "neural_compressor.torch.utils": [[446, "module-neural_compressor.torch.utils"]], "neural_compressor.torch.utils.auto_accelerator": [[443, "module-neural_compressor.torch.utils.auto_accelerator"]], "neural_compressor.torch.utils.constants": [[444, "module-neural_compressor.torch.utils.constants"]], "neural_compressor.torch.utils.environ": [[445, "module-neural_compressor.torch.utils.environ"]], "neural_compressor.torch.utils.utility": [[447, "module-neural_compressor.torch.utils.utility"]], "neural_compressor.training": [[448, "module-neural_compressor.training"]], "neural_compressor.transformers.quantization.utils": [[449, "module-neural_compressor.transformers.quantization.utils"]], "neural_compressor.transformers.utils": [[450, "module-neural_compressor.transformers.utils"]], "neural_compressor.transformers.utils.quantization_config": [[451, "module-neural_compressor.transformers.utils.quantization_config"]], "neural_compressor.utils": [[459, "module-neural_compressor.utils"]], "neural_compressor.utils.collect_layer_histogram": [[452, "module-neural_compressor.utils.collect_layer_histogram"]], "neural_compressor.utils.constant": [[453, "module-neural_compressor.utils.constant"]], "neural_compressor.utils.create_obj_from_config": [[454, "module-neural_compressor.utils.create_obj_from_config"]], "neural_compressor.utils.export": [[455, "module-neural_compressor.utils.export"]], "neural_compressor.utils.export.qlinear2qdq": [[456, "module-neural_compressor.utils.export.qlinear2qdq"]], "neural_compressor.utils.export.tf2onnx": [[457, "module-neural_compressor.utils.export.tf2onnx"]], "neural_compressor.utils.export.torch2onnx": [[458, "module-neural_compressor.utils.export.torch2onnx"]], "neural_compressor.utils.kl_divergence": [[460, "module-neural_compressor.utils.kl_divergence"]], "neural_compressor.utils.load_huggingface": [[461, "module-neural_compressor.utils.load_huggingface"]], "neural_compressor.utils.logger": [[462, "module-neural_compressor.utils.logger"]], "neural_compressor.utils.options": [[463, "module-neural_compressor.utils.options"]], "neural_compressor.utils.pytorch": [[464, "module-neural_compressor.utils.pytorch"]], "neural_compressor.utils.utility": [[465, "module-neural_compressor.utils.utility"]], "neural_compressor.utils.weights_details": [[466, "module-neural_compressor.utils.weights_details"]], "neural_compressor.version": [[467, "module-neural_compressor.version"]], "}": [[145, "id3"]]}, "docnames": ["autoapi/neural_compressor/adaptor/mxnet_utils/index", "autoapi/neural_compressor/adaptor/mxnet_utils/util/index", "autoapi/neural_compressor/adaptor/ox_utils/calibration/index", "autoapi/neural_compressor/adaptor/ox_utils/calibrator/index", "autoapi/neural_compressor/adaptor/ox_utils/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/activation/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/argmax/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/attention/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/binary_op/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/concat/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/conv/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/direct_q8/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/embed_layernorm/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/gather/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/gavgpool/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/gemm/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/lstm/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/matmul/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/maxpool/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/norm/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/ops/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/pad/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/pooling/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/reduce/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/resize/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/split/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/unary_op/index", "autoapi/neural_compressor/adaptor/ox_utils/quantizer/index", "autoapi/neural_compressor/adaptor/ox_utils/smooth_quant/index", "autoapi/neural_compressor/adaptor/ox_utils/util/index", "autoapi/neural_compressor/adaptor/ox_utils/weight_only/index", "autoapi/neural_compressor/adaptor/tensorflow/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_converter/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_converter_without_calib/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/bf16_convert/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/dequantize_cast_optimizer/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_add_to_biasadd/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_layout/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_leakyrelu/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_nan_to_random/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_placeholder_to_const/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dilated_contraction/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dummy_biasadd/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/expanddims_optimizer/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fetch_weight_from_reshape/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_batch_norm/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_constant/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_biasadd_add/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_column_wise_mul/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_conv_with_math/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_bn/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_in/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_gelu/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_layer_norm/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_conv/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_reshape_transpose/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/graph_cse_optimizer/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/grappler_pass/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/insert_print_node/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/move_squeeze_after_relu/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/pre_optimize/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/remove_training_nodes/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/rename_batch_norm/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/split_shared_input/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_equivalent_nodes/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_unused_nodes/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/switch_optimizer/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/graph_base/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_fake_quant/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value_without_calib/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_requantize/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_requantize/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/meta_op_optimizer/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_hostconst_converter/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_quantized_op_cse/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/rnn_convert/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/scale_propagation/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_graph/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_node/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_schema/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/tf2onnx_utils/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/insert_qdq_pattern/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/merge_duplicated_qdq/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/share_qdq_y_pattern/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_util/index", "autoapi/neural_compressor/adaptor/tf_utils/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/fake_quantize/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_config/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_helper/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/optimize_layer/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_add/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_base/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_bn/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_wrapper/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_bn/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_concatv2/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_conv/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_deconv/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_in/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_matmul/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_pooling/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/optimize_qdq/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_base/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_bn/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_concatv2/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_conv/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_for_intel_cpu/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_matmul/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_pooling/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph_common/index", "autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_calibration/index", "autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_scaler/index", "autoapi/neural_compressor/adaptor/tf_utils/tf2onnx_converter/index", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/bias_correction/index", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/graph_transform_base/index", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/index", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/insert_logging/index", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/rerange_quantized_concat/index", "autoapi/neural_compressor/adaptor/tf_utils/util/index", "autoapi/neural_compressor/adaptor/torch_utils/bf16_convert/index", "autoapi/neural_compressor/adaptor/torch_utils/hawq_metric/index", "autoapi/neural_compressor/adaptor/torch_utils/index", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/index", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/modified_pickle/index", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/quantize/index", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/torch_load/index", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/utils/index", "autoapi/neural_compressor/adaptor/torch_utils/model_wrapper/index", "autoapi/neural_compressor/adaptor/torch_utils/pattern_detector/index", "autoapi/neural_compressor/adaptor/torch_utils/symbolic_trace/index", "autoapi/neural_compressor/adaptor/torch_utils/util/index", "autoapi/neural_compressor/algorithm/algorithm/index", "autoapi/neural_compressor/algorithm/fast_bias_correction/index", "autoapi/neural_compressor/algorithm/index", "autoapi/neural_compressor/algorithm/smooth_quant/index", "autoapi/neural_compressor/algorithm/weight_correction/index", "autoapi/neural_compressor/benchmark/index", "autoapi/neural_compressor/common/base_config/index", "autoapi/neural_compressor/common/base_tuning/index", "autoapi/neural_compressor/common/benchmark/index", "autoapi/neural_compressor/common/index", "autoapi/neural_compressor/common/tuning_param/index", "autoapi/neural_compressor/common/utils/constants/index", "autoapi/neural_compressor/common/utils/index", "autoapi/neural_compressor/common/utils/logger/index", "autoapi/neural_compressor/common/utils/save_load/index", "autoapi/neural_compressor/common/utils/utility/index", "autoapi/neural_compressor/compression/callbacks/index", "autoapi/neural_compressor/compression/distillation/criterions/index", "autoapi/neural_compressor/compression/distillation/index", "autoapi/neural_compressor/compression/distillation/optimizers/index", "autoapi/neural_compressor/compression/distillation/utility/index", "autoapi/neural_compressor/compression/hpo/index", "autoapi/neural_compressor/compression/hpo/sa_optimizer/index", "autoapi/neural_compressor/compression/pruner/criteria/index", "autoapi/neural_compressor/compression/pruner/index", "autoapi/neural_compressor/compression/pruner/model_slim/auto_slim/index", "autoapi/neural_compressor/compression/pruner/model_slim/index", "autoapi/neural_compressor/compression/pruner/model_slim/pattern_analyzer/index", "autoapi/neural_compressor/compression/pruner/model_slim/weight_slim/index", "autoapi/neural_compressor/compression/pruner/patterns/base/index", "autoapi/neural_compressor/compression/pruner/patterns/index", "autoapi/neural_compressor/compression/pruner/patterns/mha/index", "autoapi/neural_compressor/compression/pruner/patterns/ninm/index", "autoapi/neural_compressor/compression/pruner/patterns/nxm/index", "autoapi/neural_compressor/compression/pruner/pruners/base/index", "autoapi/neural_compressor/compression/pruner/pruners/basic/index", "autoapi/neural_compressor/compression/pruner/pruners/block_mask/index", "autoapi/neural_compressor/compression/pruner/pruners/index", "autoapi/neural_compressor/compression/pruner/pruners/mha/index", "autoapi/neural_compressor/compression/pruner/pruners/pattern_lock/index", "autoapi/neural_compressor/compression/pruner/pruners/progressive/index", "autoapi/neural_compressor/compression/pruner/pruners/retrain_free/index", "autoapi/neural_compressor/compression/pruner/pruning/index", "autoapi/neural_compressor/compression/pruner/regs/index", "autoapi/neural_compressor/compression/pruner/schedulers/index", "autoapi/neural_compressor/compression/pruner/tf_criteria/index", "autoapi/neural_compressor/compression/pruner/utils/index", "autoapi/neural_compressor/compression/pruner/wanda/index", "autoapi/neural_compressor/compression/pruner/wanda/utils/index", "autoapi/neural_compressor/config/index", "autoapi/neural_compressor/contrib/index", "autoapi/neural_compressor/contrib/strategy/index", "autoapi/neural_compressor/contrib/strategy/sigopt/index", "autoapi/neural_compressor/contrib/strategy/tpe/index", "autoapi/neural_compressor/data/dataloaders/base_dataloader/index", "autoapi/neural_compressor/data/dataloaders/dataloader/index", "autoapi/neural_compressor/data/dataloaders/default_dataloader/index", "autoapi/neural_compressor/data/dataloaders/fetcher/index", "autoapi/neural_compressor/data/dataloaders/mxnet_dataloader/index", "autoapi/neural_compressor/data/dataloaders/onnxrt_dataloader/index", "autoapi/neural_compressor/data/dataloaders/pytorch_dataloader/index", "autoapi/neural_compressor/data/dataloaders/sampler/index", "autoapi/neural_compressor/data/dataloaders/tensorflow_dataloader/index", "autoapi/neural_compressor/data/datasets/bert_dataset/index", "autoapi/neural_compressor/data/datasets/coco_dataset/index", "autoapi/neural_compressor/data/datasets/dataset/index", "autoapi/neural_compressor/data/datasets/dummy_dataset/index", "autoapi/neural_compressor/data/datasets/dummy_dataset_v2/index", "autoapi/neural_compressor/data/datasets/imagenet_dataset/index", "autoapi/neural_compressor/data/datasets/index", "autoapi/neural_compressor/data/datasets/style_transfer_dataset/index", "autoapi/neural_compressor/data/filters/coco_filter/index", "autoapi/neural_compressor/data/filters/filter/index", "autoapi/neural_compressor/data/filters/index", "autoapi/neural_compressor/data/index", "autoapi/neural_compressor/data/transforms/imagenet_transform/index", "autoapi/neural_compressor/data/transforms/index", "autoapi/neural_compressor/data/transforms/postprocess/index", "autoapi/neural_compressor/data/transforms/tokenization/index", "autoapi/neural_compressor/data/transforms/transform/index", "autoapi/neural_compressor/index", "autoapi/neural_compressor/metric/bleu/index", "autoapi/neural_compressor/metric/bleu_util/index", "autoapi/neural_compressor/metric/coco_label_map/index", "autoapi/neural_compressor/metric/coco_tools/index", "autoapi/neural_compressor/metric/evaluate_squad/index", "autoapi/neural_compressor/metric/f1/index", "autoapi/neural_compressor/metric/index", "autoapi/neural_compressor/metric/metric/index", "autoapi/neural_compressor/mix_precision/index", "autoapi/neural_compressor/model/base_model/index", "autoapi/neural_compressor/model/index", "autoapi/neural_compressor/model/keras_model/index", "autoapi/neural_compressor/model/model/index", "autoapi/neural_compressor/model/mxnet_model/index", "autoapi/neural_compressor/model/nets_factory/index", "autoapi/neural_compressor/model/onnx_model/index", "autoapi/neural_compressor/model/tensorflow_model/index", "autoapi/neural_compressor/model/torch_model/index", "autoapi/neural_compressor/objective/index", "autoapi/neural_compressor/profiling/index", "autoapi/neural_compressor/profiling/parser/factory/index", "autoapi/neural_compressor/profiling/parser/onnx_parser/factory/index", "autoapi/neural_compressor/profiling/parser/onnx_parser/parser/index", "autoapi/neural_compressor/profiling/parser/parser/index", "autoapi/neural_compressor/profiling/parser/result/index", "autoapi/neural_compressor/profiling/parser/tensorflow_parser/factory/index", "autoapi/neural_compressor/profiling/parser/tensorflow_parser/parser/index", "autoapi/neural_compressor/profiling/profiler/factory/index", "autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/factory/index", "autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/profiler/index", "autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/utils/index", "autoapi/neural_compressor/profiling/profiler/profiler/index", "autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/factory/index", "autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/profiler/index", "autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/utils/index", "autoapi/neural_compressor/quantization/index", "autoapi/neural_compressor/strategy/auto/index", "autoapi/neural_compressor/strategy/auto_mixed_precision/index", "autoapi/neural_compressor/strategy/basic/index", "autoapi/neural_compressor/strategy/bayesian/index", "autoapi/neural_compressor/strategy/conservative/index", "autoapi/neural_compressor/strategy/exhaustive/index", "autoapi/neural_compressor/strategy/hawq_v2/index", "autoapi/neural_compressor/strategy/index", "autoapi/neural_compressor/strategy/mse/index", "autoapi/neural_compressor/strategy/mse_v2/index", "autoapi/neural_compressor/strategy/random/index", "autoapi/neural_compressor/strategy/strategy/index", "autoapi/neural_compressor/strategy/utils/constant/index", "autoapi/neural_compressor/strategy/utils/index", "autoapi/neural_compressor/strategy/utils/tuning_sampler/index", "autoapi/neural_compressor/strategy/utils/tuning_space/index", "autoapi/neural_compressor/strategy/utils/tuning_structs/index", "autoapi/neural_compressor/strategy/utils/utility/index", "autoapi/neural_compressor/template/api_doc_example/index", "autoapi/neural_compressor/tensorflow/algorithms/index", "autoapi/neural_compressor/tensorflow/algorithms/smoother/calibration/index", "autoapi/neural_compressor/tensorflow/algorithms/smoother/core/index", "autoapi/neural_compressor/tensorflow/algorithms/smoother/index", "autoapi/neural_compressor/tensorflow/algorithms/smoother/scaler/index", "autoapi/neural_compressor/tensorflow/algorithms/static_quant/index", "autoapi/neural_compressor/tensorflow/algorithms/static_quant/keras/index", "autoapi/neural_compressor/tensorflow/algorithms/static_quant/tensorflow/index", "autoapi/neural_compressor/tensorflow/index", "autoapi/neural_compressor/tensorflow/keras/index", "autoapi/neural_compressor/tensorflow/keras/layers/conv2d/index", "autoapi/neural_compressor/tensorflow/keras/layers/dense/index", "autoapi/neural_compressor/tensorflow/keras/layers/depthwise_conv2d/index", "autoapi/neural_compressor/tensorflow/keras/layers/index", "autoapi/neural_compressor/tensorflow/keras/layers/layer_initializer/index", "autoapi/neural_compressor/tensorflow/keras/layers/pool2d/index", "autoapi/neural_compressor/tensorflow/keras/layers/separable_conv2d/index", "autoapi/neural_compressor/tensorflow/keras/quantization/config/index", "autoapi/neural_compressor/tensorflow/keras/quantization/index", "autoapi/neural_compressor/tensorflow/quantization/algorithm_entry/index", "autoapi/neural_compressor/tensorflow/quantization/autotune/index", "autoapi/neural_compressor/tensorflow/quantization/config/index", "autoapi/neural_compressor/tensorflow/quantization/index", "autoapi/neural_compressor/tensorflow/quantization/quantize/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_converter/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/bf16_convert/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/dequantize_cast_optimizer/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_add_to_biasadd/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_layout/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_leakyrelu/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_nan_to_random/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_placeholder_to_const/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dilated_contraction/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dummy_biasadd/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/expanddims_optimizer/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fetch_weight_from_reshape/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_batch_norm/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_constant/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_biasadd_add/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_column_wise_mul/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_conv_with_math/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_bn/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_in/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_gelu/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_layer_norm/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_conv/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_reshape_transpose/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/graph_cse_optimizer/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/grappler_pass/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/insert_print_node/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/move_squeeze_after_relu/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/pre_optimize/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/remove_training_nodes/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/rename_batch_norm/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/split_shared_input/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_equivalent_nodes/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_unused_nodes/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/switch_optimizer/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/graph_base/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_fake_quant/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_value/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_requantize/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_requantize/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/meta_op_optimizer/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_hostconst_converter/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_quantized_op_cse/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/scale_propagation/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/insert_qdq_pattern/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/merge_duplicated_qdq/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/share_qdq_y_pattern/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_util/index", "autoapi/neural_compressor/tensorflow/quantization/utils/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_bn/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_concatv2/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_conv/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_deconv/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_in/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_matmul/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_pooling/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/optimize_qdq/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_base/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_bn/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_concatv2/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_conv/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_for_intel_cpu/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_matmul/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_pooling/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph_common/index", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/bias_correction/index", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/graph_transform_base/index", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/index", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/insert_logging/index", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/rerange_quantized_concat/index", "autoapi/neural_compressor/tensorflow/quantization/utils/utility/index", "autoapi/neural_compressor/tensorflow/utils/constants/index", "autoapi/neural_compressor/tensorflow/utils/data/index", "autoapi/neural_compressor/tensorflow/utils/index", "autoapi/neural_compressor/tensorflow/utils/model/index", "autoapi/neural_compressor/tensorflow/utils/model_wrappers/index", "autoapi/neural_compressor/tensorflow/utils/utility/index", "autoapi/neural_compressor/torch/algorithms/base_algorithm/index", "autoapi/neural_compressor/torch/algorithms/fp8_quant/utils/logger/index", "autoapi/neural_compressor/torch/algorithms/index", "autoapi/neural_compressor/torch/algorithms/layer_wise/index", "autoapi/neural_compressor/torch/algorithms/layer_wise/load/index", "autoapi/neural_compressor/torch/algorithms/layer_wise/modified_pickle/index", "autoapi/neural_compressor/torch/algorithms/layer_wise/utils/index", "autoapi/neural_compressor/torch/algorithms/mixed_precision/half_precision_convert/index", "autoapi/neural_compressor/torch/algorithms/mixed_precision/index", "autoapi/neural_compressor/torch/algorithms/mixed_precision/module_wrappers/index", "autoapi/neural_compressor/torch/algorithms/mx_quant/index", "autoapi/neural_compressor/torch/algorithms/mx_quant/mx/index", "autoapi/neural_compressor/torch/algorithms/mx_quant/utils/index", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/core/index", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/half_precision_rewriter/index", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/index", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/save_load/index", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/utility/index", "autoapi/neural_compressor/torch/algorithms/smooth_quant/index", "autoapi/neural_compressor/torch/algorithms/smooth_quant/save_load/index", "autoapi/neural_compressor/torch/algorithms/smooth_quant/smooth_quant/index", "autoapi/neural_compressor/torch/algorithms/smooth_quant/utility/index", "autoapi/neural_compressor/torch/algorithms/static_quant/index", "autoapi/neural_compressor/torch/algorithms/static_quant/save_load/index", "autoapi/neural_compressor/torch/algorithms/static_quant/static_quant/index", "autoapi/neural_compressor/torch/algorithms/static_quant/utility/index", "autoapi/neural_compressor/torch/algorithms/weight_only/autoround/index", "autoapi/neural_compressor/torch/algorithms/weight_only/awq/index", "autoapi/neural_compressor/torch/algorithms/weight_only/gptq/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/bitpack/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/config/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/core/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/optimizer/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/qtensor/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/quantizer/index", "autoapi/neural_compressor/torch/algorithms/weight_only/index", "autoapi/neural_compressor/torch/algorithms/weight_only/modules/index", "autoapi/neural_compressor/torch/algorithms/weight_only/rtn/index", "autoapi/neural_compressor/torch/algorithms/weight_only/save_load/index", "autoapi/neural_compressor/torch/algorithms/weight_only/teq/index", "autoapi/neural_compressor/torch/algorithms/weight_only/utility/index", "autoapi/neural_compressor/torch/export/index", "autoapi/neural_compressor/torch/export/pt2e_export/index", "autoapi/neural_compressor/torch/index", "autoapi/neural_compressor/torch/quantization/algorithm_entry/index", "autoapi/neural_compressor/torch/quantization/autotune/index", "autoapi/neural_compressor/torch/quantization/config/index", "autoapi/neural_compressor/torch/quantization/index", "autoapi/neural_compressor/torch/quantization/load_entry/index", "autoapi/neural_compressor/torch/quantization/quantize/index", "autoapi/neural_compressor/torch/utils/auto_accelerator/index", "autoapi/neural_compressor/torch/utils/constants/index", "autoapi/neural_compressor/torch/utils/environ/index", "autoapi/neural_compressor/torch/utils/index", "autoapi/neural_compressor/torch/utils/utility/index", "autoapi/neural_compressor/training/index", "autoapi/neural_compressor/transformers/quantization/utils/index", "autoapi/neural_compressor/transformers/utils/index", "autoapi/neural_compressor/transformers/utils/quantization_config/index", "autoapi/neural_compressor/utils/collect_layer_histogram/index", "autoapi/neural_compressor/utils/constant/index", "autoapi/neural_compressor/utils/create_obj_from_config/index", "autoapi/neural_compressor/utils/export/index", "autoapi/neural_compressor/utils/export/qlinear2qdq/index", "autoapi/neural_compressor/utils/export/tf2onnx/index", "autoapi/neural_compressor/utils/export/torch2onnx/index", "autoapi/neural_compressor/utils/index", "autoapi/neural_compressor/utils/kl_divergence/index", "autoapi/neural_compressor/utils/load_huggingface/index", "autoapi/neural_compressor/utils/logger/index", "autoapi/neural_compressor/utils/options/index", "autoapi/neural_compressor/utils/pytorch/index", "autoapi/neural_compressor/utils/utility/index", "autoapi/neural_compressor/utils/weights_details/index", "autoapi/neural_compressor/version/index", "docs/build_docs/source/index", "docs/source/2x_user_guide", "docs/source/3x/PT_DynamicQuant", "docs/source/3x/PT_FP8Quant", "docs/source/3x/PT_MXQuant", "docs/source/3x/PT_MixedPrecision", "docs/source/3x/PT_SmoothQuant", "docs/source/3x/PT_StaticQuant", "docs/source/3x/PT_WeightOnlyQuant", "docs/source/3x/PyTorch", "docs/source/3x/TF_Quant", "docs/source/3x/TF_SQ", "docs/source/3x/TensorFlow", "docs/source/3x/autotune", "docs/source/3x/benchmark", "docs/source/3x/client_quant", "docs/source/3x/design", "docs/source/3x/gaudi_version_map", "docs/source/3x/llm_recipes", "docs/source/3x/quantization", "docs/source/CODE_OF_CONDUCT", "docs/source/CONTRIBUTING", "docs/source/FX", "docs/source/SECURITY", "docs/source/Welcome", "docs/source/adaptor", "docs/source/add_new_adaptor", "docs/source/add_new_data_type", "docs/source/api-doc/adaptor", "docs/source/api-doc/adaptor/onnxrt", "docs/source/api-doc/adaptor/torch_utils", "docs/source/api-doc/api_2", "docs/source/api-doc/api_3", "docs/source/api-doc/api_doc_example", "docs/source/api-doc/apis", "docs/source/api-doc/benchmark", "docs/source/api-doc/compression", "docs/source/api-doc/config", "docs/source/api-doc/mix_precision", "docs/source/api-doc/model", "docs/source/api-doc/objective", "docs/source/api-doc/quantization", "docs/source/api-doc/strategy", "docs/source/api-doc/tf_quantization_autotune", "docs/source/api-doc/tf_quantization_common", "docs/source/api-doc/tf_quantization_config", "docs/source/api-doc/torch_quantization_autotune", "docs/source/api-doc/torch_quantization_common", "docs/source/api-doc/torch_quantization_config", "docs/source/api-doc/training", "docs/source/benchmark", "docs/source/calibration", "docs/source/coding_style", "docs/source/dataloader", "docs/source/design", "docs/source/distillation_quantization", "docs/source/distributed", "docs/source/examples_readme", "docs/source/export", "docs/source/faq", "docs/source/framework_yaml", "docs/source/get_started", "docs/source/incompatible_changes", "docs/source/infrastructure", "docs/source/installation_guide", "docs/source/legal_information", "docs/source/llm_recipes", "docs/source/metric", "docs/source/migration", "docs/source/mixed_precision", "docs/source/model", "docs/source/mx_quantization", "docs/source/objective", "docs/source/orchestration", "docs/source/pruning", "docs/source/publication_list", "docs/source/quantization", "docs/source/quantization_layer_wise", "docs/source/quantization_mixed_precision", "docs/source/quantization_weight_only", "docs/source/releases_info", "docs/source/sigopt_strategy", "docs/source/smooth_quant", "docs/source/transform", "docs/source/tuning_strategies", "docs/source/validated_model_list", "index"], "envversion": {"sphinx": 61, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2}, "filenames": ["autoapi/neural_compressor/adaptor/mxnet_utils/index.rst", "autoapi/neural_compressor/adaptor/mxnet_utils/util/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/calibration/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/calibrator/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/activation/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/argmax/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/attention/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/binary_op/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/concat/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/conv/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/direct_q8/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/embed_layernorm/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/gather/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/gavgpool/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/gemm/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/lstm/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/matmul/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/maxpool/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/norm/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/ops/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/pad/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/pooling/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/reduce/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/resize/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/split/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/unary_op/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/quantizer/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/smooth_quant/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/util/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/weight_only/index.rst", "autoapi/neural_compressor/adaptor/tensorflow/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_converter/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_converter_without_calib/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/bf16_convert/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/dequantize_cast_optimizer/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_add_to_biasadd/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_layout/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_leakyrelu/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_nan_to_random/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_placeholder_to_const/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dilated_contraction/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dummy_biasadd/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/expanddims_optimizer/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fetch_weight_from_reshape/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_batch_norm/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_constant/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_biasadd_add/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_column_wise_mul/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_conv_with_math/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_bn/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_in/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_gelu/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_layer_norm/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_conv/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_reshape_transpose/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/graph_cse_optimizer/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/grappler_pass/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/insert_print_node/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/move_squeeze_after_relu/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/pre_optimize/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/remove_training_nodes/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/rename_batch_norm/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/split_shared_input/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_equivalent_nodes/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_unused_nodes/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/switch_optimizer/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/graph_base/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_fake_quant/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value_without_calib/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_requantize/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_requantize/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/meta_op_optimizer/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_hostconst_converter/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_quantized_op_cse/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/rnn_convert/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/scale_propagation/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_graph/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_node/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_schema/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/tf2onnx_utils/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/insert_qdq_pattern/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/merge_duplicated_qdq/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/share_qdq_y_pattern/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_util/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/fake_quantize/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_config/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_helper/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/optimize_layer/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_add/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_base/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_bn/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_wrapper/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_bn/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_concatv2/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_conv/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_deconv/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_in/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_matmul/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_pooling/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/optimize_qdq/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_base/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_bn/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_concatv2/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_conv/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_for_intel_cpu/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_matmul/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_pooling/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph_common/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_calibration/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_scaler/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/tf2onnx_converter/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/bias_correction/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/graph_transform_base/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/insert_logging/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/rerange_quantized_concat/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/util/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/bf16_convert/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/hawq_metric/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/modified_pickle/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/quantize/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/torch_load/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/utils/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/model_wrapper/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/pattern_detector/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/symbolic_trace/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/util/index.rst", "autoapi/neural_compressor/algorithm/algorithm/index.rst", "autoapi/neural_compressor/algorithm/fast_bias_correction/index.rst", "autoapi/neural_compressor/algorithm/index.rst", "autoapi/neural_compressor/algorithm/smooth_quant/index.rst", "autoapi/neural_compressor/algorithm/weight_correction/index.rst", "autoapi/neural_compressor/benchmark/index.rst", "autoapi/neural_compressor/common/base_config/index.rst", "autoapi/neural_compressor/common/base_tuning/index.rst", "autoapi/neural_compressor/common/benchmark/index.rst", "autoapi/neural_compressor/common/index.rst", "autoapi/neural_compressor/common/tuning_param/index.rst", "autoapi/neural_compressor/common/utils/constants/index.rst", "autoapi/neural_compressor/common/utils/index.rst", "autoapi/neural_compressor/common/utils/logger/index.rst", "autoapi/neural_compressor/common/utils/save_load/index.rst", "autoapi/neural_compressor/common/utils/utility/index.rst", "autoapi/neural_compressor/compression/callbacks/index.rst", "autoapi/neural_compressor/compression/distillation/criterions/index.rst", "autoapi/neural_compressor/compression/distillation/index.rst", "autoapi/neural_compressor/compression/distillation/optimizers/index.rst", "autoapi/neural_compressor/compression/distillation/utility/index.rst", "autoapi/neural_compressor/compression/hpo/index.rst", "autoapi/neural_compressor/compression/hpo/sa_optimizer/index.rst", "autoapi/neural_compressor/compression/pruner/criteria/index.rst", "autoapi/neural_compressor/compression/pruner/index.rst", "autoapi/neural_compressor/compression/pruner/model_slim/auto_slim/index.rst", "autoapi/neural_compressor/compression/pruner/model_slim/index.rst", "autoapi/neural_compressor/compression/pruner/model_slim/pattern_analyzer/index.rst", "autoapi/neural_compressor/compression/pruner/model_slim/weight_slim/index.rst", "autoapi/neural_compressor/compression/pruner/patterns/base/index.rst", "autoapi/neural_compressor/compression/pruner/patterns/index.rst", "autoapi/neural_compressor/compression/pruner/patterns/mha/index.rst", "autoapi/neural_compressor/compression/pruner/patterns/ninm/index.rst", "autoapi/neural_compressor/compression/pruner/patterns/nxm/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/base/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/basic/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/block_mask/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/mha/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/pattern_lock/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/progressive/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/retrain_free/index.rst", "autoapi/neural_compressor/compression/pruner/pruning/index.rst", "autoapi/neural_compressor/compression/pruner/regs/index.rst", "autoapi/neural_compressor/compression/pruner/schedulers/index.rst", "autoapi/neural_compressor/compression/pruner/tf_criteria/index.rst", "autoapi/neural_compressor/compression/pruner/utils/index.rst", "autoapi/neural_compressor/compression/pruner/wanda/index.rst", "autoapi/neural_compressor/compression/pruner/wanda/utils/index.rst", "autoapi/neural_compressor/config/index.rst", "autoapi/neural_compressor/contrib/index.rst", "autoapi/neural_compressor/contrib/strategy/index.rst", "autoapi/neural_compressor/contrib/strategy/sigopt/index.rst", "autoapi/neural_compressor/contrib/strategy/tpe/index.rst", "autoapi/neural_compressor/data/dataloaders/base_dataloader/index.rst", "autoapi/neural_compressor/data/dataloaders/dataloader/index.rst", "autoapi/neural_compressor/data/dataloaders/default_dataloader/index.rst", "autoapi/neural_compressor/data/dataloaders/fetcher/index.rst", "autoapi/neural_compressor/data/dataloaders/mxnet_dataloader/index.rst", "autoapi/neural_compressor/data/dataloaders/onnxrt_dataloader/index.rst", "autoapi/neural_compressor/data/dataloaders/pytorch_dataloader/index.rst", "autoapi/neural_compressor/data/dataloaders/sampler/index.rst", "autoapi/neural_compressor/data/dataloaders/tensorflow_dataloader/index.rst", "autoapi/neural_compressor/data/datasets/bert_dataset/index.rst", "autoapi/neural_compressor/data/datasets/coco_dataset/index.rst", "autoapi/neural_compressor/data/datasets/dataset/index.rst", "autoapi/neural_compressor/data/datasets/dummy_dataset/index.rst", "autoapi/neural_compressor/data/datasets/dummy_dataset_v2/index.rst", "autoapi/neural_compressor/data/datasets/imagenet_dataset/index.rst", "autoapi/neural_compressor/data/datasets/index.rst", "autoapi/neural_compressor/data/datasets/style_transfer_dataset/index.rst", "autoapi/neural_compressor/data/filters/coco_filter/index.rst", "autoapi/neural_compressor/data/filters/filter/index.rst", "autoapi/neural_compressor/data/filters/index.rst", "autoapi/neural_compressor/data/index.rst", "autoapi/neural_compressor/data/transforms/imagenet_transform/index.rst", "autoapi/neural_compressor/data/transforms/index.rst", "autoapi/neural_compressor/data/transforms/postprocess/index.rst", "autoapi/neural_compressor/data/transforms/tokenization/index.rst", "autoapi/neural_compressor/data/transforms/transform/index.rst", "autoapi/neural_compressor/index.rst", "autoapi/neural_compressor/metric/bleu/index.rst", "autoapi/neural_compressor/metric/bleu_util/index.rst", "autoapi/neural_compressor/metric/coco_label_map/index.rst", "autoapi/neural_compressor/metric/coco_tools/index.rst", "autoapi/neural_compressor/metric/evaluate_squad/index.rst", "autoapi/neural_compressor/metric/f1/index.rst", "autoapi/neural_compressor/metric/index.rst", "autoapi/neural_compressor/metric/metric/index.rst", "autoapi/neural_compressor/mix_precision/index.rst", "autoapi/neural_compressor/model/base_model/index.rst", "autoapi/neural_compressor/model/index.rst", "autoapi/neural_compressor/model/keras_model/index.rst", "autoapi/neural_compressor/model/model/index.rst", "autoapi/neural_compressor/model/mxnet_model/index.rst", "autoapi/neural_compressor/model/nets_factory/index.rst", "autoapi/neural_compressor/model/onnx_model/index.rst", "autoapi/neural_compressor/model/tensorflow_model/index.rst", "autoapi/neural_compressor/model/torch_model/index.rst", "autoapi/neural_compressor/objective/index.rst", "autoapi/neural_compressor/profiling/index.rst", "autoapi/neural_compressor/profiling/parser/factory/index.rst", "autoapi/neural_compressor/profiling/parser/onnx_parser/factory/index.rst", "autoapi/neural_compressor/profiling/parser/onnx_parser/parser/index.rst", "autoapi/neural_compressor/profiling/parser/parser/index.rst", "autoapi/neural_compressor/profiling/parser/result/index.rst", "autoapi/neural_compressor/profiling/parser/tensorflow_parser/factory/index.rst", "autoapi/neural_compressor/profiling/parser/tensorflow_parser/parser/index.rst", "autoapi/neural_compressor/profiling/profiler/factory/index.rst", "autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/factory/index.rst", "autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/profiler/index.rst", "autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/utils/index.rst", "autoapi/neural_compressor/profiling/profiler/profiler/index.rst", "autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/factory/index.rst", "autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/profiler/index.rst", "autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/utils/index.rst", "autoapi/neural_compressor/quantization/index.rst", "autoapi/neural_compressor/strategy/auto/index.rst", "autoapi/neural_compressor/strategy/auto_mixed_precision/index.rst", "autoapi/neural_compressor/strategy/basic/index.rst", "autoapi/neural_compressor/strategy/bayesian/index.rst", "autoapi/neural_compressor/strategy/conservative/index.rst", "autoapi/neural_compressor/strategy/exhaustive/index.rst", "autoapi/neural_compressor/strategy/hawq_v2/index.rst", "autoapi/neural_compressor/strategy/index.rst", "autoapi/neural_compressor/strategy/mse/index.rst", "autoapi/neural_compressor/strategy/mse_v2/index.rst", "autoapi/neural_compressor/strategy/random/index.rst", "autoapi/neural_compressor/strategy/strategy/index.rst", "autoapi/neural_compressor/strategy/utils/constant/index.rst", "autoapi/neural_compressor/strategy/utils/index.rst", "autoapi/neural_compressor/strategy/utils/tuning_sampler/index.rst", "autoapi/neural_compressor/strategy/utils/tuning_space/index.rst", "autoapi/neural_compressor/strategy/utils/tuning_structs/index.rst", "autoapi/neural_compressor/strategy/utils/utility/index.rst", "autoapi/neural_compressor/template/api_doc_example/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/smoother/calibration/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/smoother/core/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/smoother/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/smoother/scaler/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/static_quant/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/static_quant/keras/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/static_quant/tensorflow/index.rst", "autoapi/neural_compressor/tensorflow/index.rst", "autoapi/neural_compressor/tensorflow/keras/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/conv2d/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/dense/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/depthwise_conv2d/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/layer_initializer/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/pool2d/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/separable_conv2d/index.rst", "autoapi/neural_compressor/tensorflow/keras/quantization/config/index.rst", "autoapi/neural_compressor/tensorflow/keras/quantization/index.rst", "autoapi/neural_compressor/tensorflow/quantization/algorithm_entry/index.rst", "autoapi/neural_compressor/tensorflow/quantization/autotune/index.rst", "autoapi/neural_compressor/tensorflow/quantization/config/index.rst", "autoapi/neural_compressor/tensorflow/quantization/index.rst", "autoapi/neural_compressor/tensorflow/quantization/quantize/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_converter/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/bf16_convert/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/dequantize_cast_optimizer/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_add_to_biasadd/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_layout/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_leakyrelu/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_nan_to_random/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_placeholder_to_const/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dilated_contraction/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dummy_biasadd/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/expanddims_optimizer/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fetch_weight_from_reshape/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_batch_norm/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_constant/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_biasadd_add/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_column_wise_mul/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_conv_with_math/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_bn/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_in/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_gelu/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_layer_norm/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_conv/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_reshape_transpose/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/graph_cse_optimizer/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/grappler_pass/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/insert_print_node/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/move_squeeze_after_relu/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/pre_optimize/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/remove_training_nodes/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/rename_batch_norm/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/split_shared_input/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_equivalent_nodes/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_unused_nodes/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/switch_optimizer/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/graph_base/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_fake_quant/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_value/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_requantize/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_requantize/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/meta_op_optimizer/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_hostconst_converter/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_quantized_op_cse/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/scale_propagation/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/insert_qdq_pattern/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/merge_duplicated_qdq/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/share_qdq_y_pattern/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_util/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_bn/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_concatv2/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_conv/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_deconv/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_in/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_matmul/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_pooling/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/optimize_qdq/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_base/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_bn/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_concatv2/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_conv/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_for_intel_cpu/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_matmul/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_pooling/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph_common/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/bias_correction/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/graph_transform_base/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/insert_logging/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/rerange_quantized_concat/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/utility/index.rst", "autoapi/neural_compressor/tensorflow/utils/constants/index.rst", "autoapi/neural_compressor/tensorflow/utils/data/index.rst", "autoapi/neural_compressor/tensorflow/utils/index.rst", "autoapi/neural_compressor/tensorflow/utils/model/index.rst", "autoapi/neural_compressor/tensorflow/utils/model_wrappers/index.rst", "autoapi/neural_compressor/tensorflow/utils/utility/index.rst", "autoapi/neural_compressor/torch/algorithms/base_algorithm/index.rst", "autoapi/neural_compressor/torch/algorithms/fp8_quant/utils/logger/index.rst", "autoapi/neural_compressor/torch/algorithms/index.rst", "autoapi/neural_compressor/torch/algorithms/layer_wise/index.rst", "autoapi/neural_compressor/torch/algorithms/layer_wise/load/index.rst", "autoapi/neural_compressor/torch/algorithms/layer_wise/modified_pickle/index.rst", "autoapi/neural_compressor/torch/algorithms/layer_wise/utils/index.rst", "autoapi/neural_compressor/torch/algorithms/mixed_precision/half_precision_convert/index.rst", "autoapi/neural_compressor/torch/algorithms/mixed_precision/index.rst", "autoapi/neural_compressor/torch/algorithms/mixed_precision/module_wrappers/index.rst", "autoapi/neural_compressor/torch/algorithms/mx_quant/index.rst", "autoapi/neural_compressor/torch/algorithms/mx_quant/mx/index.rst", "autoapi/neural_compressor/torch/algorithms/mx_quant/utils/index.rst", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/core/index.rst", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/half_precision_rewriter/index.rst", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/index.rst", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/save_load/index.rst", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/utility/index.rst", "autoapi/neural_compressor/torch/algorithms/smooth_quant/index.rst", "autoapi/neural_compressor/torch/algorithms/smooth_quant/save_load/index.rst", "autoapi/neural_compressor/torch/algorithms/smooth_quant/smooth_quant/index.rst", "autoapi/neural_compressor/torch/algorithms/smooth_quant/utility/index.rst", "autoapi/neural_compressor/torch/algorithms/static_quant/index.rst", "autoapi/neural_compressor/torch/algorithms/static_quant/save_load/index.rst", "autoapi/neural_compressor/torch/algorithms/static_quant/static_quant/index.rst", "autoapi/neural_compressor/torch/algorithms/static_quant/utility/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/autoround/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/awq/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/gptq/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/bitpack/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/config/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/core/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/optimizer/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/qtensor/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/quantizer/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/modules/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/rtn/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/save_load/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/teq/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/utility/index.rst", "autoapi/neural_compressor/torch/export/index.rst", "autoapi/neural_compressor/torch/export/pt2e_export/index.rst", "autoapi/neural_compressor/torch/index.rst", "autoapi/neural_compressor/torch/quantization/algorithm_entry/index.rst", "autoapi/neural_compressor/torch/quantization/autotune/index.rst", "autoapi/neural_compressor/torch/quantization/config/index.rst", "autoapi/neural_compressor/torch/quantization/index.rst", "autoapi/neural_compressor/torch/quantization/load_entry/index.rst", "autoapi/neural_compressor/torch/quantization/quantize/index.rst", "autoapi/neural_compressor/torch/utils/auto_accelerator/index.rst", "autoapi/neural_compressor/torch/utils/constants/index.rst", "autoapi/neural_compressor/torch/utils/environ/index.rst", "autoapi/neural_compressor/torch/utils/index.rst", "autoapi/neural_compressor/torch/utils/utility/index.rst", "autoapi/neural_compressor/training/index.rst", "autoapi/neural_compressor/transformers/quantization/utils/index.rst", "autoapi/neural_compressor/transformers/utils/index.rst", "autoapi/neural_compressor/transformers/utils/quantization_config/index.rst", "autoapi/neural_compressor/utils/collect_layer_histogram/index.rst", "autoapi/neural_compressor/utils/constant/index.rst", "autoapi/neural_compressor/utils/create_obj_from_config/index.rst", "autoapi/neural_compressor/utils/export/index.rst", "autoapi/neural_compressor/utils/export/qlinear2qdq/index.rst", "autoapi/neural_compressor/utils/export/tf2onnx/index.rst", "autoapi/neural_compressor/utils/export/torch2onnx/index.rst", "autoapi/neural_compressor/utils/index.rst", "autoapi/neural_compressor/utils/kl_divergence/index.rst", "autoapi/neural_compressor/utils/load_huggingface/index.rst", "autoapi/neural_compressor/utils/logger/index.rst", "autoapi/neural_compressor/utils/options/index.rst", "autoapi/neural_compressor/utils/pytorch/index.rst", "autoapi/neural_compressor/utils/utility/index.rst", "autoapi/neural_compressor/utils/weights_details/index.rst", "autoapi/neural_compressor/version/index.rst", "docs/build_docs/source/index.rst", "docs/source/2x_user_guide.md", "docs/source/3x/PT_DynamicQuant.md", "docs/source/3x/PT_FP8Quant.md", "docs/source/3x/PT_MXQuant.md", "docs/source/3x/PT_MixedPrecision.md", "docs/source/3x/PT_SmoothQuant.md", "docs/source/3x/PT_StaticQuant.md", "docs/source/3x/PT_WeightOnlyQuant.md", "docs/source/3x/PyTorch.md", "docs/source/3x/TF_Quant.md", "docs/source/3x/TF_SQ.md", "docs/source/3x/TensorFlow.md", "docs/source/3x/autotune.md", "docs/source/3x/benchmark.md", "docs/source/3x/client_quant.md", "docs/source/3x/design.md", "docs/source/3x/gaudi_version_map.md", "docs/source/3x/llm_recipes.md", "docs/source/3x/quantization.md", "docs/source/CODE_OF_CONDUCT.md", "docs/source/CONTRIBUTING.md", "docs/source/FX.md", "docs/source/SECURITY.md", "docs/source/Welcome.md", "docs/source/adaptor.md", "docs/source/add_new_adaptor.md", "docs/source/add_new_data_type.md", "docs/source/api-doc/adaptor.rst", "docs/source/api-doc/adaptor/onnxrt.rst", "docs/source/api-doc/adaptor/torch_utils.rst", "docs/source/api-doc/api_2.rst", "docs/source/api-doc/api_3.rst", "docs/source/api-doc/api_doc_example.rst", "docs/source/api-doc/apis.rst", "docs/source/api-doc/benchmark.rst", "docs/source/api-doc/compression.rst", "docs/source/api-doc/config.rst", "docs/source/api-doc/mix_precision.rst", "docs/source/api-doc/model.rst", "docs/source/api-doc/objective.rst", "docs/source/api-doc/quantization.rst", "docs/source/api-doc/strategy.rst", "docs/source/api-doc/tf_quantization_autotune.rst", "docs/source/api-doc/tf_quantization_common.rst", "docs/source/api-doc/tf_quantization_config.rst", "docs/source/api-doc/torch_quantization_autotune.rst", "docs/source/api-doc/torch_quantization_common.rst", "docs/source/api-doc/torch_quantization_config.rst", "docs/source/api-doc/training.rst", "docs/source/benchmark.md", "docs/source/calibration.md", "docs/source/coding_style.md", "docs/source/dataloader.md", "docs/source/design.md", "docs/source/distillation_quantization.md", "docs/source/distributed.md", "docs/source/examples_readme.md", "docs/source/export.md", "docs/source/faq.md", "docs/source/framework_yaml.md", "docs/source/get_started.md", "docs/source/incompatible_changes.md", "docs/source/infrastructure.md", "docs/source/installation_guide.md", "docs/source/legal_information.md", "docs/source/llm_recipes.md", "docs/source/metric.md", "docs/source/migration.md", "docs/source/mixed_precision.md", "docs/source/model.md", "docs/source/mx_quantization.md", "docs/source/objective.md", "docs/source/orchestration.md", "docs/source/pruning.md", "docs/source/publication_list.md", "docs/source/quantization.md", "docs/source/quantization_layer_wise.md", "docs/source/quantization_mixed_precision.md", "docs/source/quantization_weight_only.md", "docs/source/releases_info.md", "docs/source/sigopt_strategy.md", "docs/source/smooth_quant.md", "docs/source/transform.md", "docs/source/tuning_strategies.md", "docs/source/validated_model_list.md", "index.rst"], "indexentries": {"_epoch_ran (neural_compressor.compression.callbacks.distillationcallbacks attribute)": [[162, "neural_compressor.compression.callbacks.DistillationCallbacks._epoch_ran", false]], "acceleratorregistry (class in neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.AcceleratorRegistry", false]], "accuracy (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.Accuracy", false]], "accuracy (class in neural_compressor.objective)": [[245, "neural_compressor.objective.Accuracy", false]], "accuracycriterion (class in neural_compressor.config)": [[195, "neural_compressor.config.AccuracyCriterion", false]], "acq_max() (in module neural_compressor.strategy.bayesian)": [[266, "neural_compressor.strategy.bayesian.acq_max", false]], "activationoperator (class in neural_compressor.adaptor.ox_utils.operators.activation)": [[5, "neural_compressor.adaptor.ox_utils.operators.activation.ActivationOperator", false]], "add_port_to_name() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.add_port_to_name", false]], "algorithm (class in neural_compressor.algorithm.algorithm)": [[146, "neural_compressor.algorithm.algorithm.Algorithm", false]], "algorithm_registry() (in module neural_compressor.algorithm.algorithm)": [[146, "neural_compressor.algorithm.algorithm.algorithm_registry", false]], "algorithms (class in neural_compressor.algorithm.algorithm)": [[146, "neural_compressor.algorithm.algorithm.ALGORITHMS", false]], "algorithmscheduler (class in neural_compressor.algorithm.algorithm)": [[146, "neural_compressor.algorithm.algorithm.AlgorithmScheduler", false]], "alias_param() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.alias_param", false]], "alignimagechanneltransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.AlignImageChannelTransform", false]], "alpha (neural_compressor.compression.pruner.regs.grouplasso attribute)": [[189, "neural_compressor.compression.pruner.regs.GroupLasso.alpha", false]], "amp_convert() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.amp_convert", false]], "append_attr() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.append_attr", false]], "apply_awq_clip() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.apply_awq_clip", false]], "apply_awq_scale() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.apply_awq_scale", false]], "apply_inlining() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.apply_inlining", false]], "apply_inlining() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.apply_inlining", false]], "apply_single_pattern_pair() (in module neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.apply_single_pattern_pair", false]], "are_shapes_equal() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.are_shapes_equal", false]], "argmaxoperator (class in neural_compressor.adaptor.ox_utils.operators.argmax)": [[6, "neural_compressor.adaptor.ox_utils.operators.argmax.ArgMaxOperator", false]], "assert_error() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.assert_error", false]], "attentionoperator (class in neural_compressor.adaptor.ox_utils.operators.attention)": [[7, "neural_compressor.adaptor.ox_utils.operators.attention.AttentionOperator", false]], "attr1 (neural_compressor.template.api_doc_example.exampleclass attribute)": [[281, "neural_compressor.template.api_doc_example.ExampleClass.attr1", false]], "attr2 (neural_compressor.template.api_doc_example.exampleclass attribute)": [[281, "neural_compressor.template.api_doc_example.ExampleClass.attr2", false]], "attr5 (neural_compressor.template.api_doc_example.exampleclass attribute)": [[281, "neural_compressor.template.api_doc_example.ExampleClass.attr5", false]], "attribute1 (in module neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.attribute1", false]], "attribute_to_kwarg() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.attribute_to_kwarg", false]], "auto_accelerator (class in neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.Auto_Accelerator", false]], "auto_copy() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.auto_copy", false]], "auto_detect_accelerator() (in module neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.auto_detect_accelerator", false]], "autoalpha (class in neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.AutoAlpha", false]], "automixedprecisiontunestrategy (class in neural_compressor.strategy.auto_mixed_precision)": [[264, "neural_compressor.strategy.auto_mixed_precision.AutoMixedPrecisionTuneStrategy", false]], "autoround_quantize_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.autoround_quantize_entry", false]], "autoroundconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.AutoRoundConfig", false]], "autoroundconfig (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.AutoRoundConfig", false]], "autoroundquantizer (class in neural_compressor.torch.algorithms.weight_only.autoround)": [[418, "neural_compressor.torch.algorithms.weight_only.autoround.AutoRoundQuantizer", false]], "autotune() (in module neural_compressor.tensorflow.quantization.autotune)": [[302, "neural_compressor.tensorflow.quantization.autotune.autotune", false]], "autotune() (in module neural_compressor.torch.quantization.autotune)": [[438, "neural_compressor.torch.quantization.autotune.autotune", false]], "autotunestrategy (class in neural_compressor.strategy.auto)": [[263, "neural_compressor.strategy.auto.AutoTuneStrategy", false]], "awq_quantize() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.awq_quantize", false]], "awq_quantize_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.awq_quantize_entry", false]], "awqconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.AWQConfig", false]], "awqconfig (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.AwqConfig", false]], "awqquantizer (class in neural_compressor.torch.algorithms.weight_only.awq)": [[419, "neural_compressor.torch.algorithms.weight_only.awq.AWQQuantizer", false]], "axis (neural_compressor.torch.algorithms.weight_only.hqq.qtensor.qtensormetainfo attribute)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo.axis", false]], "basecallbacks (class in neural_compressor.compression.callbacks)": [[162, "neural_compressor.compression.callbacks.BaseCallbacks", false]], "baseconfig (class in neural_compressor.common.base_config)": [[152, "neural_compressor.common.base_config.BaseConfig", false]], "basedataloader (class in neural_compressor.data.dataloaders.base_dataloader)": [[200, "neural_compressor.data.dataloaders.base_dataloader.BaseDataLoader", false]], "basedataloader (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.BaseDataLoader", false]], "basemetric (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.BaseMetric", false]], "basemodel (class in neural_compressor.model.base_model)": [[236, "neural_compressor.model.base_model.BaseModel", false]], "basemodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.BaseModel", false]], "basepattern (class in neural_compressor.compression.pruner.patterns.base)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern", false]], "basepruner (class in neural_compressor.compression.pruner.pruners.base)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner", false]], "basepruning (class in neural_compressor.compression.pruner.pruning)": [[188, "neural_compressor.compression.pruner.pruning.BasePruning", false]], "basereg (class in neural_compressor.compression.pruner.regs)": [[189, "neural_compressor.compression.pruner.regs.BaseReg", false]], "basetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.BaseTransform", false]], "basicpruning (class in neural_compressor.compression.pruner.pruning)": [[188, "neural_compressor.compression.pruner.pruning.BasicPruning", false]], "basictokenizer (class in neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.BasicTokenizer", false]], "basictunestrategy (class in neural_compressor.strategy.basic)": [[265, "neural_compressor.strategy.basic.BasicTuneStrategy", false]], "batchnormalizationoperator (class in neural_compressor.adaptor.ox_utils.operators.norm)": [[20, "neural_compressor.adaptor.ox_utils.operators.norm.BatchNormalizationOperator", false]], "batchsampler (class in neural_compressor.data.dataloaders.sampler)": [[207, "neural_compressor.data.dataloaders.sampler.BatchSampler", false]], "batchsampler (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.BatchSampler", false]], "bayesianoptimization (class in neural_compressor.strategy.bayesian)": [[266, "neural_compressor.strategy.bayesian.BayesianOptimization", false]], "bayesiantunestrategy (class in neural_compressor.strategy.bayesian)": [[266, "neural_compressor.strategy.bayesian.BayesianTuneStrategy", false]], "benchmark() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.benchmark", false]], "benchmark_with_raw_cmd() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.benchmark_with_raw_cmd", false]], "benchmarkconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.BenchmarkConfig", false]], "best_model (neural_compressor.compression.callbacks.distillationcallbacks attribute)": [[162, "neural_compressor.compression.callbacks.DistillationCallbacks.best_model", false]], "best_score (neural_compressor.compression.callbacks.distillationcallbacks attribute)": [[162, "neural_compressor.compression.callbacks.DistillationCallbacks.best_score", false]], "bf16convert (class in neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert)": [[35, "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert.BF16Convert", false]], "bf16convert (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert)": [[307, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert.BF16Convert", false]], "bf16modulewrapper (class in neural_compressor.adaptor.torch_utils.bf16_convert)": [[134, "neural_compressor.adaptor.torch_utils.bf16_convert.BF16ModuleWrapper", false]], "biascorrection (class in neural_compressor.adaptor.tf_utils.transform_graph.bias_correction)": [[128, "neural_compressor.adaptor.tf_utils.transform_graph.bias_correction.BiasCorrection", false]], "biascorrection (class in neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction)": [[380, "neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction.BiasCorrection", false]], "bilinearimagenettransform (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.BilinearImagenetTransform", false]], "binarydirect8bitoperator (class in neural_compressor.adaptor.ox_utils.operators.binary_op)": [[8, "neural_compressor.adaptor.ox_utils.operators.binary_op.BinaryDirect8BitOperator", false]], "binaryoperator (class in neural_compressor.adaptor.ox_utils.operators.binary_op)": [[8, "neural_compressor.adaptor.ox_utils.operators.binary_op.BinaryOperator", false]], "bleu (class in neural_compressor.metric.bleu)": [[227, "neural_compressor.metric.bleu.BLEU", false]], "bleu_tokenize() (in module neural_compressor.metric.bleu)": [[227, "neural_compressor.metric.bleu.bleu_tokenize", false]], "block_size (neural_compressor.compression.pruner.patterns.nxm.keraspatternnxm attribute)": [[179, "neural_compressor.compression.pruner.patterns.nxm.KerasPatternNxM.block_size", false]], "block_size (neural_compressor.compression.pruner.patterns.nxm.pytorchpatternnxm attribute)": [[179, "neural_compressor.compression.pruner.patterns.nxm.PytorchPatternNxM.block_size", false]], "blockfallbacktuningsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.BlockFallbackTuningSampler", false]], "blockmaskcriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.BlockMaskCriterion", false]], "build_captured_dataloader() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.build_captured_dataloader", false]], "build_slave_faker_model() (in module neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.build_slave_faker_model", false]], "bypass_reshape() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.bypass_reshape", false]], "bypass_reshape() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.bypass_reshape", false]], "bypass_reshape() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.bypass_reshape", false]], "bypass_reshape() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.bypass_reshape", false]], "cal_scale() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.cal_scale", false]], "calculate_md5() (in module neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.calculate_md5", false]], "calculate_mse() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.calculate_mse", false]], "calculate_quant_min_max() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.calculate_quant_min_max", false]], "calculate_scale_zp() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.calculate_scale_zp", false]], "calib_model() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.calib_model", false]], "calib_registry() (in module neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.calib_registry", false]], "calibcollector (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.CalibCollector", false]], "calibdata (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.CalibData", false]], "calibration (class in neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.Calibration", false]], "calibration() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.calibration", false]], "calibratorbase (class in neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.CalibratorBase", false]], "call_counter() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.call_counter", false]], "call_one() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.call_one", false]], "callbacks (class in neural_compressor.training)": [[448, "neural_compressor.training.CallBacks", false]], "captureoutputtofile (class in neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.CaptureOutputToFile", false]], "captureoutputtofile (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.CaptureOutputToFile", false]], "cast_tensor() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.cast_tensor", false]], "castonnxtransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CastONNXTransform", false]], "castpytorchtransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CastPyTorchTransform", false]], "casttftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CastTFTransform", false]], "centercroptftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CenterCropTFTransform", false]], "centercroptransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CenterCropTransform", false]], "cfg_to_qconfig() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.cfg_to_qconfig", false]], "cfg_to_qconfig() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.cfg_to_qconfig", false]], "check_cfg_and_qconfig() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.check_cfg_and_qconfig", false]], "check_cfg_and_qconfig() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.check_cfg_and_qconfig", false]], "check_cfg_and_qconfig() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.check_cfg_and_qconfig", false]], "check_config() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.check_config", false]], "check_dataloader() (in module neural_compressor.data.dataloaders.dataloader)": [[201, "neural_compressor.data.dataloaders.dataloader.check_dataloader", false]], "check_integrity() (in module neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.check_integrity", false]], "check_key_exist() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.check_key_exist", false]], "check_key_validity() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.check_key_validity", false]], "check_model() (in module neural_compressor.utils.export.qlinear2qdq)": [[456, "neural_compressor.utils.export.qlinear2qdq.check_model", false]], "check_mx_version() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.check_mx_version", false]], "checkpoint_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.checkpoint_session", false]], "checkpoint_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.checkpoint_session", false]], "cifar10 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.CIFAR10", false]], "cifar100 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.CIFAR100", false]], "classifierheadsearcher (class in neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcher", false]], "classifierheadsearchertf (class in neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcherTF", false]], "classregister (class in neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.ClassRegister", false]], "clean_module_weight() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.clean_module_weight", false]], "cocoevalwrapper (class in neural_compressor.metric.coco_tools)": [[230, "neural_compressor.metric.coco_tools.COCOEvalWrapper", false]], "cocomapv2 (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.COCOmAPv2", false]], "coconpy (class in neural_compressor.data.datasets.coco_dataset)": [[210, "neural_compressor.data.datasets.coco_dataset.COCONpy", false]], "cocoraw (class in neural_compressor.data.datasets.coco_dataset)": [[210, "neural_compressor.data.datasets.coco_dataset.COCORaw", false]], "cocorecorddataset (class in neural_compressor.data.datasets.coco_dataset)": [[210, "neural_compressor.data.datasets.coco_dataset.COCORecordDataset", false]], "cocowrapper (class in neural_compressor.metric.coco_tools)": [[230, "neural_compressor.metric.coco_tools.COCOWrapper", false]], "collate_preds() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.collate_preds", false]], "collate_tf_preds() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.collate_tf_preds", false]], "collate_tf_preds() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.collate_tf_preds", false]], "collate_torch_preds() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.collate_torch_preds", false]], "collect_layer_inputs() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.collect_layer_inputs", false]], "collect_weight_info() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.collect_weight_info", false]], "collectorbase (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.CollectorBase", false]], "collecttransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CollectTransform", false]], "combine_capabilities() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.combine_capabilities", false]], "combine_histogram() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.combine_histogram", false]], "combine_histogram() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.combine_histogram", false]], "compare_label (neural_compressor.metric.metric.mae attribute)": [[234, "neural_compressor.metric.metric.MAE.compare_label", false]], "compare_label (neural_compressor.metric.metric.mse attribute)": [[234, "neural_compressor.metric.metric.MSE.compare_label", false]], "compare_objects() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.compare_objects", false]], "compare_weights() (in module neural_compressor.adaptor.torch_utils.hawq_metric)": [[135, "neural_compressor.adaptor.torch_utils.hawq_metric.compare_weights", false]], "composableconfig (class in neural_compressor.common.base_config)": [[152, "neural_compressor.common.base_config.ComposableConfig", false]], "composetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ComposeTransform", false]], "compressionmanager (class in neural_compressor.training)": [[448, "neural_compressor.training.CompressionManager", false]], "compute_bleu() (in module neural_compressor.metric.bleu_util)": [[228, "neural_compressor.metric.bleu_util.compute_bleu", false]], "compute_const_folding_using_tf() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.compute_const_folding_using_tf", false]], "compute_sparsity() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.compute_sparsity", false]], "concatoperator (class in neural_compressor.adaptor.ox_utils.operators.concat)": [[9, "neural_compressor.adaptor.ox_utils.operators.concat.ConcatOperator", false]], "config (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.config", false]], "config (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.config", false]], "config (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.config", false]], "config (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.config", false]], "config (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.config", false]], "config (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.config", false]], "config (neural_compressor.compression.pruner.schedulers.pruningscheduler attribute)": [[190, "neural_compressor.compression.pruner.schedulers.PruningScheduler.config", false]], "config_file_path (neural_compressor.compression.pruner.pruning.basepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasePruning.config_file_path", false]], "config_file_path (neural_compressor.compression.pruner.pruning.basicpruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasicPruning.config_file_path", false]], "config_file_path (neural_compressor.compression.pruner.pruning.retrainfreepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.RetrainFreePruning.config_file_path", false]], "config_instance() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.config_instance", false]], "config_list (neural_compressor.common.base_config.composableconfig attribute)": [[152, "neural_compressor.common.base_config.ComposableConfig.config_list", false]], "config_list (neural_compressor.common.base_tuning.configset attribute)": [[153, "neural_compressor.common.base_tuning.ConfigSet.config_list", false]], "config_quantizable_layers() (in module neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer)": [[103, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer.config_quantizable_layers", false]], "configloader (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.ConfigLoader", false]], "configregistry (class in neural_compressor.common.base_config)": [[152, "neural_compressor.common.base_config.ConfigRegistry", false]], "configset (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.ConfigSet", false]], "conservativetunestrategy (class in neural_compressor.strategy.conservative)": [[267, "neural_compressor.strategy.conservative.ConservativeTuneStrategy", false]], "construct_function_from_graph_def() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.construct_function_from_graph_def", false]], "construct_function_from_graph_def() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.construct_function_from_graph_def", false]], "convert() (in module neural_compressor.adaptor.torch_utils.bf16_convert)": [[134, "neural_compressor.adaptor.torch_utils.bf16_convert.Convert", false]], "convert() (in module neural_compressor.torch.quantization.quantize)": [[442, "neural_compressor.torch.quantization.quantize.convert", false]], "convert_by_vocab() (in module neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.convert_by_vocab", false]], "convert_examples_to_features() (in module neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.convert_examples_to_features", false]], "convert_examples_to_features() (in module neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.convert_examples_to_features", false]], "convert_tensorflow_tensor_to_onnx() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.convert_tensorflow_tensor_to_onnx", false]], "convert_to_unicode() (in module neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.convert_to_unicode", false]], "convertaddtobiasaddoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd)": [[38, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd.ConvertAddToBiasAddOptimizer", false]], "convertaddtobiasaddoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd)": [[310, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd.ConvertAddToBiasAddOptimizer", false]], "convertlayoutoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout)": [[39, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout.ConvertLayoutOptimizer", false]], "convertlayoutoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout)": [[311, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout.ConvertLayoutOptimizer", false]], "convertleakyreluoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu)": [[40, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu.ConvertLeakyReluOptimizer", false]], "convertleakyreluoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu)": [[312, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu.ConvertLeakyReluOptimizer", false]], "convertnantorandom (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random)": [[41, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random.ConvertNanToRandom", false]], "convertnantorandom (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random)": [[313, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random.ConvertNanToRandom", false]], "convertplaceholdertoconst (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const)": [[42, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const.ConvertPlaceholderToConst", false]], "convertplaceholdertoconst (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const)": [[314, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const.ConvertPlaceholderToConst", false]], "convoperator (class in neural_compressor.adaptor.ox_utils.operators.conv)": [[10, "neural_compressor.adaptor.ox_utils.operators.conv.ConvOperator", false]], "cpu_accelerator (class in neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.CPU_Accelerator", false]], "cpuinfo (class in neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.CpuInfo", false]], "cpuinfo (class in neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.CpuInfo", false]], "cpuinfo (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.CpuInfo", false]], "create_data_example() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.create_data_example", false]], "create_dataloader() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.create_dataloader", false]], "create_dataset() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.create_dataset", false]], "create_eval_func() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.create_eval_func", false]], "create_onnx_config() (in module neural_compressor.profiling.profiler.onnxrt_profiler.utils)": [[257, "neural_compressor.profiling.profiler.onnxrt_profiler.utils.create_onnx_config", false]], "create_quant_spec_from_config() (in module neural_compressor.torch.algorithms.pt2e_quant.utility)": [[409, "neural_compressor.torch.algorithms.pt2e_quant.utility.create_quant_spec_from_config", false]], "create_tf_config() (in module neural_compressor.profiling.profiler.tensorflow_profiler.utils)": [[261, "neural_compressor.profiling.profiler.tensorflow_profiler.utils.create_tf_config", false]], "create_train_func() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.create_train_func", false]], "create_xiq_quantizer_from_pt2e_config() (in module neural_compressor.torch.algorithms.pt2e_quant.utility)": [[409, "neural_compressor.torch.algorithms.pt2e_quant.utility.create_xiq_quantizer_from_pt2e_config", false]], "criterion (neural_compressor.compression.pruner.pruners.basic.kerasbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.KerasBasicPruner.criterion", false]], "criterion (neural_compressor.compression.pruner.pruners.basic.pytorchbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.PytorchBasicPruner.criterion", false]], "criterion (neural_compressor.compression.pruner.pruners.block_mask.pytorchblockmaskpruner attribute)": [[182, "neural_compressor.compression.pruner.pruners.block_mask.PytorchBlockMaskPruner.criterion", false]], "criterion (neural_compressor.compression.pruner.pruners.retrain_free.pytorchretrainfreepruner attribute)": [[187, "neural_compressor.compression.pruner.pruners.retrain_free.PytorchRetrainFreePruner.criterion", false]], "criterion_registry() (in module neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.criterion_registry", false]], "criterions (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.Criterions", false]], "cropresizetftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CropResizeTFTransform", false]], "cropresizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CropResizeTransform", false]], "croptoboundingbox (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CropToBoundingBox", false]], "cuda_accelerator (class in neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.CUDA_Accelerator", false]], "current_pattern (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.current_pattern", false]], "current_sparsity_ratio (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.current_sparsity_ratio", false]], "current_sparsity_ratio (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.current_sparsity_ratio", false]], "current_sparsity_ratio (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.current_sparsity_ratio", false]], "dataiterloader (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.DataIterLoader", false]], "dataloader (class in neural_compressor.data.dataloaders.dataloader)": [[201, "neural_compressor.data.dataloaders.dataloader.DataLoader", false]], "dataloaderwrap (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.DataLoaderWrap", false]], "dataset (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.Dataset", false]], "dataset (neural_compressor.metric.coco_tools.cocowrapper attribute)": [[230, "neural_compressor.metric.coco_tools.COCOWrapper.dataset", false]], "dataset_registry() (in module neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.dataset_registry", false]], "datasets (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.Datasets", false]], "debug() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.debug", false]], "deep_get() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.deep_get", false]], "deep_get() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.deep_get", false]], "deep_set() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.deep_set", false]], "default_collate() (in module neural_compressor.data.dataloaders.default_dataloader)": [[202, "neural_compressor.data.dataloaders.default_dataloader.default_collate", false]], "default_collate() (in module neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.default_collate", false]], "defaultdataloader (class in neural_compressor.data.dataloaders.default_dataloader)": [[202, "neural_compressor.data.dataloaders.default_dataloader.DefaultDataLoader", false]], "delete_assign() (in module neural_compressor.profiling.profiler.tensorflow_profiler.utils)": [[261, "neural_compressor.profiling.profiler.tensorflow_profiler.utils.delete_assign", false]], "dequantize() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.Dequantize", false]], "dequantize_data() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.dequantize_data", false]], "dequantize_data_with_scale_zero() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.dequantize_data_with_scale_zero", false]], "dequantize_weight() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.dequantize_weight", false]], "dequantizecastoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer)": [[36, "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer.DequantizeCastOptimizer", false]], "dequantizecastoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer)": [[308, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer.DequantizeCastOptimizer", false]], "detect_processor_type_based_on_hw() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.detect_processor_type_based_on_hw", false]], "detection_type (neural_compressor.metric.coco_tools.cocowrapper attribute)": [[230, "neural_compressor.metric.coco_tools.COCOWrapper.detection_type", false]], "device (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcher.device", false]], "device (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearchertf attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcherTF.device", false]], "device (neural_compressor.compression.pruner.model_slim.pattern_analyzer.jitbasicsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher.device", false]], "device (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.device", false]], "device (neural_compressor.compression.pruner.model_slim.pattern_analyzer.selfmhasearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.SelfMHASearcher.device", false]], "device (neural_compressor.compression.pruner.model_slim.weight_slim.linearcompression attribute)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompression.device", false]], "device_synchronize() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.device_synchronize", false]], "dilatedcontraction (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction)": [[43, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction.DilatedContraction", false]], "dilatedcontraction (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction)": [[315, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction.DilatedContraction", false]], "direct8bitoperator (class in neural_compressor.adaptor.ox_utils.operators.direct_q8)": [[11, "neural_compressor.adaptor.ox_utils.operators.direct_q8.Direct8BitOperator", false]], "disable_random() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.disable_random", false]], "disable_random() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.disable_random", false]], "distillationcallbacks (class in neural_compressor.compression.callbacks)": [[162, "neural_compressor.compression.callbacks.DistillationCallbacks", false]], "distillationconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.DistillationConfig", false]], "distribute_calib_tensors() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.distribute_calib_tensors", false]], "dotdict (class in neural_compressor.config)": [[195, "neural_compressor.config.DotDict", false]], "dotdict (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.DotDict", false]], "dowload_hf_model() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.dowload_hf_model", false]], "dowload_hf_model() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.dowload_hf_model", false]], "dowload_hf_model() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.dowload_hf_model", false]], "download_url() (in module neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.download_url", false]], "dtype_to_name() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.dtype_to_name", false]], "dummydataset (class in neural_compressor.data.datasets.dummy_dataset)": [[212, "neural_compressor.data.datasets.dummy_dataset.DummyDataset", false]], "dummydataset (class in neural_compressor.data.datasets.dummy_dataset_v2)": [[213, "neural_compressor.data.datasets.dummy_dataset_v2.DummyDataset", false]], "dummydataset (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.DummyDataset", false]], "dummydatasetv2 (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.DummyDatasetV2", false]], "dump_class_attrs() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.dump_class_attrs", false]], "dump_data_to_local() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.dump_data_to_local", false]], "dump_elapsed_time() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.dump_elapsed_time", false]], "dump_elapsed_time() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.dump_elapsed_time", false]], "dump_elapsed_time() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.dump_elapsed_time", false]], "dump_model_op_stats() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.dump_model_op_stats", false]], "dump_model_op_stats() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.dump_model_op_stats", false]], "dump_model_op_stats() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.dump_model_op_stats", false]], "dump_numa_info() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.dump_numa_info", false]], "dump_table() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.dump_table", false]], "dump_table_to_csv() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.dump_table_to_csv", false]], "dynamic_quant_export() (in module neural_compressor.utils.export.torch2onnx)": [[458, "neural_compressor.utils.export.torch2onnx.dynamic_quant_export", false]], "dynamicquantconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.DynamicQuantConfig", false]], "elemformat (class in neural_compressor.torch.algorithms.mx_quant.utils)": [[404, "neural_compressor.torch.algorithms.mx_quant.utils.ElemFormat", false]], "embedlayernormalizationoperator (class in neural_compressor.adaptor.ox_utils.operators.embed_layernorm)": [[12, "neural_compressor.adaptor.ox_utils.operators.embed_layernorm.EmbedLayerNormalizationOperator", false]], "end_step (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.end_step", false]], "end_step (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.end_step", false]], "end_step (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.end_step", false]], "enough_memo_store_scale() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.enough_memo_store_scale", false]], "ensure_list() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.ensure_list", false]], "equal_dicts() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.equal_dicts", false]], "error() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.error", false]], "estimator_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.estimator_session", false]], "estimator_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.estimator_session", false]], "eval_frequency (neural_compressor.compression.callbacks.distillationcallbacks attribute)": [[162, "neural_compressor.compression.callbacks.DistillationCallbacks.eval_frequency", false]], "evaluate() (in module neural_compressor.metric.evaluate_squad)": [[231, "neural_compressor.metric.evaluate_squad.evaluate", false]], "evaluate() (in module neural_compressor.metric.f1)": [[232, "neural_compressor.metric.f1.evaluate", false]], "evaluationfuncwrapper (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.EvaluationFuncWrapper", false]], "evaluator (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.Evaluator", false]], "exact_match_score() (in module neural_compressor.metric.evaluate_squad)": [[231, "neural_compressor.metric.evaluate_squad.exact_match_score", false]], "exampleclass (class in neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.ExampleClass", false]], "exhaustivetunestrategy (class in neural_compressor.strategy.exhaustive)": [[268, "neural_compressor.strategy.exhaustive.ExhaustiveTuneStrategy", false]], "expanddimsoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer)": [[45, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer.ExpandDimsOptimizer", false]], "expanddimsoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer)": [[317, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer.ExpandDimsOptimizer", false]], "export() (in module neural_compressor.torch.export.pt2e_export)": [[435, "neural_compressor.torch.export.pt2e_export.export", false]], "export_compressed_model() (in module neural_compressor.utils.load_huggingface)": [[461, "neural_compressor.utils.load_huggingface.export_compressed_model", false]], "export_model_for_pt2e_quant() (in module neural_compressor.torch.export.pt2e_export)": [[435, "neural_compressor.torch.export.pt2e_export.export_model_for_pt2e_quant", false]], "exportconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.ExportConfig", false]], "exportsingleimagedetectionboxestococo() (in module neural_compressor.metric.coco_tools)": [[230, "neural_compressor.metric.coco_tools.ExportSingleImageDetectionBoxesToCoco", false]], "exportsingleimagedetectionmaskstococo() (in module neural_compressor.metric.coco_tools)": [[230, "neural_compressor.metric.coco_tools.ExportSingleImageDetectionMasksToCoco", false]], "exportsingleimagegroundtruthtococo() (in module neural_compressor.metric.coco_tools)": [[230, "neural_compressor.metric.coco_tools.ExportSingleImageGroundtruthToCoco", false]], "extract_data_type() (in module neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.extract_data_type", false]], "f1 (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.F1", false]], "f1_score() (in module neural_compressor.metric.evaluate_squad)": [[231, "neural_compressor.metric.evaluate_squad.f1_score", false]], "f1_score() (in module neural_compressor.metric.f1)": [[232, "neural_compressor.metric.f1.f1_score", false]], "fakeaffinetensorquantfunction (class in neural_compressor.adaptor.torch_utils.model_wrapper)": [[142, "neural_compressor.adaptor.torch_utils.model_wrapper.FakeAffineTensorQuantFunction", false]], "fakeaffinetensorquantfunction (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.FakeAffineTensorQuantFunction", false]], "fakequantize (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize)": [[98, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize.FakeQuantize", false]], "fakequantizebase (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize)": [[98, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize.FakeQuantizeBase", false]], "fallbacktuningsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.FallbackTuningSampler", false]], "fashionmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.FashionMNIST", false]], "fastbiascorrection (class in neural_compressor.algorithm.fast_bias_correction)": [[147, "neural_compressor.algorithm.fast_bias_correction.FastBiasCorrection", false]], "fatal() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.fatal", false]], "fault_tolerant_file() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.fault_tolerant_file", false]], "fetch_module() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.fetch_module", false]], "fetch_module() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.fetch_module", false]], "fetch_module() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.fetch_module", false]], "fetcher (class in neural_compressor.data.dataloaders.fetcher)": [[203, "neural_compressor.data.dataloaders.fetcher.Fetcher", false]], "fetchweightfromreshapeoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape)": [[46, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape.FetchWeightFromReshapeOptimizer", false]], "fetchweightfromreshapeoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape)": [[318, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape.FetchWeightFromReshapeOptimizer", false]], "filter (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.Filter", false]], "filter_fn() (in module neural_compressor.torch.algorithms.weight_only.hqq.quantizer)": [[427, "neural_compressor.torch.algorithms.weight_only.hqq.quantizer.filter_fn", false]], "filter_registry() (in module neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.filter_registry", false]], "filters (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.FILTERS", false]], "finalize_calibration() (in module neural_compressor.torch.quantization.quantize)": [[442, "neural_compressor.torch.quantization.quantize.finalize_calibration", false]], "find_by_name() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.find_by_name", false]], "find_layers() (in module neural_compressor.compression.pruner.wanda.utils)": [[194, "neural_compressor.compression.pruner.wanda.utils.find_layers", false]], "find_layers() (in module neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.find_layers", false]], "find_layers_name() (in module neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.find_layers_name", false]], "find_opset() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.find_opset", false]], "fit() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.fit", false]], "fit() (in module neural_compressor.mix_precision)": [[235, "neural_compressor.mix_precision.fit", false]], "fit() (in module neural_compressor.quantization)": [[262, "neural_compressor.quantization.fit", false]], "fit() (in module neural_compressor.training)": [[448, "neural_compressor.training.fit", false]], "fix_ref_type_of_graph_def() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.fix_ref_type_of_graph_def", false]], "fix_ref_type_of_graph_def() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.fix_ref_type_of_graph_def", false]], "flatten_static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcher.flatten_static_graph", false]], "flatten_static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearchertf attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcherTF.flatten_static_graph", false]], "flatten_static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.jitbasicsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher.flatten_static_graph", false]], "flatten_static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.flatten_static_graph", false]], "flatten_static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.selfmhasearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.SelfMHASearcher.flatten_static_graph", false]], "float16activationoperator (class in neural_compressor.adaptor.ox_utils.operators.activation)": [[5, "neural_compressor.adaptor.ox_utils.operators.activation.Float16ActivationOperator", false]], "float16binaryoperator (class in neural_compressor.adaptor.ox_utils.operators.binary_op)": [[8, "neural_compressor.adaptor.ox_utils.operators.binary_op.Float16BinaryOperator", false]], "float_to_bfloat16() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.float_to_bfloat16", false]], "float_to_float16() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.float_to_float16", false]], "fn (neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.patternpair attribute)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.PatternPair.fn", false]], "foldbatchnormnodesoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm)": [[47, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm.FoldBatchNormNodesOptimizer", false]], "foldbatchnormnodesoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm)": [[319, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm.FoldBatchNormNodesOptimizer", false]], "footprint (class in neural_compressor.objective)": [[245, "neural_compressor.objective.Footprint", false]], "format_list2str() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.format_list2str", false]], "forward_wrapper() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.forward_wrapper", false]], "forward_wrapper() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.forward_wrapper", false]], "forward_wrapper() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.forward_wrapper", false]], "fp8_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.fp8_entry", false]], "fp8config (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.FP8Config", false]], "framework_datasets (in module neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.framework_datasets", false]], "freezefakequantopoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant)": [[73, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant.FreezeFakeQuantOpOptimizer", false]], "freezefakequantopoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant)": [[345, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant.FreezeFakeQuantOpOptimizer", false]], "freezevaluetransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value)": [[74, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value.FreezeValueTransformer", false]], "freezevaluetransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value)": [[346, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value.FreezeValueTransformer", false]], "freezevaluewithoutcalibtransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib)": [[75, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib.FreezeValueWithoutCalibTransformer", false]], "frozen_pb_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.frozen_pb_session", false]], "frozen_pb_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.frozen_pb_session", false]], "fulltokenizer (class in neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.FullTokenizer", false]], "function1() (in module neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.function1", false]], "function2() (in module neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.function2", false]], "function3() (in module neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.function3", false]], "fuse() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.fuse", false]], "fusebiasaddandaddoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add)": [[49, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add.FuseBiasAddAndAddOptimizer", false]], "fusebiasaddandaddoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add)": [[321, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add.FuseBiasAddAndAddOptimizer", false]], "fusecolumnwisemuloptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul)": [[50, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul.FuseColumnWiseMulOptimizer", false]], "fusecolumnwisemuloptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul)": [[322, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul.FuseColumnWiseMulOptimizer", false]], "fuseconvredundantdequantizetransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize)": [[76, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize.FuseConvRedundantDequantizeTransformer", false]], "fuseconvredundantdequantizetransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize)": [[347, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize.FuseConvRedundantDequantizeTransformer", false]], "fuseconvrequantizetransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize)": [[77, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize.FuseConvRequantizeTransformer", false]], "fuseconvrequantizetransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize)": [[348, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize.FuseConvRequantizeTransformer", false]], "fuseconvwithmathoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math)": [[51, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math.FuseConvWithMathOptimizer", false]], "fuseconvwithmathoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math)": [[323, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math.FuseConvWithMathOptimizer", false]], "fusedecomposedbnoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.FuseDecomposedBNOptimizer", false]], "fusedecomposedbnoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.FuseDecomposedBNOptimizer", false]], "fusedecomposedinoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.FuseDecomposedINOptimizer", false]], "fusedecomposedinoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.FuseDecomposedINOptimizer", false]], "fusedmatmuloperator (class in neural_compressor.adaptor.ox_utils.operators.matmul)": [[18, "neural_compressor.adaptor.ox_utils.operators.matmul.FusedMatMulOperator", false]], "fusegeluoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu)": [[54, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu.FuseGeluOptimizer", false]], "fusegeluoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu)": [[326, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu.FuseGeluOptimizer", false]], "fuselayernormoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm)": [[55, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm.FuseLayerNormOptimizer", false]], "fuselayernormoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm)": [[327, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm.FuseLayerNormOptimizer", false]], "fusematmulredundantdequantizetransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize)": [[78, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize.FuseMatMulRedundantDequantizeTransformer", false]], "fusematmulredundantdequantizetransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize)": [[349, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize.FuseMatMulRedundantDequantizeTransformer", false]], "fusematmulrequantizedequantizenewapitransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize)": [[79, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeDequantizeNewAPITransformer", false]], "fusematmulrequantizedequantizenewapitransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize)": [[350, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeDequantizeNewAPITransformer", false]], "fusematmulrequantizedequantizetransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize)": [[79, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeDequantizeTransformer", false]], "fusematmulrequantizedequantizetransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize)": [[350, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeDequantizeTransformer", false]], "fusematmulrequantizenewapitransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize)": [[79, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeNewAPITransformer", false]], "fusematmulrequantizenewapitransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize)": [[350, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeNewAPITransformer", false]], "fusematmulrequantizetransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize)": [[79, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeTransformer", false]], "fusematmulrequantizetransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize)": [[350, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeTransformer", false]], "fusenodestartwithconcatv2 (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2)": [[109, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2.FuseNodeStartWithConcatV2", false]], "fusenodestartwithconcatv2 (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2)": [[119, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2.FuseNodeStartWithConcatV2", false]], "fusenodestartwithconcatv2 (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2)": [[364, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2.FuseNodeStartWithConcatV2", false]], "fusenodestartwithconcatv2 (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2)": [[374, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2.FuseNodeStartWithConcatV2", false]], "fusenodestartwithconv2d (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv)": [[110, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv.FuseNodeStartWithConv2d", false]], "fusenodestartwithconv2d (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv)": [[120, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv.FuseNodeStartWithConv2d", false]], "fusenodestartwithconv2d (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv)": [[365, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv.FuseNodeStartWithConv2d", false]], "fusenodestartwithconv2d (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv)": [[375, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv.FuseNodeStartWithConv2d", false]], "fusenodestartwithdeconv2d (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv)": [[111, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv.FuseNodeStartWithDeconv2d", false]], "fusenodestartwithdeconv2d (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv)": [[366, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv.FuseNodeStartWithDeconv2d", false]], "fusenodestartwithfusedbatchnormv3 (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn)": [[108, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn.FuseNodeStartWithFusedBatchNormV3", false]], "fusenodestartwithfusedbatchnormv3 (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn)": [[118, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn.FuseNodeStartWithFusedBatchNormV3", false]], "fusenodestartwithfusedbatchnormv3 (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn)": [[363, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn.FuseNodeStartWithFusedBatchNormV3", false]], "fusenodestartwithfusedbatchnormv3 (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn)": [[373, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn.FuseNodeStartWithFusedBatchNormV3", false]], "fusenodestartwithfusedinstancenorm (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in)": [[112, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in.FuseNodeStartWithFusedInstanceNorm", false]], "fusenodestartwithfusedinstancenorm (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in)": [[367, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in.FuseNodeStartWithFusedInstanceNorm", false]], "fusenodestartwithmatmul (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul)": [[113, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul.FuseNodeStartWithMatmul", false]], "fusenodestartwithmatmul (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul)": [[122, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul.FuseNodeStartWithMatmul", false]], "fusenodestartwithmatmul (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul)": [[368, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul.FuseNodeStartWithMatmul", false]], "fusenodestartwithmatmul (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul)": [[377, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul.FuseNodeStartWithMatmul", false]], "fusenodestartwithpooling (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling)": [[114, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling.FuseNodeStartWithPooling", false]], "fusenodestartwithpooling (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling)": [[123, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling.FuseNodeStartWithPooling", false]], "fusenodestartwithpooling (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling)": [[369, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling.FuseNodeStartWithPooling", false]], "fusenodestartwithpooling (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling)": [[378, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling.FuseNodeStartWithPooling", false]], "fusepadwithconv2doptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv)": [[56, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv.FusePadWithConv2DOptimizer", false]], "fusepadwithconv2doptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv)": [[328, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv.FusePadWithConv2DOptimizer", false]], "fusepadwithfp32conv2doptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv)": [[57, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv.FusePadWithFP32Conv2DOptimizer", false]], "fusepadwithfp32conv2doptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv)": [[329, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv.FusePadWithFP32Conv2DOptimizer", false]], "fusetransposereshapeoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose)": [[58, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose.FuseTransposeReshapeOptimizer", false]], "fusetransposereshapeoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose)": [[330, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose.FuseTransposeReshapeOptimizer", false]], "gatheroperator (class in neural_compressor.adaptor.ox_utils.operators.gather)": [[13, "neural_compressor.adaptor.ox_utils.operators.gather.GatherOperator", false]], "gemmoperator (class in neural_compressor.adaptor.ox_utils.operators.gemm)": [[15, "neural_compressor.adaptor.ox_utils.operators.gemm.GemmOperator", false]], "gen_bar_updater() (in module neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.gen_bar_updater", false]], "generaltopk (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.GeneralTopK", false]], "generate_activation_observer() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.generate_activation_observer", false]], "generate_activation_observer() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.generate_activation_observer", false]], "generate_feed_dict() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.generate_feed_dict", false]], "generate_feed_dict() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.generate_feed_dict", false]], "generate_ffn2_pruning_config() (in module neural_compressor.compression.pruner.model_slim.auto_slim)": [[171, "neural_compressor.compression.pruner.model_slim.auto_slim.generate_ffn2_pruning_config", false]], "generate_mha_pruning_config() (in module neural_compressor.compression.pruner.model_slim.auto_slim)": [[171, "neural_compressor.compression.pruner.model_slim.auto_slim.generate_mha_pruning_config", false]], "generate_prefix() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.generate_prefix", false]], "generate_prefix() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.generate_prefix", false]], "generate_xpu_qconfig() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.generate_xpu_qconfig", false]], "generategraphwithqdqpattern (class in neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern)": [[92, "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern.GenerateGraphWithQDQPattern", false]], "generategraphwithqdqpattern (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern)": [[357, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern.GenerateGraphWithQDQPattern", false]], "generator1() (in module neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.generator1", false]], "get_absorb_layers() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_absorb_layers", false]], "get_absorb_layers() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.get_absorb_layers", false]], "get_accelerator() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.get_accelerator", false]], "get_activation() (in module neural_compressor.compression.distillation.utility)": [[166, "neural_compressor.compression.distillation.utility.get_activation", false]], "get_adaptor_name() (in module neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.get_adaptor_name", false]], "get_algorithm() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.get_algorithm", false]], "get_all_config_set() (in module neural_compressor.tensorflow.quantization.autotune)": [[302, "neural_compressor.tensorflow.quantization.autotune.get_all_config_set", false]], "get_all_config_set() (in module neural_compressor.torch.quantization.autotune)": [[438, "neural_compressor.torch.quantization.autotune.get_all_config_set", false]], "get_all_config_set_from_config_registry() (in module neural_compressor.common.base_config)": [[152, "neural_compressor.common.base_config.get_all_config_set_from_config_registry", false]], "get_all_fp32_data() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.get_all_fp32_data", false]], "get_all_fp32_data() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_all_fp32_data", false]], "get_all_registered_configs() (in module neural_compressor.tensorflow.keras.quantization.config)": [[299, "neural_compressor.tensorflow.keras.quantization.config.get_all_registered_configs", false]], "get_all_registered_configs() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_all_registered_configs", false]], "get_architecture() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.get_architecture", false]], "get_attributes() (in module neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.get_attributes", false]], "get_blob_size() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.get_blob_size", false]], "get_block_prefix() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_block_prefix", false]], "get_block_prefix() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.get_block_prefix", false]], "get_bounded_threads() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.get_bounded_threads", false]], "get_children() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.get_children", false]], "get_children() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.get_children", false]], "get_common_module() (in module neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.get_common_module", false]], "get_const_dim_count() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.get_const_dim_count", false]], "get_const_dim_count() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.get_const_dim_count", false]], "get_const_dim_count() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.get_const_dim_count", false]], "get_const_dim_count() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.get_const_dim_count", false]], "get_core_ids() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.get_core_ids", false]], "get_criterion() (in module neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.get_criterion", false]], "get_dataloader() (in module neural_compressor.torch.algorithms.weight_only.autoround)": [[418, "neural_compressor.torch.algorithms.weight_only.autoround.get_dataloader", false]], "get_default_autoround_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_AutoRound_config", false]], "get_default_awq_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_awq_config", false]], "get_default_double_quant_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_double_quant_config", false]], "get_default_dynamic_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_dynamic_config", false]], "get_default_fp8_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_fp8_config", false]], "get_default_fp8_config_set() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_fp8_config_set", false]], "get_default_gptq_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_gptq_config", false]], "get_default_hqq_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_hqq_config", false]], "get_default_mixed_precision_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_mixed_precision_config", false]], "get_default_mixed_precision_config_set() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_mixed_precision_config_set", false]], "get_default_mx_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_mx_config", false]], "get_default_rtn_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_rtn_config", false]], "get_default_sq_config() (in module neural_compressor.tensorflow.quantization.config)": [[303, "neural_compressor.tensorflow.quantization.config.get_default_sq_config", false]], "get_default_sq_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_sq_config", false]], "get_default_static_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_static_config", false]], "get_default_static_quant_config() (in module neural_compressor.tensorflow.keras.quantization.config)": [[299, "neural_compressor.tensorflow.keras.quantization.config.get_default_static_quant_config", false]], "get_default_static_quant_config() (in module neural_compressor.tensorflow.quantization.config)": [[303, "neural_compressor.tensorflow.quantization.config.get_default_static_quant_config", false]], "get_default_teq_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_teq_config", false]], "get_depth() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_depth", false]], "get_depth() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.get_depth", false]], "get_dict_at_depth() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_dict_at_depth", false]], "get_dict_at_depth() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.get_dict_at_depth", false]], "get_double_quant_config_dict() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.get_double_quant_config_dict", false]], "get_element_under_depth() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_element_under_depth", false]], "get_element_under_depth() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.get_element_under_depth", false]], "get_embedding_contiguous() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_embedding_contiguous", false]], "get_estimator_graph() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_estimator_graph", false]], "get_example_input() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_example_input", false]], "get_fallback_order() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_fallback_order", false]], "get_filter_fn() (in module neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.get_filter_fn", false]], "get_final_text() (in module neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.get_final_text", false]], "get_framework_name() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.get_framework_name", false]], "get_func_from_config() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.get_func_from_config", false]], "get_graph_def() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_graph_def", false]], "get_graph_def() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.get_graph_def", false]], "get_half_precision_node_set() (in module neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.get_half_precision_node_set", false]], "get_hidden_states() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_hidden_states", false]], "get_index_from_strided_slice_of_shape() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.get_index_from_strided_slice_of_shape", false]], "get_input_output_node_names() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_input_output_node_names", false]], "get_input_output_node_names() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.get_input_output_node_names", false]], "get_ipex_version() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.get_ipex_version", false]], "get_layers() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.get_layers", false]], "get_linux_numa_info() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.get_linux_numa_info", false]], "get_max_supported_opset_version() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema)": [[89, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema.get_max_supported_opset_version", false]], "get_metrics() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.get_metrics", false]], "get_model_device() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.get_model_device", false]], "get_model_fwk_name() (in module neural_compressor.model.model)": [[239, "neural_compressor.model.model.get_model_fwk_name", false]], "get_model_info() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.get_model_info", false]], "get_model_input_shape() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_model_input_shape", false]], "get_model_input_shape() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.get_model_input_shape", false]], "get_model_type() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.get_model_type", false]], "get_model_type() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.get_model_type", false]], "get_module() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.get_module", false]], "get_module() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.get_module", false]], "get_module() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.get_module", false]], "get_module() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.get_module", false]], "get_module_input_output() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_module_input_output", false]], "get_module_input_output() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.get_module_input_output", false]], "get_mse_order_per_fp32() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_mse_order_per_fp32", false]], "get_mse_order_per_int8() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_mse_order_per_int8", false]], "get_named_children() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.get_named_children", false]], "get_named_children() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.get_named_children", false]], "get_node_mapping() (in module neural_compressor.utils.export.torch2onnx)": [[458, "neural_compressor.utils.export.torch2onnx.get_node_mapping", false]], "get_node_original_name() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.get_node_original_name", false]], "get_numa_node() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.get_numa_node", false]], "get_number_of_sockets() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_number_of_sockets", false]], "get_op_list() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_op_list", false]], "get_op_type_by_name() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_op_type_by_name", false]], "get_parent() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.get_parent", false]], "get_parent() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.get_parent", false]], "get_pattern() (in module neural_compressor.compression.pruner.patterns)": [[176, "neural_compressor.compression.pruner.patterns.get_pattern", false]], "get_physical_ids() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.get_physical_ids", false]], "get_postprocess() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.get_postprocess", false]], "get_preprocess() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.get_preprocess", false]], "get_processor_type_from_user_config() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.get_processor_type_from_user_config", false]], "get_pruner() (in module neural_compressor.compression.pruner.pruners)": [[183, "neural_compressor.compression.pruner.pruners.get_pruner", false]], "get_quant_dequant_output() (in module neural_compressor.adaptor.ox_utils.smooth_quant)": [[29, "neural_compressor.adaptor.ox_utils.smooth_quant.get_quant_dequant_output", false]], "get_quantizable_onnx_ops() (in module neural_compressor.utils.export.torch2onnx)": [[458, "neural_compressor.utils.export.torch2onnx.get_quantizable_onnx_ops", false]], "get_quantizable_ops_from_cfgs() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_quantizable_ops_from_cfgs", false]], "get_quantizable_ops_from_cfgs() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.get_quantizable_ops_from_cfgs", false]], "get_quantizable_ops_recursively() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.get_quantizable_ops_recursively", false]], "get_quantizable_ops_recursively() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.get_quantizable_ops_recursively", false]], "get_quantizer() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.get_quantizer", false]], "get_reg() (in module neural_compressor.compression.pruner.regs)": [[189, "neural_compressor.compression.pruner.regs.get_reg", false]], "get_reg_type() (in module neural_compressor.compression.pruner.regs)": [[189, "neural_compressor.compression.pruner.regs.get_reg_type", false]], "get_reversed_numa_info() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.get_reversed_numa_info", false]], "get_rtn_double_quant_config_set() (in module neural_compressor.torch.quantization.autotune)": [[438, "neural_compressor.torch.quantization.autotune.get_rtn_double_quant_config_set", false]], "get_scheduler() (in module neural_compressor.compression.pruner.schedulers)": [[190, "neural_compressor.compression.pruner.schedulers.get_scheduler", false]], "get_schema() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema)": [[89, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema.get_schema", false]], "get_size() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_size", false]], "get_sparsity_ratio() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.get_sparsity_ratio", false]], "get_sparsity_ratio_tf() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.get_sparsity_ratio_tf", false]], "get_subgraphs_from_onnx() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.get_subgraphs_from_onnx", false]], "get_super_module_by_name() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.get_super_module_by_name", false]], "get_super_module_by_name() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.get_super_module_by_name", false]], "get_tensor_by_name() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_tensor_by_name", false]], "get_tensor_by_name() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.get_tensor_by_name", false]], "get_tensor_histogram() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.get_tensor_histogram", false]], "get_tensor_histogram() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_tensor_histogram", false]], "get_tensor_val_from_graph_node() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_tensor_val_from_graph_node", false]], "get_tensorflow_node_attr() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.get_tensorflow_node_attr", false]], "get_tensorflow_node_shape_attr() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.get_tensorflow_node_shape_attr", false]], "get_tensorflow_tensor_data() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.get_tensorflow_tensor_data", false]], "get_tensorflow_tensor_shape() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.get_tensorflow_tensor_shape", false]], "get_tensors_info() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_tensors_info", false]], "get_tf_criterion() (in module neural_compressor.compression.pruner.tf_criteria)": [[191, "neural_compressor.compression.pruner.tf_criteria.get_tf_criterion", false]], "get_tf_model_type() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.get_tf_model_type", false]], "get_threads() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.get_threads", false]], "get_threads_per_core() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.get_threads_per_core", false]], "get_torch_version() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_torch_version", false]], "get_torch_version() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.get_torch_version", false]], "get_torchvision_map() (in module neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.get_torchvision_map", false]], "get_tuning_history() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_tuning_history", false]], "get_unquantized_node_set() (in module neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.get_unquantized_node_set", false]], "get_weight_from_input_tensor() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_weight_from_input_tensor", false]], "get_weight_scale() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.get_weight_scale", false]], "get_weights_details() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_weights_details", false]], "get_windows_numa_info() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.get_windows_numa_info", false]], "get_woq_tuning_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_woq_tuning_config", false]], "get_workspace() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.get_workspace", false]], "global_state (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.GLOBAL_STATE", false]], "global_step (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.global_step", false]], "global_step (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.global_step", false]], "global_step (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.global_step", false]], "globalaveragepooloperator (class in neural_compressor.adaptor.ox_utils.operators.gavgpool)": [[14, "neural_compressor.adaptor.ox_utils.operators.gavgpool.GlobalAveragePoolOperator", false]], "gptq (class in neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.GPTQ", false]], "gptq() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.gptq", false]], "gptq_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.gptq_entry", false]], "gptq_quantize() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.gptq_quantize", false]], "gptqconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.GPTQConfig", false]], "gptqconfig (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.GPTQConfig", false]], "gptquantizer (class in neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.GPTQuantizer", false]], "gradientcriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.GradientCriterion", false]], "graph_def_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.graph_def_session", false]], "graph_def_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.graph_def_session", false]], "graph_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.graph_session", false]], "graph_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.graph_session", false]], "graphanalyzer (class in neural_compressor.adaptor.tf_utils.graph_util)": [[95, "neural_compressor.adaptor.tf_utils.graph_util.GraphAnalyzer", false]], "graphanalyzer (class in neural_compressor.tensorflow.quantization.utils.graph_util)": [[360, "neural_compressor.tensorflow.quantization.utils.graph_util.GraphAnalyzer", false]], "graphconverter (class in neural_compressor.adaptor.tf_utils.graph_converter)": [[33, "neural_compressor.adaptor.tf_utils.graph_converter.GraphConverter", false]], "graphconverter (class in neural_compressor.tensorflow.quantization.utils.graph_converter)": [[306, "neural_compressor.tensorflow.quantization.utils.graph_converter.GraphConverter", false]], "graphconverterwithoutcalib (class in neural_compressor.adaptor.tf_utils.graph_converter_without_calib)": [[34, "neural_compressor.adaptor.tf_utils.graph_converter_without_calib.GraphConverterWithoutCalib", false]], "graphcseoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer)": [[59, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer.GraphCseOptimizer", false]], "graphcseoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer)": [[331, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer.GraphCseOptimizer", false]], "graphfoldconstantoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant)": [[48, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant.GraphFoldConstantOptimizer", false]], "graphfoldconstantoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant)": [[320, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant.GraphFoldConstantOptimizer", false]], "graphrewriterbase (class in neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base)": [[71, "neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base.GraphRewriterBase", false]], "graphrewriterbase (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base)": [[343, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base.GraphRewriterBase", false]], "graphrewriterhelper (class in neural_compressor.adaptor.tf_utils.graph_util)": [[95, "neural_compressor.adaptor.tf_utils.graph_util.GraphRewriterHelper", false]], "graphrewriterhelper (class in neural_compressor.tensorflow.quantization.utils.graph_util)": [[360, "neural_compressor.tensorflow.quantization.utils.graph_util.GraphRewriterHelper", false]], "graphtrace (class in neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.GraphTrace", false]], "graphtrace (class in neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.GraphTrace", false]], "graphtransformbase (class in neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base)": [[129, "neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base.GraphTransformBase", false]], "graphtransformbase (class in neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base)": [[381, "neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base.GraphTransformBase", false]], "grappleroptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass)": [[60, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass.GrapplerOptimizer", false]], "grappleroptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass)": [[332, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass.GrapplerOptimizer", false]], "group_size (neural_compressor.torch.algorithms.weight_only.hqq.qtensor.qtensormetainfo attribute)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo.group_size", false]], "grouplasso (class in neural_compressor.compression.pruner.regs)": [[189, "neural_compressor.compression.pruner.regs.GroupLasso", false]], "halfprecisionconverter (class in neural_compressor.torch.algorithms.mixed_precision.half_precision_convert)": [[399, "neural_compressor.torch.algorithms.mixed_precision.half_precision_convert.HalfPrecisionConverter", false]], "halfprecisionmodulewrapper (class in neural_compressor.torch.algorithms.mixed_precision.module_wrappers)": [[401, "neural_compressor.torch.algorithms.mixed_precision.module_wrappers.HalfPrecisionModuleWrapper", false]], "hawq_top() (in module neural_compressor.adaptor.torch_utils.hawq_metric)": [[135, "neural_compressor.adaptor.torch_utils.hawq_metric.hawq_top", false]], "hawq_v2tunestrategy (class in neural_compressor.strategy.hawq_v2)": [[269, "neural_compressor.strategy.hawq_v2.HAWQ_V2TuneStrategy", false]], "head_masks (neural_compressor.compression.pruner.pruners.mha.pythonmultiheadattentionpruner attribute)": [[184, "neural_compressor.compression.pruner.pruners.mha.PythonMultiheadAttentionPruner.head_masks", false]], "hessiantrace (class in neural_compressor.adaptor.torch_utils.hawq_metric)": [[135, "neural_compressor.adaptor.torch_utils.hawq_metric.HessianTrace", false]], "histogramcollector (class in neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.HistogramCollector", false]], "hpoconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.HPOConfig", false]], "hpu_accelerator (class in neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.HPU_Accelerator", false]], "hpuweightonlylinear (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.HPUWeightOnlyLinear", false]], "hqq_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.hqq_entry", false]], "hqqconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.HQQConfig", false]], "hqqlinear (class in neural_compressor.torch.algorithms.weight_only.hqq.core)": [[423, "neural_compressor.torch.algorithms.weight_only.hqq.core.HQQLinear", false]], "hqqmoduleconfig (class in neural_compressor.torch.algorithms.weight_only.hqq.config)": [[422, "neural_compressor.torch.algorithms.weight_only.hqq.config.HQQModuleConfig", false]], "hqqtensorhandle (class in neural_compressor.torch.algorithms.weight_only.hqq.core)": [[423, "neural_compressor.torch.algorithms.weight_only.hqq.core.HQQTensorHandle", false]], "hqquantizer (class in neural_compressor.torch.algorithms.weight_only.hqq.quantizer)": [[427, "neural_compressor.torch.algorithms.weight_only.hqq.quantizer.HQQuantizer", false]], "imagefolder (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.ImageFolder", false]], "imagenetraw (class in neural_compressor.data.datasets.imagenet_dataset)": [[214, "neural_compressor.data.datasets.imagenet_dataset.ImagenetRaw", false]], "incquantizationconfigmixin (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.INCQuantizationConfigMixin", false]], "incweightonlylinear (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.INCWeightOnlyLinear", false]], "indexfetcher (class in neural_compressor.data.dataloaders.fetcher)": [[203, "neural_compressor.data.dataloaders.fetcher.IndexFetcher", false]], "indexfetcher (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.IndexFetcher", false]], "infer_onnx_shape_dtype() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.infer_onnx_shape_dtype", false]], "infer_shapes() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.infer_shapes", false]], "info() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.info", false]], "init_quantize_config() (in module neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper)": [[101, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper.init_quantize_config", false]], "init_tuning() (in module neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.init_tuning", false]], "initial_tuning_cfg_with_quant_mode() (in module neural_compressor.strategy.utils.tuning_space)": [[278, "neural_compressor.strategy.utils.tuning_space.initial_tuning_cfg_with_quant_mode", false]], "initialize_int8_avgpool() (in module neural_compressor.tensorflow.keras.layers.pool2d)": [[297, "neural_compressor.tensorflow.keras.layers.pool2d.initialize_int8_avgpool", false]], "initialize_int8_conv2d() (in module neural_compressor.tensorflow.keras.layers.conv2d)": [[292, "neural_compressor.tensorflow.keras.layers.conv2d.initialize_int8_conv2d", false]], "initialize_int8_dense() (in module neural_compressor.tensorflow.keras.layers.dense)": [[293, "neural_compressor.tensorflow.keras.layers.dense.initialize_int8_dense", false]], "initialize_int8_depthwise_conv2d() (in module neural_compressor.tensorflow.keras.layers.depthwise_conv2d)": [[294, "neural_compressor.tensorflow.keras.layers.depthwise_conv2d.initialize_int8_depthwise_conv2d", false]], "initialize_int8_maxpool() (in module neural_compressor.tensorflow.keras.layers.pool2d)": [[297, "neural_compressor.tensorflow.keras.layers.pool2d.initialize_int8_maxpool", false]], "initialize_int8_separable_conv2d() (in module neural_compressor.tensorflow.keras.layers.separable_conv2d)": [[298, "neural_compressor.tensorflow.keras.layers.separable_conv2d.initialize_int8_separable_conv2d", false]], "initialize_name_counter() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.initialize_name_counter", false]], "injectdummybiasaddoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd)": [[44, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd.InjectDummyBiasAddOptimizer", false]], "injectdummybiasaddoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd)": [[316, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd.InjectDummyBiasAddOptimizer", false]], "input2tuple() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.input2tuple", false]], "inputfeatures (class in neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.InputFeatures", false]], "inputfeatures (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.InputFeatures", false]], "insertlogging (class in neural_compressor.adaptor.tf_utils.transform_graph.insert_logging)": [[131, "neural_compressor.adaptor.tf_utils.transform_graph.insert_logging.InsertLogging", false]], "insertlogging (class in neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging)": [[383, "neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging.InsertLogging", false]], "insertprintminmaxnode (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node)": [[62, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node.InsertPrintMinMaxNode", false]], "insertprintminmaxnode (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node)": [[334, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node.InsertPrintMinMaxNode", false]], "int8_node_name_reverse() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.int8_node_name_reverse", false]], "intermediatelayersknowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.IntermediateLayersKnowledgeDistillationLoss", false]], "intermediatelayersknowledgedistillationlossconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.IntermediateLayersKnowledgeDistillationLossConfig", false]], "invalid_layers (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.invalid_layers", false]], "invalid_layers (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.invalid_layers", false]], "invalid_layers (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.invalid_layers", false]], "ipexmodel (class in neural_compressor.model.torch_model)": [[244, "neural_compressor.model.torch_model.IPEXModel", false]], "is_b_transposed() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.is_B_transposed", false]], "is_ckpt_format() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.is_ckpt_format", false]], "is_ckpt_format() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.is_ckpt_format", false]], "is_fused_module() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.is_fused_module", false]], "is_global (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.is_global", false]], "is_global (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.is_global", false]], "is_global (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.is_global", false]], "is_hpex_available() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.is_hpex_available", false]], "is_int8_model() (in module neural_compressor.utils.pytorch)": [[464, "neural_compressor.utils.pytorch.is_int8_model", false]], "is_ipex_available() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.is_ipex_available", false]], "is_ipex_imported() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.is_ipex_imported", false]], "is_leaf() (in module neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.is_leaf", false]], "is_list_or_tuple() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.is_list_or_tuple", false]], "is_model_quantized() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.is_model_quantized", false]], "is_onnx_domain() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.is_onnx_domain", false]], "is_package_available() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.is_package_available", false]], "is_saved_model_format() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.is_saved_model_format", false]], "is_saved_model_format() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.is_saved_model_format", false]], "is_transformers_imported() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.is_transformers_imported", false]], "isiterable() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.isiterable", false]], "iterabledataset (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.IterableDataset", false]], "iterablefetcher (class in neural_compressor.data.dataloaders.fetcher)": [[203, "neural_compressor.data.dataloaders.fetcher.IterableFetcher", false]], "iterablefetcher (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.IterableFetcher", false]], "iterablesampler (class in neural_compressor.data.dataloaders.sampler)": [[207, "neural_compressor.data.dataloaders.sampler.IterableSampler", false]], "iterablesampler (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.IterableSampler", false]], "iterativescheduler (class in neural_compressor.compression.pruner.schedulers)": [[190, "neural_compressor.compression.pruner.schedulers.IterativeScheduler", false]], "iterator_sess_run() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.iterator_sess_run", false]], "iterator_sess_run() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.iterator_sess_run", false]], "itex_installed() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.itex_installed", false]], "jitbasicsearcher (class in neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher", false]], "k (neural_compressor.metric.metric.generaltopk attribute)": [[234, "neural_compressor.metric.metric.GeneralTopK.k", false]], "k (neural_compressor.metric.metric.tensorflowtopk attribute)": [[234, "neural_compressor.metric.metric.TensorflowTopK.k", false]], "keep_mask_layers (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.keep_mask_layers", false]], "keep_mask_layers (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.keep_mask_layers", false]], "keep_mask_layers (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.keep_mask_layers", false]], "keras (class in neural_compressor.config)": [[195, "neural_compressor.config.Keras", false]], "keras_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.keras_session", false]], "keras_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.keras_session", false]], "kerasadaptor (class in neural_compressor.tensorflow.algorithms.static_quant.keras)": [[288, "neural_compressor.tensorflow.algorithms.static_quant.keras.KerasAdaptor", false]], "kerasbasepattern (class in neural_compressor.compression.pruner.patterns.base)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern", false]], "kerasbasepruner (class in neural_compressor.compression.pruner.pruners.base)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner", false]], "kerasbasicpruner (class in neural_compressor.compression.pruner.pruners.basic)": [[181, "neural_compressor.compression.pruner.pruners.basic.KerasBasicPruner", false]], "kerasconfigconverter (class in neural_compressor.tensorflow.algorithms.static_quant.keras)": [[288, "neural_compressor.tensorflow.algorithms.static_quant.keras.KerasConfigConverter", false]], "kerasmodel (class in neural_compressor.model.keras_model)": [[238, "neural_compressor.model.keras_model.KerasModel", false]], "kerasmodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.KerasModel", false]], "keraspatternnxm (class in neural_compressor.compression.pruner.patterns.nxm)": [[179, "neural_compressor.compression.pruner.patterns.nxm.KerasPatternNxM", false]], "kerasquery (class in neural_compressor.tensorflow.algorithms.static_quant.keras)": [[288, "neural_compressor.tensorflow.algorithms.static_quant.keras.KerasQuery", false]], "kerassurgery (class in neural_compressor.tensorflow.algorithms.static_quant.keras)": [[288, "neural_compressor.tensorflow.algorithms.static_quant.keras.KerasSurgery", false]], "kl_divergence (class in neural_compressor.utils.kl_divergence)": [[460, "neural_compressor.utils.kl_divergence.KL_Divergence", false]], "klcalibrator (class in neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.KLCalibrator", false]], "knowledgedistillationframework (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.KnowledgeDistillationFramework", false]], "knowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.KnowledgeDistillationLoss", false]], "knowledgedistillationlossconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.KnowledgeDistillationLossConfig", false]], "label_list (neural_compressor.metric.metric.accuracy attribute)": [[234, "neural_compressor.metric.metric.Accuracy.label_list", false]], "label_list (neural_compressor.metric.metric.mae attribute)": [[234, "neural_compressor.metric.metric.MAE.label_list", false]], "label_list (neural_compressor.metric.metric.mse attribute)": [[234, "neural_compressor.metric.metric.MSE.label_list", false]], "labelbalancecocorawfilter (class in neural_compressor.data.filters.coco_filter)": [[217, "neural_compressor.data.filters.coco_filter.LabelBalanceCOCORawFilter", false]], "labelbalancecocorecordfilter (class in neural_compressor.data.filters.coco_filter)": [[217, "neural_compressor.data.filters.coco_filter.LabelBalanceCOCORecordFilter", false]], "labels (neural_compressor.metric.bleu.bleu attribute)": [[227, "neural_compressor.metric.bleu.BLEU.labels", false]], "labelshift (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.LabelShift", false]], "layer_1 (neural_compressor.compression.pruner.model_slim.weight_slim.linearcompression attribute)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompression.layer_1", false]], "layer_2 (neural_compressor.compression.pruner.model_slim.weight_slim.linearcompression attribute)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompression.layer_2", false]], "layerhistogramcollector (class in neural_compressor.utils.collect_layer_histogram)": [[452, "neural_compressor.utils.collect_layer_histogram.LayerHistogramCollector", false]], "layerwisequant (class in neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize)": [[139, "neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize.LayerWiseQuant", false]], "lazyimport (class in neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.LazyImport", false]], "lazyimport (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.LazyImport", false]], "linear2linearsearcher (class in neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher", false]], "linear_layers (neural_compressor.compression.pruner.pruners.mha.pythonmultiheadattentionpruner attribute)": [[184, "neural_compressor.compression.pruner.pruners.mha.PythonMultiheadAttentionPruner.linear_layers", false]], "linear_patterns (neural_compressor.compression.pruner.model_slim.weight_slim.linearcompressioniterator attribute)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompressionIterator.linear_patterns", false]], "linearcompression (class in neural_compressor.compression.pruner.model_slim.weight_slim)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompression", false]], "linearcompressioniterator (class in neural_compressor.compression.pruner.model_slim.weight_slim)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompressionIterator", false]], "load() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load)": [[140, "neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load.load", false]], "load() (in module neural_compressor.torch.algorithms.layer_wise.load)": [[396, "neural_compressor.torch.algorithms.layer_wise.load.load", false]], "load() (in module neural_compressor.torch.algorithms.pt2e_quant.save_load)": [[408, "neural_compressor.torch.algorithms.pt2e_quant.save_load.load", false]], "load() (in module neural_compressor.torch.algorithms.static_quant.save_load)": [[415, "neural_compressor.torch.algorithms.static_quant.save_load.load", false]], "load() (in module neural_compressor.torch.algorithms.weight_only.save_load)": [[431, "neural_compressor.torch.algorithms.weight_only.save_load.load", false]], "load() (in module neural_compressor.torch.quantization.load_entry)": [[441, "neural_compressor.torch.quantization.load_entry.load", false]], "load() (in module neural_compressor.utils.pytorch)": [[464, "neural_compressor.utils.pytorch.load", false]], "load_and_cache_examples() (in module neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.load_and_cache_examples", false]], "load_config_mapping() (in module neural_compressor.common.utils.save_load)": [[160, "neural_compressor.common.utils.save_load.load_config_mapping", false]], "load_data_from_pkl() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.load_data_from_pkl", false]], "load_empty_model() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.load_empty_model", false]], "load_empty_model() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.load_empty_model", false]], "load_empty_model() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.load_empty_model", false]], "load_layer_wise_quantized_model() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.load_layer_wise_quantized_model", false]], "load_layer_wise_quantized_model() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.load_layer_wise_quantized_model", false]], "load_module() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.load_module", false]], "load_saved_model() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.load_saved_model", false]], "load_saved_model() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.load_saved_model", false]], "load_tensor() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.load_tensor", false]], "load_tensor() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.load_tensor", false]], "load_tensor_from_shard() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.load_tensor_from_shard", false]], "load_tensor_from_shard() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.load_tensor_from_shard", false]], "load_value() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.load_value", false]], "load_vocab() (in module neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.load_vocab", false]], "load_weight_only() (in module neural_compressor.utils.pytorch)": [[464, "neural_compressor.utils.pytorch.load_weight_only", false]], "loadformat (class in neural_compressor.torch.utils.constants)": [[444, "neural_compressor.torch.utils.constants.LoadFormat", false]], "log() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.log", false]], "log_process() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.log_process", false]], "log_quantizable_layers_per_transformer() (in module neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.log_quantizable_layers_per_transformer", false]], "logger (class in neural_compressor.common.utils.logger)": [[159, "neural_compressor.common.utils.logger.Logger", false]], "logger (class in neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.Logger", false]], "loss (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.Loss", false]], "lowerbitssampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.LowerBitsSampler", false]], "lstmoperator (class in neural_compressor.adaptor.ox_utils.operators.lstm)": [[17, "neural_compressor.adaptor.ox_utils.operators.lstm.LSTMOperator", false]], "m (neural_compressor.compression.pruner.patterns.mha.patternmha attribute)": [[177, "neural_compressor.compression.pruner.patterns.mha.PatternMHA.M", false]], "m (neural_compressor.compression.pruner.patterns.ninm.pytorchpatternninm attribute)": [[178, "neural_compressor.compression.pruner.patterns.ninm.PytorchPatternNInM.M", false]], "mae (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.MAE", false]], "magnitudecriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.MagnitudeCriterion", false]], "magnitudecriterion (class in neural_compressor.compression.pruner.tf_criteria)": [[191, "neural_compressor.compression.pruner.tf_criteria.MagnitudeCriterion", false]], "make_dquant_node() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.make_dquant_node", false]], "make_matmul_weight_only_node() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.make_matmul_weight_only_node", false]], "make_module() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.make_module", false]], "make_nc_model() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.make_nc_model", false]], "make_onnx_inputs_outputs() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.make_onnx_inputs_outputs", false]], "make_onnx_shape() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.make_onnx_shape", false]], "make_quant_node() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.make_quant_node", false]], "make_sub_graph() (in module neural_compressor.adaptor.ox_utils.smooth_quant)": [[29, "neural_compressor.adaptor.ox_utils.smooth_quant.make_sub_graph", false]], "make_symbol_block() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.make_symbol_block", false]], "map_numpy_to_onnx_dtype() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.map_numpy_to_onnx_dtype", false]], "map_onnx_to_numpy_type() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.map_onnx_to_numpy_type", false]], "map_tensorflow_dtype() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.map_tensorflow_dtype", false]], "masks (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.masks", false]], "masks (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.masks", false]], "masks (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.masks", false]], "match_datatype_pattern() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.match_datatype_pattern", false]], "matmuloperator (class in neural_compressor.adaptor.ox_utils.operators.matmul)": [[18, "neural_compressor.adaptor.ox_utils.operators.matmul.MatMulOperator", false]], "max_sparsity_ratio_per_op (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.max_sparsity_ratio_per_op", false]], "max_sparsity_ratio_per_op (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.max_sparsity_ratio_per_op", false]], "max_sparsity_ratio_per_op (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.max_sparsity_ratio_per_op", false]], "max_sparsity_ratio_per_op (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.max_sparsity_ratio_per_op", false]], "max_sparsity_ratio_per_op (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.max_sparsity_ratio_per_op", false]], "max_sparsity_ratio_per_op (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.max_sparsity_ratio_per_op", false]], "maxpooloperator (class in neural_compressor.adaptor.ox_utils.operators.maxpool)": [[19, "neural_compressor.adaptor.ox_utils.operators.maxpool.MaxPoolOperator", false]], "mergeduplicatedqdqoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq)": [[93, "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq.MergeDuplicatedQDQOptimizer", false]], "mergeduplicatedqdqoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq)": [[358, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq.MergeDuplicatedQDQOptimizer", false]], "metainfochangingmemopoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer)": [[81, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer.MetaInfoChangingMemOpOptimizer", false]], "metainfochangingmemopoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer)": [[352, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer.MetaInfoChangingMemOpOptimizer", false]], "metric (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.Metric", false]], "metric_max_over_ground_truths() (in module neural_compressor.metric.evaluate_squad)": [[231, "neural_compressor.metric.evaluate_squad.metric_max_over_ground_truths", false]], "metric_max_over_ground_truths() (in module neural_compressor.metric.f1)": [[232, "neural_compressor.metric.f1.metric_max_over_ground_truths", false]], "metric_registry() (in module neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.metric_registry", false]], "metrics (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.METRICS", false]], "metrics (neural_compressor.metric.metric.metrics attribute)": [[234, "neural_compressor.metric.metric.METRICS.metrics", false]], "metrics (neural_compressor.metric.metric.mxnetmetrics attribute)": [[234, "neural_compressor.metric.metric.MXNetMetrics.metrics", false]], "metrics (neural_compressor.metric.metric.onnxrtitmetrics attribute)": [[234, "neural_compressor.metric.metric.ONNXRTITMetrics.metrics", false]], "metrics (neural_compressor.metric.metric.onnxrtqlmetrics attribute)": [[234, "neural_compressor.metric.metric.ONNXRTQLMetrics.metrics", false]], "metrics (neural_compressor.metric.metric.pytorchmetrics attribute)": [[234, "neural_compressor.metric.metric.PyTorchMetrics.metrics", false]], "metrics (neural_compressor.metric.metric.tensorflowmetrics attribute)": [[234, "neural_compressor.metric.metric.TensorflowMetrics.metrics", false]], "mha_compressions (neural_compressor.compression.pruner.pruners.mha.pythonmultiheadattentionpruner attribute)": [[184, "neural_compressor.compression.pruner.pruners.mha.PythonMultiheadAttentionPruner.mha_compressions", false]], "mha_scores (neural_compressor.compression.pruner.pruners.mha.pythonmultiheadattentionpruner attribute)": [[184, "neural_compressor.compression.pruner.pruners.mha.PythonMultiheadAttentionPruner.mha_scores", false]], "min_sparsity_ratio_per_op (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.min_sparsity_ratio_per_op", false]], "min_sparsity_ratio_per_op (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.min_sparsity_ratio_per_op", false]], "min_sparsity_ratio_per_op (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.min_sparsity_ratio_per_op", false]], "minmaxcalibrator (class in neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.MinMaxCalibrator", false]], "miou (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.mIOU", false]], "mixed_precision_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.mixed_precision_entry", false]], "mixedprecisionconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.MixedPrecisionConfig", false]], "mixedprecisionconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.MixedPrecisionConfig", false]], "mnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MNIST", false]], "mode (class in neural_compressor.common.utils.constants)": [[157, "neural_compressor.common.utils.constants.Mode", false]], "mode (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.MODE", false]], "model (class in neural_compressor.model.model)": [[239, "neural_compressor.model.model.Model", false]], "model (class in neural_compressor.tensorflow.utils.model)": [[389, "neural_compressor.tensorflow.utils.model.Model", false]], "model (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcher.model", false]], "model (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearchertf attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcherTF.model", false]], "model (neural_compressor.compression.pruner.model_slim.pattern_analyzer.jitbasicsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher.model", false]], "model (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.model", false]], "model (neural_compressor.compression.pruner.model_slim.pattern_analyzer.recipesearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.RecipeSearcher.model", false]], "model (neural_compressor.compression.pruner.model_slim.pattern_analyzer.selfmhasearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.SelfMHASearcher.model", false]], "model (neural_compressor.compression.pruner.pruning.basepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasePruning.model", false]], "model (neural_compressor.compression.pruner.pruning.basicpruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasicPruning.model", false]], "model (neural_compressor.compression.pruner.pruning.retrainfreepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.RetrainFreePruning.model", false]], "model_forward() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.model_forward", false]], "model_forward() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.model_forward", false]], "model_forward_per_sample() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.model_forward_per_sample", false]], "model_level (neural_compressor.common.tuning_param.paramlevel attribute)": [[156, "neural_compressor.common.tuning_param.ParamLevel.MODEL_LEVEL", false]], "model_slim() (in module neural_compressor.compression.pruner.model_slim.auto_slim)": [[171, "neural_compressor.compression.pruner.model_slim.auto_slim.model_slim", false]], "model_slim_ffn2() (in module neural_compressor.compression.pruner.model_slim.auto_slim)": [[171, "neural_compressor.compression.pruner.model_slim.auto_slim.model_slim_ffn2", false]], "model_slim_mha() (in module neural_compressor.compression.pruner.model_slim.auto_slim)": [[171, "neural_compressor.compression.pruner.model_slim.auto_slim.model_slim_mha", false]], "modelsize (class in neural_compressor.objective)": [[245, "neural_compressor.objective.ModelSize", false]], "modelwisetuningsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.ModelWiseTuningSampler", false]], "module": [[0, "module-neural_compressor.adaptor.mxnet_utils", false], [1, "module-neural_compressor.adaptor.mxnet_utils.util", false], [2, "module-neural_compressor.adaptor.ox_utils.calibration", false], [3, "module-neural_compressor.adaptor.ox_utils.calibrator", false], [4, "module-neural_compressor.adaptor.ox_utils", false], [5, "module-neural_compressor.adaptor.ox_utils.operators.activation", false], [6, "module-neural_compressor.adaptor.ox_utils.operators.argmax", false], [7, "module-neural_compressor.adaptor.ox_utils.operators.attention", false], [8, "module-neural_compressor.adaptor.ox_utils.operators.binary_op", false], [9, "module-neural_compressor.adaptor.ox_utils.operators.concat", false], [10, "module-neural_compressor.adaptor.ox_utils.operators.conv", false], [11, "module-neural_compressor.adaptor.ox_utils.operators.direct_q8", false], [12, "module-neural_compressor.adaptor.ox_utils.operators.embed_layernorm", false], [13, "module-neural_compressor.adaptor.ox_utils.operators.gather", false], [14, "module-neural_compressor.adaptor.ox_utils.operators.gavgpool", false], [15, "module-neural_compressor.adaptor.ox_utils.operators.gemm", false], [16, "module-neural_compressor.adaptor.ox_utils.operators", false], [17, "module-neural_compressor.adaptor.ox_utils.operators.lstm", false], [18, "module-neural_compressor.adaptor.ox_utils.operators.matmul", false], [19, "module-neural_compressor.adaptor.ox_utils.operators.maxpool", false], [20, "module-neural_compressor.adaptor.ox_utils.operators.norm", false], [21, "module-neural_compressor.adaptor.ox_utils.operators.ops", false], [22, "module-neural_compressor.adaptor.ox_utils.operators.pad", false], [23, "module-neural_compressor.adaptor.ox_utils.operators.pooling", false], [24, "module-neural_compressor.adaptor.ox_utils.operators.reduce", false], [25, "module-neural_compressor.adaptor.ox_utils.operators.resize", false], [26, "module-neural_compressor.adaptor.ox_utils.operators.split", false], [27, "module-neural_compressor.adaptor.ox_utils.operators.unary_op", false], [28, "module-neural_compressor.adaptor.ox_utils.quantizer", false], [29, "module-neural_compressor.adaptor.ox_utils.smooth_quant", false], [30, "module-neural_compressor.adaptor.ox_utils.util", false], [31, "module-neural_compressor.adaptor.ox_utils.weight_only", false], [32, "module-neural_compressor.adaptor.tensorflow", false], [33, "module-neural_compressor.adaptor.tf_utils.graph_converter", false], [34, "module-neural_compressor.adaptor.tf_utils.graph_converter_without_calib", false], [35, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert", false], [36, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer", false], [37, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16", false], [38, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd", false], [39, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout", false], [40, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu", false], [41, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random", false], [42, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const", false], [43, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction", false], [44, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd", false], [45, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer", false], [46, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape", false], [47, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm", false], [48, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant", false], [49, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add", false], [50, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul", false], [51, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math", false], [52, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn", false], [53, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in", false], [54, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu", false], [55, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm", false], [56, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv", false], [57, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv", false], [58, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose", false], [59, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer", false], [60, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass", false], [61, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic", false], [62, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node", false], [63, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu", false], [64, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize", false], [65, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes", false], [66, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm", false], [67, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input", false], [68, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes", false], [69, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes", false], [70, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer", false], [71, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base", false], [72, "module-neural_compressor.adaptor.tf_utils.graph_rewriter", false], [73, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant", false], [74, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value", false], [75, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib", false], [76, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize", false], [77, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize", false], [78, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize", false], [79, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize", false], [80, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8", false], [81, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer", false], [82, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter", false], [83, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse", false], [84, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert", false], [85, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation", false], [86, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx", false], [87, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph", false], [88, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node", false], [89, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema", false], [90, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils", false], [91, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq", false], [92, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern", false], [93, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq", false], [94, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern", false], [95, "module-neural_compressor.adaptor.tf_utils.graph_util", false], [96, "module-neural_compressor.adaptor.tf_utils", false], [97, "module-neural_compressor.adaptor.tf_utils.quantize_graph", false], [98, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize", false], [99, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat", false], [100, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config", false], [101, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper", false], [102, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers", false], [103, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer", false], [104, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add", false], [105, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base", false], [106, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn", false], [107, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper", false], [108, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn", false], [109, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2", false], [110, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv", false], [111, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv", false], [112, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in", false], [113, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul", false], [114, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling", false], [115, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq", false], [116, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq", false], [117, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base", false], [118, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn", false], [119, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2", false], [120, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv", false], [121, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu", false], [122, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul", false], [123, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling", false], [124, "module-neural_compressor.adaptor.tf_utils.quantize_graph_common", false], [125, "module-neural_compressor.adaptor.tf_utils.smooth_quant_calibration", false], [126, "module-neural_compressor.adaptor.tf_utils.smooth_quant_scaler", false], [127, "module-neural_compressor.adaptor.tf_utils.tf2onnx_converter", false], [128, "module-neural_compressor.adaptor.tf_utils.transform_graph.bias_correction", false], [129, "module-neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base", false], [130, "module-neural_compressor.adaptor.tf_utils.transform_graph", false], [131, "module-neural_compressor.adaptor.tf_utils.transform_graph.insert_logging", false], [132, "module-neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat", false], [133, "module-neural_compressor.adaptor.tf_utils.util", false], [134, "module-neural_compressor.adaptor.torch_utils.bf16_convert", false], [135, "module-neural_compressor.adaptor.torch_utils.hawq_metric", false], [136, "module-neural_compressor.adaptor.torch_utils", false], [137, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant", false], [138, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle", false], [139, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize", false], [140, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load", false], [141, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.utils", false], [142, "module-neural_compressor.adaptor.torch_utils.model_wrapper", false], [143, "module-neural_compressor.adaptor.torch_utils.pattern_detector", false], [144, "module-neural_compressor.adaptor.torch_utils.symbolic_trace", false], [145, "module-neural_compressor.adaptor.torch_utils.util", false], [146, "module-neural_compressor.algorithm.algorithm", false], [147, "module-neural_compressor.algorithm.fast_bias_correction", false], [148, "module-neural_compressor.algorithm", false], [149, "module-neural_compressor.algorithm.smooth_quant", false], [150, "module-neural_compressor.algorithm.weight_correction", false], [151, "module-neural_compressor.benchmark", false], [152, "module-neural_compressor.common.base_config", false], [153, "module-neural_compressor.common.base_tuning", false], [154, "module-neural_compressor.common.benchmark", false], [155, "module-neural_compressor.common", false], [156, "module-neural_compressor.common.tuning_param", false], [157, "module-neural_compressor.common.utils.constants", false], [158, "module-neural_compressor.common.utils", false], [159, "module-neural_compressor.common.utils.logger", false], [160, "module-neural_compressor.common.utils.save_load", false], [161, "module-neural_compressor.common.utils.utility", false], [162, "module-neural_compressor.compression.callbacks", false], [163, "module-neural_compressor.compression.distillation.criterions", false], [164, "module-neural_compressor.compression.distillation", false], [165, "module-neural_compressor.compression.distillation.optimizers", false], [166, "module-neural_compressor.compression.distillation.utility", false], [167, "module-neural_compressor.compression.hpo", false], [168, "module-neural_compressor.compression.hpo.sa_optimizer", false], [169, "module-neural_compressor.compression.pruner.criteria", false], [170, "module-neural_compressor.compression.pruner", false], [171, "module-neural_compressor.compression.pruner.model_slim.auto_slim", false], [172, "module-neural_compressor.compression.pruner.model_slim", false], [173, "module-neural_compressor.compression.pruner.model_slim.pattern_analyzer", false], [174, "module-neural_compressor.compression.pruner.model_slim.weight_slim", false], [175, "module-neural_compressor.compression.pruner.patterns.base", false], [176, "module-neural_compressor.compression.pruner.patterns", false], [177, "module-neural_compressor.compression.pruner.patterns.mha", false], [178, "module-neural_compressor.compression.pruner.patterns.ninm", false], [179, "module-neural_compressor.compression.pruner.patterns.nxm", false], [180, "module-neural_compressor.compression.pruner.pruners.base", false], [181, "module-neural_compressor.compression.pruner.pruners.basic", false], [182, "module-neural_compressor.compression.pruner.pruners.block_mask", false], [183, "module-neural_compressor.compression.pruner.pruners", false], [184, "module-neural_compressor.compression.pruner.pruners.mha", false], [185, "module-neural_compressor.compression.pruner.pruners.pattern_lock", false], [186, "module-neural_compressor.compression.pruner.pruners.progressive", false], [187, "module-neural_compressor.compression.pruner.pruners.retrain_free", false], [188, "module-neural_compressor.compression.pruner.pruning", false], [189, "module-neural_compressor.compression.pruner.regs", false], [190, "module-neural_compressor.compression.pruner.schedulers", false], [191, "module-neural_compressor.compression.pruner.tf_criteria", false], [192, "module-neural_compressor.compression.pruner.utils", false], [193, "module-neural_compressor.compression.pruner.wanda", false], [194, "module-neural_compressor.compression.pruner.wanda.utils", false], [195, "module-neural_compressor.config", false], [196, "module-neural_compressor.contrib", false], [197, "module-neural_compressor.contrib.strategy", false], [198, "module-neural_compressor.contrib.strategy.sigopt", false], [199, "module-neural_compressor.contrib.strategy.tpe", false], [200, "module-neural_compressor.data.dataloaders.base_dataloader", false], [201, "module-neural_compressor.data.dataloaders.dataloader", false], [202, "module-neural_compressor.data.dataloaders.default_dataloader", false], [203, "module-neural_compressor.data.dataloaders.fetcher", false], [204, "module-neural_compressor.data.dataloaders.mxnet_dataloader", false], [205, "module-neural_compressor.data.dataloaders.onnxrt_dataloader", false], [206, "module-neural_compressor.data.dataloaders.pytorch_dataloader", false], [207, "module-neural_compressor.data.dataloaders.sampler", false], [208, "module-neural_compressor.data.dataloaders.tensorflow_dataloader", false], [209, "module-neural_compressor.data.datasets.bert_dataset", false], [210, "module-neural_compressor.data.datasets.coco_dataset", false], [211, "module-neural_compressor.data.datasets.dataset", false], [212, "module-neural_compressor.data.datasets.dummy_dataset", false], [213, "module-neural_compressor.data.datasets.dummy_dataset_v2", false], [214, "module-neural_compressor.data.datasets.imagenet_dataset", false], [215, "module-neural_compressor.data.datasets", false], [216, "module-neural_compressor.data.datasets.style_transfer_dataset", false], [217, "module-neural_compressor.data.filters.coco_filter", false], [218, "module-neural_compressor.data.filters.filter", false], [219, "module-neural_compressor.data.filters", false], [220, "module-neural_compressor.data", false], [221, "module-neural_compressor.data.transforms.imagenet_transform", false], [222, "module-neural_compressor.data.transforms", false], [223, "module-neural_compressor.data.transforms.postprocess", false], [224, "module-neural_compressor.data.transforms.tokenization", false], [225, "module-neural_compressor.data.transforms.transform", false], [226, "module-neural_compressor", false], [227, "module-neural_compressor.metric.bleu", false], [228, "module-neural_compressor.metric.bleu_util", false], [229, "module-neural_compressor.metric.coco_label_map", false], [230, "module-neural_compressor.metric.coco_tools", false], [231, "module-neural_compressor.metric.evaluate_squad", false], [232, "module-neural_compressor.metric.f1", false], [233, "module-neural_compressor.metric", false], [234, "module-neural_compressor.metric.metric", false], [235, "module-neural_compressor.mix_precision", false], [236, "module-neural_compressor.model.base_model", false], [237, "module-neural_compressor.model", false], [238, "module-neural_compressor.model.keras_model", false], [239, "module-neural_compressor.model.model", false], [240, "module-neural_compressor.model.mxnet_model", false], [241, "module-neural_compressor.model.nets_factory", false], [242, "module-neural_compressor.model.onnx_model", false], [243, "module-neural_compressor.model.tensorflow_model", false], [244, "module-neural_compressor.model.torch_model", false], [245, "module-neural_compressor.objective", false], [246, "module-neural_compressor.profiling", false], [247, "module-neural_compressor.profiling.parser.factory", false], [248, "module-neural_compressor.profiling.parser.onnx_parser.factory", false], [249, "module-neural_compressor.profiling.parser.onnx_parser.parser", false], [250, "module-neural_compressor.profiling.parser.parser", false], [251, "module-neural_compressor.profiling.parser.result", false], [252, "module-neural_compressor.profiling.parser.tensorflow_parser.factory", false], [253, "module-neural_compressor.profiling.parser.tensorflow_parser.parser", false], [254, "module-neural_compressor.profiling.profiler.factory", false], [255, "module-neural_compressor.profiling.profiler.onnxrt_profiler.factory", false], [256, "module-neural_compressor.profiling.profiler.onnxrt_profiler.profiler", false], [257, "module-neural_compressor.profiling.profiler.onnxrt_profiler.utils", false], [258, "module-neural_compressor.profiling.profiler.profiler", false], [259, "module-neural_compressor.profiling.profiler.tensorflow_profiler.factory", false], [260, "module-neural_compressor.profiling.profiler.tensorflow_profiler.profiler", false], [261, "module-neural_compressor.profiling.profiler.tensorflow_profiler.utils", false], [262, "module-neural_compressor.quantization", false], [263, "module-neural_compressor.strategy.auto", false], [264, "module-neural_compressor.strategy.auto_mixed_precision", false], [265, "module-neural_compressor.strategy.basic", false], [266, "module-neural_compressor.strategy.bayesian", false], [267, "module-neural_compressor.strategy.conservative", false], [268, "module-neural_compressor.strategy.exhaustive", false], [269, "module-neural_compressor.strategy.hawq_v2", false], [270, "module-neural_compressor.strategy", false], [271, "module-neural_compressor.strategy.mse", false], [272, "module-neural_compressor.strategy.mse_v2", false], [273, "module-neural_compressor.strategy.random", false], [274, "module-neural_compressor.strategy.strategy", false], [275, "module-neural_compressor.strategy.utils.constant", false], [276, "module-neural_compressor.strategy.utils", false], [277, "module-neural_compressor.strategy.utils.tuning_sampler", false], [278, "module-neural_compressor.strategy.utils.tuning_space", false], [279, "module-neural_compressor.strategy.utils.tuning_structs", false], [280, "module-neural_compressor.strategy.utils.utility", false], [281, "module-neural_compressor.template.api_doc_example", false], [282, "module-neural_compressor.tensorflow.algorithms", false], [283, "module-neural_compressor.tensorflow.algorithms.smoother.calibration", false], [284, "module-neural_compressor.tensorflow.algorithms.smoother.core", false], [285, "module-neural_compressor.tensorflow.algorithms.smoother", false], [286, "module-neural_compressor.tensorflow.algorithms.smoother.scaler", false], [287, "module-neural_compressor.tensorflow.algorithms.static_quant", false], [288, "module-neural_compressor.tensorflow.algorithms.static_quant.keras", false], [289, "module-neural_compressor.tensorflow.algorithms.static_quant.tensorflow", false], [290, "module-neural_compressor.tensorflow", false], [291, "module-neural_compressor.tensorflow.keras", false], [292, "module-neural_compressor.tensorflow.keras.layers.conv2d", false], [293, "module-neural_compressor.tensorflow.keras.layers.dense", false], [294, "module-neural_compressor.tensorflow.keras.layers.depthwise_conv2d", false], [295, "module-neural_compressor.tensorflow.keras.layers", false], [296, "module-neural_compressor.tensorflow.keras.layers.layer_initializer", false], [297, "module-neural_compressor.tensorflow.keras.layers.pool2d", false], [298, "module-neural_compressor.tensorflow.keras.layers.separable_conv2d", false], [299, "module-neural_compressor.tensorflow.keras.quantization.config", false], [300, "module-neural_compressor.tensorflow.keras.quantization", false], [301, "module-neural_compressor.tensorflow.quantization.algorithm_entry", false], [302, "module-neural_compressor.tensorflow.quantization.autotune", false], [303, "module-neural_compressor.tensorflow.quantization.config", false], [304, "module-neural_compressor.tensorflow.quantization", false], [305, "module-neural_compressor.tensorflow.quantization.quantize", false], [306, "module-neural_compressor.tensorflow.quantization.utils.graph_converter", false], [307, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert", false], [308, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer", false], [309, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16", false], [310, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd", false], [311, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout", false], [312, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu", false], [313, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random", false], [314, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const", false], [315, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction", false], [316, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd", false], [317, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer", false], [318, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape", false], [319, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm", false], [320, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant", false], [321, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add", false], [322, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul", false], [323, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math", false], [324, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn", false], [325, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in", false], [326, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu", false], [327, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm", false], [328, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv", false], [329, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv", false], [330, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose", false], [331, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer", false], [332, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass", false], [333, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic", false], [334, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node", false], [335, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu", false], [336, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize", false], [337, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes", false], [338, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm", false], [339, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input", false], [340, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes", false], [341, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes", false], [342, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer", false], [343, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base", false], [344, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter", false], [345, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant", false], [346, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value", false], [347, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize", false], [348, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize", false], [349, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize", false], [350, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize", false], [351, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8", false], [352, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer", false], [353, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter", false], [354, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse", false], [355, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation", false], [356, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq", false], [357, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern", false], [358, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq", false], [359, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern", false], [360, "module-neural_compressor.tensorflow.quantization.utils.graph_util", false], [361, "module-neural_compressor.tensorflow.quantization.utils", false], [362, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph", false], [363, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn", false], [364, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2", false], [365, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv", false], [366, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv", false], [367, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in", false], [368, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul", false], [369, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling", false], [370, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq", false], [371, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq", false], [372, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base", false], [373, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn", false], [374, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2", false], [375, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv", false], [376, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu", false], [377, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul", false], [378, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling", false], [379, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph_common", false], [380, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction", false], [381, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base", false], [382, "module-neural_compressor.tensorflow.quantization.utils.transform_graph", false], [383, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging", false], [384, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat", false], [385, "module-neural_compressor.tensorflow.quantization.utils.utility", false], [386, "module-neural_compressor.tensorflow.utils.constants", false], [387, "module-neural_compressor.tensorflow.utils.data", false], [388, "module-neural_compressor.tensorflow.utils", false], [389, "module-neural_compressor.tensorflow.utils.model", false], [390, "module-neural_compressor.tensorflow.utils.model_wrappers", false], [391, "module-neural_compressor.tensorflow.utils.utility", false], [392, "module-neural_compressor.torch.algorithms.base_algorithm", false], [393, "module-neural_compressor.torch.algorithms.fp8_quant.utils.logger", false], [394, "module-neural_compressor.torch.algorithms", false], [395, "module-neural_compressor.torch.algorithms.layer_wise", false], [396, "module-neural_compressor.torch.algorithms.layer_wise.load", false], [397, "module-neural_compressor.torch.algorithms.layer_wise.modified_pickle", false], [398, "module-neural_compressor.torch.algorithms.layer_wise.utils", false], [399, "module-neural_compressor.torch.algorithms.mixed_precision.half_precision_convert", false], [400, "module-neural_compressor.torch.algorithms.mixed_precision", false], [401, "module-neural_compressor.torch.algorithms.mixed_precision.module_wrappers", false], [402, "module-neural_compressor.torch.algorithms.mx_quant", false], [403, "module-neural_compressor.torch.algorithms.mx_quant.mx", false], [404, "module-neural_compressor.torch.algorithms.mx_quant.utils", false], [405, "module-neural_compressor.torch.algorithms.pt2e_quant.core", false], [406, "module-neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter", false], [407, "module-neural_compressor.torch.algorithms.pt2e_quant", false], [408, "module-neural_compressor.torch.algorithms.pt2e_quant.save_load", false], [409, "module-neural_compressor.torch.algorithms.pt2e_quant.utility", false], [410, "module-neural_compressor.torch.algorithms.smooth_quant", false], [411, "module-neural_compressor.torch.algorithms.smooth_quant.save_load", false], [412, "module-neural_compressor.torch.algorithms.smooth_quant.smooth_quant", false], [413, "module-neural_compressor.torch.algorithms.smooth_quant.utility", false], [414, "module-neural_compressor.torch.algorithms.static_quant", false], [415, "module-neural_compressor.torch.algorithms.static_quant.save_load", false], [416, "module-neural_compressor.torch.algorithms.static_quant.static_quant", false], [417, "module-neural_compressor.torch.algorithms.static_quant.utility", false], [418, "module-neural_compressor.torch.algorithms.weight_only.autoround", false], [419, "module-neural_compressor.torch.algorithms.weight_only.awq", false], [420, "module-neural_compressor.torch.algorithms.weight_only.gptq", false], [421, "module-neural_compressor.torch.algorithms.weight_only.hqq.bitpack", false], [422, "module-neural_compressor.torch.algorithms.weight_only.hqq.config", false], [423, "module-neural_compressor.torch.algorithms.weight_only.hqq.core", false], [424, "module-neural_compressor.torch.algorithms.weight_only.hqq", false], [425, "module-neural_compressor.torch.algorithms.weight_only.hqq.optimizer", false], [426, "module-neural_compressor.torch.algorithms.weight_only.hqq.qtensor", false], [427, "module-neural_compressor.torch.algorithms.weight_only.hqq.quantizer", false], [428, "module-neural_compressor.torch.algorithms.weight_only", false], [429, "module-neural_compressor.torch.algorithms.weight_only.modules", false], [430, "module-neural_compressor.torch.algorithms.weight_only.rtn", false], [431, "module-neural_compressor.torch.algorithms.weight_only.save_load", false], [432, "module-neural_compressor.torch.algorithms.weight_only.teq", false], [433, "module-neural_compressor.torch.algorithms.weight_only.utility", false], [434, "module-neural_compressor.torch.export", false], [435, "module-neural_compressor.torch.export.pt2e_export", false], [436, "module-neural_compressor.torch", false], [437, "module-neural_compressor.torch.quantization.algorithm_entry", false], [438, "module-neural_compressor.torch.quantization.autotune", false], [439, "module-neural_compressor.torch.quantization.config", false], [440, "module-neural_compressor.torch.quantization", false], [441, "module-neural_compressor.torch.quantization.load_entry", false], [442, "module-neural_compressor.torch.quantization.quantize", false], [443, "module-neural_compressor.torch.utils.auto_accelerator", false], [444, "module-neural_compressor.torch.utils.constants", false], [445, "module-neural_compressor.torch.utils.environ", false], [446, "module-neural_compressor.torch.utils", false], [447, "module-neural_compressor.torch.utils.utility", false], [448, "module-neural_compressor.training", false], [449, "module-neural_compressor.transformers.quantization.utils", false], [450, "module-neural_compressor.transformers.utils", false], [451, "module-neural_compressor.transformers.utils.quantization_config", false], [452, "module-neural_compressor.utils.collect_layer_histogram", false], [453, "module-neural_compressor.utils.constant", false], [454, "module-neural_compressor.utils.create_obj_from_config", false], [455, "module-neural_compressor.utils.export", false], [456, "module-neural_compressor.utils.export.qlinear2qdq", false], [457, "module-neural_compressor.utils.export.tf2onnx", false], [458, "module-neural_compressor.utils.export.torch2onnx", false], [459, "module-neural_compressor.utils", false], [460, "module-neural_compressor.utils.kl_divergence", false], [461, "module-neural_compressor.utils.load_huggingface", false], [462, "module-neural_compressor.utils.logger", false], [463, "module-neural_compressor.utils.options", false], [464, "module-neural_compressor.utils.pytorch", false], [465, "module-neural_compressor.utils.utility", false], [466, "module-neural_compressor.utils.weights_details", false], [467, "module-neural_compressor.version", false]], "module_debug_level1 (in module neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.module_debug_level1", false]], "modules (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.modules", false]], "modules (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.modules", false]], "modules (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.modules", false]], "modules (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.modules", false]], "modules (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.modules", false]], "modules (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.modules", false]], "move_input_device() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.move_input_device", false]], "move_input_to_device() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.move_input_to_device", false]], "move_input_to_device() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.move_input_to_device", false]], "movesqueezeafterreluoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu)": [[63, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu.MoveSqueezeAfterReluOptimizer", false]], "movesqueezeafterreluoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu)": [[335, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu.MoveSqueezeAfterReluOptimizer", false]], "mse (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.MSE", false]], "mse (neural_compressor.metric.metric.rmse attribute)": [[234, "neural_compressor.metric.metric.RMSE.mse", false]], "mse_metric_gap() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.mse_metric_gap", false]], "mse_v2tunestrategy (class in neural_compressor.strategy.mse_v2)": [[272, "neural_compressor.strategy.mse_v2.MSE_V2TuneStrategy", false]], "msetunestrategy (class in neural_compressor.strategy.mse)": [[271, "neural_compressor.strategy.mse.MSETuneStrategy", false]], "mullinear (class in neural_compressor.adaptor.torch_utils.model_wrapper)": [[142, "neural_compressor.adaptor.torch_utils.model_wrapper.MulLinear", false]], "mullinear (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.MulLinear", false]], "multiobjective (class in neural_compressor.objective)": [[245, "neural_compressor.objective.MultiObjective", false]], "mx_quant_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.mx_quant_entry", false]], "mxlinear (class in neural_compressor.torch.algorithms.mx_quant.mx)": [[403, "neural_compressor.torch.algorithms.mx_quant.mx.MXLinear", false]], "mxnet (class in neural_compressor.config)": [[195, "neural_compressor.config.MXNet", false]], "mxnetcifar10 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MXNetCIFAR10", false]], "mxnetcifar100 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MXNetCIFAR100", false]], "mxnetcropresizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.MXNetCropResizeTransform", false]], "mxnetcroptoboundingbox (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.MXNetCropToBoundingBox", false]], "mxnetdataloader (class in neural_compressor.data.dataloaders.mxnet_dataloader)": [[204, "neural_compressor.data.dataloaders.mxnet_dataloader.MXNetDataLoader", false]], "mxnetdatasets (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MXNetDatasets", false]], "mxnetfashionmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MXNetFashionMNIST", false]], "mxnetfilters (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.MXNetFilters", false]], "mxnetimagefolder (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MXNetImageFolder", false]], "mxnetimagenetraw (class in neural_compressor.data.datasets.imagenet_dataset)": [[214, "neural_compressor.data.datasets.imagenet_dataset.MXNetImagenetRaw", false]], "mxnetmetrics (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.MXNetMetrics", false]], "mxnetmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MXNetMNIST", false]], "mxnetmodel (class in neural_compressor.model.mxnet_model)": [[240, "neural_compressor.model.mxnet_model.MXNetModel", false]], "mxnetnormalizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.MXNetNormalizeTransform", false]], "mxnettransforms (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.MXNetTransforms", false]], "mxnettranspose (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.MXNetTranspose", false]], "mxquantconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.MXQuantConfig", false]], "mxquantizer (class in neural_compressor.torch.algorithms.mx_quant.mx)": [[403, "neural_compressor.torch.algorithms.mx_quant.mx.MXQuantizer", false]], "n (neural_compressor.compression.pruner.patterns.mha.patternmha attribute)": [[177, "neural_compressor.compression.pruner.patterns.mha.PatternMHA.N", false]], "n (neural_compressor.compression.pruner.patterns.ninm.pytorchpatternninm attribute)": [[178, "neural_compressor.compression.pruner.patterns.ninm.PytorchPatternNInM.N", false]], "name (neural_compressor.common.base_config.baseconfig attribute)": [[152, "neural_compressor.common.base_config.BaseConfig.name", false]], "namecollector (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.NameCollector", false]], "nasconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.NASConfig", false]], "nbits (neural_compressor.torch.algorithms.weight_only.hqq.qtensor.qtensormetainfo attribute)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo.nbits", false]], "ndarray_to_device() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.ndarray_to_device", false]], "need_apply() (in module neural_compressor.tensorflow.quantization.quantize)": [[305, "neural_compressor.tensorflow.quantization.quantize.need_apply", false]], "need_apply() (in module neural_compressor.torch.quantization.quantize)": [[442, "neural_compressor.torch.quantization.quantize.need_apply", false]], "neural_compressor": [[226, "module-neural_compressor", false]], "neural_compressor.adaptor.mxnet_utils": [[0, "module-neural_compressor.adaptor.mxnet_utils", false]], "neural_compressor.adaptor.mxnet_utils.util": [[1, "module-neural_compressor.adaptor.mxnet_utils.util", false]], "neural_compressor.adaptor.ox_utils": [[4, "module-neural_compressor.adaptor.ox_utils", false]], "neural_compressor.adaptor.ox_utils.calibration": [[2, "module-neural_compressor.adaptor.ox_utils.calibration", false]], "neural_compressor.adaptor.ox_utils.calibrator": [[3, "module-neural_compressor.adaptor.ox_utils.calibrator", false]], "neural_compressor.adaptor.ox_utils.operators": [[16, "module-neural_compressor.adaptor.ox_utils.operators", false]], "neural_compressor.adaptor.ox_utils.operators.activation": [[5, "module-neural_compressor.adaptor.ox_utils.operators.activation", false]], "neural_compressor.adaptor.ox_utils.operators.argmax": [[6, "module-neural_compressor.adaptor.ox_utils.operators.argmax", false]], "neural_compressor.adaptor.ox_utils.operators.attention": [[7, "module-neural_compressor.adaptor.ox_utils.operators.attention", false]], "neural_compressor.adaptor.ox_utils.operators.binary_op": [[8, "module-neural_compressor.adaptor.ox_utils.operators.binary_op", false]], "neural_compressor.adaptor.ox_utils.operators.concat": [[9, "module-neural_compressor.adaptor.ox_utils.operators.concat", false]], "neural_compressor.adaptor.ox_utils.operators.conv": [[10, "module-neural_compressor.adaptor.ox_utils.operators.conv", false]], "neural_compressor.adaptor.ox_utils.operators.direct_q8": [[11, "module-neural_compressor.adaptor.ox_utils.operators.direct_q8", false]], "neural_compressor.adaptor.ox_utils.operators.embed_layernorm": [[12, "module-neural_compressor.adaptor.ox_utils.operators.embed_layernorm", false]], "neural_compressor.adaptor.ox_utils.operators.gather": [[13, "module-neural_compressor.adaptor.ox_utils.operators.gather", false]], "neural_compressor.adaptor.ox_utils.operators.gavgpool": [[14, "module-neural_compressor.adaptor.ox_utils.operators.gavgpool", false]], "neural_compressor.adaptor.ox_utils.operators.gemm": [[15, "module-neural_compressor.adaptor.ox_utils.operators.gemm", false]], "neural_compressor.adaptor.ox_utils.operators.lstm": [[17, "module-neural_compressor.adaptor.ox_utils.operators.lstm", false]], "neural_compressor.adaptor.ox_utils.operators.matmul": [[18, "module-neural_compressor.adaptor.ox_utils.operators.matmul", false]], "neural_compressor.adaptor.ox_utils.operators.maxpool": [[19, "module-neural_compressor.adaptor.ox_utils.operators.maxpool", false]], "neural_compressor.adaptor.ox_utils.operators.norm": [[20, "module-neural_compressor.adaptor.ox_utils.operators.norm", false]], "neural_compressor.adaptor.ox_utils.operators.ops": [[21, "module-neural_compressor.adaptor.ox_utils.operators.ops", false]], "neural_compressor.adaptor.ox_utils.operators.pad": [[22, "module-neural_compressor.adaptor.ox_utils.operators.pad", false]], "neural_compressor.adaptor.ox_utils.operators.pooling": [[23, "module-neural_compressor.adaptor.ox_utils.operators.pooling", false]], "neural_compressor.adaptor.ox_utils.operators.reduce": [[24, "module-neural_compressor.adaptor.ox_utils.operators.reduce", false]], "neural_compressor.adaptor.ox_utils.operators.resize": [[25, "module-neural_compressor.adaptor.ox_utils.operators.resize", false]], "neural_compressor.adaptor.ox_utils.operators.split": [[26, "module-neural_compressor.adaptor.ox_utils.operators.split", false]], "neural_compressor.adaptor.ox_utils.operators.unary_op": [[27, "module-neural_compressor.adaptor.ox_utils.operators.unary_op", false]], "neural_compressor.adaptor.ox_utils.quantizer": [[28, "module-neural_compressor.adaptor.ox_utils.quantizer", false]], "neural_compressor.adaptor.ox_utils.smooth_quant": [[29, "module-neural_compressor.adaptor.ox_utils.smooth_quant", false]], "neural_compressor.adaptor.ox_utils.util": [[30, "module-neural_compressor.adaptor.ox_utils.util", false]], "neural_compressor.adaptor.ox_utils.weight_only": [[31, "module-neural_compressor.adaptor.ox_utils.weight_only", false]], "neural_compressor.adaptor.tensorflow": [[32, "module-neural_compressor.adaptor.tensorflow", false]], "neural_compressor.adaptor.tf_utils": [[96, "module-neural_compressor.adaptor.tf_utils", false]], "neural_compressor.adaptor.tf_utils.graph_converter": [[33, "module-neural_compressor.adaptor.tf_utils.graph_converter", false]], "neural_compressor.adaptor.tf_utils.graph_converter_without_calib": [[34, "module-neural_compressor.adaptor.tf_utils.graph_converter_without_calib", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter": [[72, "module-neural_compressor.adaptor.tf_utils.graph_rewriter", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16": [[37, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert": [[35, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer": [[36, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic": [[61, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd": [[38, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout": [[39, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu": [[40, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random": [[41, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const": [[42, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction": [[43, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd": [[44, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer": [[45, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape": [[46, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm": [[47, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant": [[48, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add": [[49, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul": [[50, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math": [[51, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn": [[52, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in": [[53, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu": [[54, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm": [[55, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv": [[56, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv": [[57, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose": [[58, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer": [[59, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass": [[60, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node": [[62, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu": [[63, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize": [[64, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes": [[65, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm": [[66, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input": [[67, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes": [[68, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes": [[69, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer": [[70, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base": [[71, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8": [[80, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant": [[73, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value": [[74, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib": [[75, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize": [[76, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize": [[77, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize": [[78, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize": [[79, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer": [[81, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter": [[82, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse": [[83, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert": [[84, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation": [[85, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx": [[86, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph": [[87, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node": [[88, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema": [[89, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils": [[90, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq": [[91, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern": [[92, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq": [[93, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern": [[94, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern", false]], "neural_compressor.adaptor.tf_utils.graph_util": [[95, "module-neural_compressor.adaptor.tf_utils.graph_util", false]], "neural_compressor.adaptor.tf_utils.quantize_graph": [[97, "module-neural_compressor.adaptor.tf_utils.quantize_graph", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat": [[99, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize": [[98, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config": [[100, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper": [[101, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers": [[102, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer": [[103, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add": [[104, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base": [[105, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn": [[106, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper": [[107, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq": [[115, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn": [[108, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2": [[109, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv": [[110, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv": [[111, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in": [[112, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul": [[113, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling": [[114, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq": [[116, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base": [[117, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn": [[118, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2": [[119, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv": [[120, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu": [[121, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul": [[122, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling": [[123, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling", false]], "neural_compressor.adaptor.tf_utils.quantize_graph_common": [[124, "module-neural_compressor.adaptor.tf_utils.quantize_graph_common", false]], "neural_compressor.adaptor.tf_utils.smooth_quant_calibration": [[125, "module-neural_compressor.adaptor.tf_utils.smooth_quant_calibration", false]], "neural_compressor.adaptor.tf_utils.smooth_quant_scaler": [[126, "module-neural_compressor.adaptor.tf_utils.smooth_quant_scaler", false]], "neural_compressor.adaptor.tf_utils.tf2onnx_converter": [[127, "module-neural_compressor.adaptor.tf_utils.tf2onnx_converter", false]], "neural_compressor.adaptor.tf_utils.transform_graph": [[130, "module-neural_compressor.adaptor.tf_utils.transform_graph", false]], "neural_compressor.adaptor.tf_utils.transform_graph.bias_correction": [[128, "module-neural_compressor.adaptor.tf_utils.transform_graph.bias_correction", false]], "neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base": [[129, "module-neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base", false]], "neural_compressor.adaptor.tf_utils.transform_graph.insert_logging": [[131, "module-neural_compressor.adaptor.tf_utils.transform_graph.insert_logging", false]], "neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat": [[132, "module-neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat", false]], "neural_compressor.adaptor.tf_utils.util": [[133, "module-neural_compressor.adaptor.tf_utils.util", false]], "neural_compressor.adaptor.torch_utils": [[136, "module-neural_compressor.adaptor.torch_utils", false]], "neural_compressor.adaptor.torch_utils.bf16_convert": [[134, "module-neural_compressor.adaptor.torch_utils.bf16_convert", false]], "neural_compressor.adaptor.torch_utils.hawq_metric": [[135, "module-neural_compressor.adaptor.torch_utils.hawq_metric", false]], "neural_compressor.adaptor.torch_utils.layer_wise_quant": [[137, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant", false]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle": [[138, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle", false]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize": [[139, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize", false]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load": [[140, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load", false]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils": [[141, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.utils", false]], "neural_compressor.adaptor.torch_utils.model_wrapper": [[142, "module-neural_compressor.adaptor.torch_utils.model_wrapper", false]], "neural_compressor.adaptor.torch_utils.pattern_detector": [[143, "module-neural_compressor.adaptor.torch_utils.pattern_detector", false]], "neural_compressor.adaptor.torch_utils.symbolic_trace": [[144, "module-neural_compressor.adaptor.torch_utils.symbolic_trace", false]], "neural_compressor.adaptor.torch_utils.util": [[145, "module-neural_compressor.adaptor.torch_utils.util", false]], "neural_compressor.algorithm": [[148, "module-neural_compressor.algorithm", false]], "neural_compressor.algorithm.algorithm": [[146, "module-neural_compressor.algorithm.algorithm", false]], "neural_compressor.algorithm.fast_bias_correction": [[147, "module-neural_compressor.algorithm.fast_bias_correction", false]], "neural_compressor.algorithm.smooth_quant": [[149, "module-neural_compressor.algorithm.smooth_quant", false]], "neural_compressor.algorithm.weight_correction": [[150, "module-neural_compressor.algorithm.weight_correction", false]], "neural_compressor.benchmark": [[151, "module-neural_compressor.benchmark", false]], "neural_compressor.common": [[155, "module-neural_compressor.common", false]], "neural_compressor.common.base_config": [[152, "module-neural_compressor.common.base_config", false]], "neural_compressor.common.base_tuning": [[153, "module-neural_compressor.common.base_tuning", false]], "neural_compressor.common.benchmark": [[154, "module-neural_compressor.common.benchmark", false]], "neural_compressor.common.tuning_param": [[156, "module-neural_compressor.common.tuning_param", false]], "neural_compressor.common.utils": [[158, "module-neural_compressor.common.utils", false]], "neural_compressor.common.utils.constants": [[157, "module-neural_compressor.common.utils.constants", false]], "neural_compressor.common.utils.logger": [[159, "module-neural_compressor.common.utils.logger", false]], "neural_compressor.common.utils.save_load": [[160, "module-neural_compressor.common.utils.save_load", false]], "neural_compressor.common.utils.utility": [[161, "module-neural_compressor.common.utils.utility", false]], "neural_compressor.compression.callbacks": [[162, "module-neural_compressor.compression.callbacks", false]], "neural_compressor.compression.distillation": [[164, "module-neural_compressor.compression.distillation", false]], "neural_compressor.compression.distillation.criterions": [[163, "module-neural_compressor.compression.distillation.criterions", false]], "neural_compressor.compression.distillation.optimizers": [[165, "module-neural_compressor.compression.distillation.optimizers", false]], "neural_compressor.compression.distillation.utility": [[166, "module-neural_compressor.compression.distillation.utility", false]], "neural_compressor.compression.hpo": [[167, "module-neural_compressor.compression.hpo", false]], "neural_compressor.compression.hpo.sa_optimizer": [[168, "module-neural_compressor.compression.hpo.sa_optimizer", false]], "neural_compressor.compression.pruner": [[170, "module-neural_compressor.compression.pruner", false]], "neural_compressor.compression.pruner.criteria": [[169, "module-neural_compressor.compression.pruner.criteria", false]], "neural_compressor.compression.pruner.model_slim": [[172, "module-neural_compressor.compression.pruner.model_slim", false]], "neural_compressor.compression.pruner.model_slim.auto_slim": [[171, "module-neural_compressor.compression.pruner.model_slim.auto_slim", false]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer": [[173, "module-neural_compressor.compression.pruner.model_slim.pattern_analyzer", false]], "neural_compressor.compression.pruner.model_slim.weight_slim": [[174, "module-neural_compressor.compression.pruner.model_slim.weight_slim", false]], "neural_compressor.compression.pruner.patterns": [[176, "module-neural_compressor.compression.pruner.patterns", false]], "neural_compressor.compression.pruner.patterns.base": [[175, "module-neural_compressor.compression.pruner.patterns.base", false]], "neural_compressor.compression.pruner.patterns.mha": [[177, "module-neural_compressor.compression.pruner.patterns.mha", false]], "neural_compressor.compression.pruner.patterns.ninm": [[178, "module-neural_compressor.compression.pruner.patterns.ninm", false]], "neural_compressor.compression.pruner.patterns.nxm": [[179, "module-neural_compressor.compression.pruner.patterns.nxm", false]], "neural_compressor.compression.pruner.pruners": [[183, "module-neural_compressor.compression.pruner.pruners", false]], "neural_compressor.compression.pruner.pruners.base": [[180, "module-neural_compressor.compression.pruner.pruners.base", false]], "neural_compressor.compression.pruner.pruners.basic": [[181, "module-neural_compressor.compression.pruner.pruners.basic", false]], "neural_compressor.compression.pruner.pruners.block_mask": [[182, "module-neural_compressor.compression.pruner.pruners.block_mask", false]], "neural_compressor.compression.pruner.pruners.mha": [[184, "module-neural_compressor.compression.pruner.pruners.mha", false]], "neural_compressor.compression.pruner.pruners.pattern_lock": [[185, "module-neural_compressor.compression.pruner.pruners.pattern_lock", false]], "neural_compressor.compression.pruner.pruners.progressive": [[186, "module-neural_compressor.compression.pruner.pruners.progressive", false]], "neural_compressor.compression.pruner.pruners.retrain_free": [[187, "module-neural_compressor.compression.pruner.pruners.retrain_free", false]], "neural_compressor.compression.pruner.pruning": [[188, "module-neural_compressor.compression.pruner.pruning", false]], "neural_compressor.compression.pruner.regs": [[189, "module-neural_compressor.compression.pruner.regs", false]], "neural_compressor.compression.pruner.schedulers": [[190, "module-neural_compressor.compression.pruner.schedulers", false]], "neural_compressor.compression.pruner.tf_criteria": [[191, "module-neural_compressor.compression.pruner.tf_criteria", false]], "neural_compressor.compression.pruner.utils": [[192, "module-neural_compressor.compression.pruner.utils", false]], "neural_compressor.compression.pruner.wanda": [[193, "module-neural_compressor.compression.pruner.wanda", false]], "neural_compressor.compression.pruner.wanda.utils": [[194, "module-neural_compressor.compression.pruner.wanda.utils", false]], "neural_compressor.config": [[195, "module-neural_compressor.config", false]], "neural_compressor.contrib": [[196, "module-neural_compressor.contrib", false]], "neural_compressor.contrib.strategy": [[197, "module-neural_compressor.contrib.strategy", false]], "neural_compressor.contrib.strategy.sigopt": [[198, "module-neural_compressor.contrib.strategy.sigopt", false]], "neural_compressor.contrib.strategy.tpe": [[199, "module-neural_compressor.contrib.strategy.tpe", false]], "neural_compressor.data": [[220, "module-neural_compressor.data", false]], "neural_compressor.data.dataloaders.base_dataloader": [[200, "module-neural_compressor.data.dataloaders.base_dataloader", false]], "neural_compressor.data.dataloaders.dataloader": [[201, "module-neural_compressor.data.dataloaders.dataloader", false]], "neural_compressor.data.dataloaders.default_dataloader": [[202, "module-neural_compressor.data.dataloaders.default_dataloader", false]], "neural_compressor.data.dataloaders.fetcher": [[203, "module-neural_compressor.data.dataloaders.fetcher", false]], "neural_compressor.data.dataloaders.mxnet_dataloader": [[204, "module-neural_compressor.data.dataloaders.mxnet_dataloader", false]], "neural_compressor.data.dataloaders.onnxrt_dataloader": [[205, "module-neural_compressor.data.dataloaders.onnxrt_dataloader", false]], "neural_compressor.data.dataloaders.pytorch_dataloader": [[206, "module-neural_compressor.data.dataloaders.pytorch_dataloader", false]], "neural_compressor.data.dataloaders.sampler": [[207, "module-neural_compressor.data.dataloaders.sampler", false]], "neural_compressor.data.dataloaders.tensorflow_dataloader": [[208, "module-neural_compressor.data.dataloaders.tensorflow_dataloader", false]], "neural_compressor.data.datasets": [[215, "module-neural_compressor.data.datasets", false]], "neural_compressor.data.datasets.bert_dataset": [[209, "module-neural_compressor.data.datasets.bert_dataset", false]], "neural_compressor.data.datasets.coco_dataset": [[210, "module-neural_compressor.data.datasets.coco_dataset", false]], "neural_compressor.data.datasets.dataset": [[211, "module-neural_compressor.data.datasets.dataset", false]], "neural_compressor.data.datasets.dummy_dataset": [[212, "module-neural_compressor.data.datasets.dummy_dataset", false]], "neural_compressor.data.datasets.dummy_dataset_v2": [[213, "module-neural_compressor.data.datasets.dummy_dataset_v2", false]], "neural_compressor.data.datasets.imagenet_dataset": [[214, "module-neural_compressor.data.datasets.imagenet_dataset", false]], "neural_compressor.data.datasets.style_transfer_dataset": [[216, "module-neural_compressor.data.datasets.style_transfer_dataset", false]], "neural_compressor.data.filters": [[219, "module-neural_compressor.data.filters", false]], "neural_compressor.data.filters.coco_filter": [[217, "module-neural_compressor.data.filters.coco_filter", false]], "neural_compressor.data.filters.filter": [[218, "module-neural_compressor.data.filters.filter", false]], "neural_compressor.data.transforms": [[222, "module-neural_compressor.data.transforms", false]], "neural_compressor.data.transforms.imagenet_transform": [[221, "module-neural_compressor.data.transforms.imagenet_transform", false]], "neural_compressor.data.transforms.postprocess": [[223, "module-neural_compressor.data.transforms.postprocess", false]], "neural_compressor.data.transforms.tokenization": [[224, "module-neural_compressor.data.transforms.tokenization", false]], "neural_compressor.data.transforms.transform": [[225, "module-neural_compressor.data.transforms.transform", false]], "neural_compressor.metric": [[233, "module-neural_compressor.metric", false]], "neural_compressor.metric.bleu": [[227, "module-neural_compressor.metric.bleu", false]], "neural_compressor.metric.bleu_util": [[228, "module-neural_compressor.metric.bleu_util", false]], "neural_compressor.metric.coco_label_map": [[229, "module-neural_compressor.metric.coco_label_map", false]], "neural_compressor.metric.coco_tools": [[230, "module-neural_compressor.metric.coco_tools", false]], "neural_compressor.metric.evaluate_squad": [[231, "module-neural_compressor.metric.evaluate_squad", false]], "neural_compressor.metric.f1": [[232, "module-neural_compressor.metric.f1", false]], "neural_compressor.metric.metric": [[234, "module-neural_compressor.metric.metric", false]], "neural_compressor.mix_precision": [[235, "module-neural_compressor.mix_precision", false]], "neural_compressor.model": [[237, "module-neural_compressor.model", false]], "neural_compressor.model.base_model": [[236, "module-neural_compressor.model.base_model", false]], "neural_compressor.model.keras_model": [[238, "module-neural_compressor.model.keras_model", false]], "neural_compressor.model.model": [[239, "module-neural_compressor.model.model", false]], "neural_compressor.model.mxnet_model": [[240, "module-neural_compressor.model.mxnet_model", false]], "neural_compressor.model.nets_factory": [[241, "module-neural_compressor.model.nets_factory", false]], "neural_compressor.model.onnx_model": [[242, "module-neural_compressor.model.onnx_model", false]], "neural_compressor.model.tensorflow_model": [[243, "module-neural_compressor.model.tensorflow_model", false]], "neural_compressor.model.torch_model": [[244, "module-neural_compressor.model.torch_model", false]], "neural_compressor.objective": [[245, "module-neural_compressor.objective", false]], "neural_compressor.profiling": [[246, "module-neural_compressor.profiling", false]], "neural_compressor.profiling.parser.factory": [[247, "module-neural_compressor.profiling.parser.factory", false]], "neural_compressor.profiling.parser.onnx_parser.factory": [[248, "module-neural_compressor.profiling.parser.onnx_parser.factory", false]], "neural_compressor.profiling.parser.onnx_parser.parser": [[249, "module-neural_compressor.profiling.parser.onnx_parser.parser", false]], "neural_compressor.profiling.parser.parser": [[250, "module-neural_compressor.profiling.parser.parser", false]], "neural_compressor.profiling.parser.result": [[251, "module-neural_compressor.profiling.parser.result", false]], "neural_compressor.profiling.parser.tensorflow_parser.factory": [[252, "module-neural_compressor.profiling.parser.tensorflow_parser.factory", false]], "neural_compressor.profiling.parser.tensorflow_parser.parser": [[253, "module-neural_compressor.profiling.parser.tensorflow_parser.parser", false]], "neural_compressor.profiling.profiler.factory": [[254, "module-neural_compressor.profiling.profiler.factory", false]], "neural_compressor.profiling.profiler.onnxrt_profiler.factory": [[255, "module-neural_compressor.profiling.profiler.onnxrt_profiler.factory", false]], "neural_compressor.profiling.profiler.onnxrt_profiler.profiler": [[256, "module-neural_compressor.profiling.profiler.onnxrt_profiler.profiler", false]], "neural_compressor.profiling.profiler.onnxrt_profiler.utils": [[257, "module-neural_compressor.profiling.profiler.onnxrt_profiler.utils", false]], "neural_compressor.profiling.profiler.profiler": [[258, "module-neural_compressor.profiling.profiler.profiler", false]], "neural_compressor.profiling.profiler.tensorflow_profiler.factory": [[259, "module-neural_compressor.profiling.profiler.tensorflow_profiler.factory", false]], "neural_compressor.profiling.profiler.tensorflow_profiler.profiler": [[260, "module-neural_compressor.profiling.profiler.tensorflow_profiler.profiler", false]], "neural_compressor.profiling.profiler.tensorflow_profiler.utils": [[261, "module-neural_compressor.profiling.profiler.tensorflow_profiler.utils", false]], "neural_compressor.quantization": [[262, "module-neural_compressor.quantization", false]], "neural_compressor.strategy": [[270, "module-neural_compressor.strategy", false]], "neural_compressor.strategy.auto": [[263, "module-neural_compressor.strategy.auto", false]], "neural_compressor.strategy.auto_mixed_precision": [[264, "module-neural_compressor.strategy.auto_mixed_precision", false]], "neural_compressor.strategy.basic": [[265, "module-neural_compressor.strategy.basic", false]], "neural_compressor.strategy.bayesian": [[266, "module-neural_compressor.strategy.bayesian", false]], "neural_compressor.strategy.conservative": [[267, "module-neural_compressor.strategy.conservative", false]], "neural_compressor.strategy.exhaustive": [[268, "module-neural_compressor.strategy.exhaustive", false]], "neural_compressor.strategy.hawq_v2": [[269, "module-neural_compressor.strategy.hawq_v2", false]], "neural_compressor.strategy.mse": [[271, "module-neural_compressor.strategy.mse", false]], "neural_compressor.strategy.mse_v2": [[272, "module-neural_compressor.strategy.mse_v2", false]], "neural_compressor.strategy.random": [[273, "module-neural_compressor.strategy.random", false]], "neural_compressor.strategy.strategy": [[274, "module-neural_compressor.strategy.strategy", false]], "neural_compressor.strategy.utils": [[276, "module-neural_compressor.strategy.utils", false]], "neural_compressor.strategy.utils.constant": [[275, "module-neural_compressor.strategy.utils.constant", false]], "neural_compressor.strategy.utils.tuning_sampler": [[277, "module-neural_compressor.strategy.utils.tuning_sampler", false]], "neural_compressor.strategy.utils.tuning_space": [[278, "module-neural_compressor.strategy.utils.tuning_space", false]], "neural_compressor.strategy.utils.tuning_structs": [[279, "module-neural_compressor.strategy.utils.tuning_structs", false]], "neural_compressor.strategy.utils.utility": [[280, "module-neural_compressor.strategy.utils.utility", false]], "neural_compressor.template.api_doc_example": [[281, "module-neural_compressor.template.api_doc_example", false]], "neural_compressor.tensorflow": [[290, "module-neural_compressor.tensorflow", false]], "neural_compressor.tensorflow.algorithms": [[282, "module-neural_compressor.tensorflow.algorithms", false]], "neural_compressor.tensorflow.algorithms.smoother": [[285, "module-neural_compressor.tensorflow.algorithms.smoother", false]], "neural_compressor.tensorflow.algorithms.smoother.calibration": [[283, "module-neural_compressor.tensorflow.algorithms.smoother.calibration", false]], "neural_compressor.tensorflow.algorithms.smoother.core": [[284, "module-neural_compressor.tensorflow.algorithms.smoother.core", false]], "neural_compressor.tensorflow.algorithms.smoother.scaler": [[286, "module-neural_compressor.tensorflow.algorithms.smoother.scaler", false]], "neural_compressor.tensorflow.algorithms.static_quant": [[287, "module-neural_compressor.tensorflow.algorithms.static_quant", false]], "neural_compressor.tensorflow.algorithms.static_quant.keras": [[288, "module-neural_compressor.tensorflow.algorithms.static_quant.keras", false]], "neural_compressor.tensorflow.algorithms.static_quant.tensorflow": [[289, "module-neural_compressor.tensorflow.algorithms.static_quant.tensorflow", false]], "neural_compressor.tensorflow.keras": [[291, "module-neural_compressor.tensorflow.keras", false]], "neural_compressor.tensorflow.keras.layers": [[295, "module-neural_compressor.tensorflow.keras.layers", false]], "neural_compressor.tensorflow.keras.layers.conv2d": [[292, "module-neural_compressor.tensorflow.keras.layers.conv2d", false]], "neural_compressor.tensorflow.keras.layers.dense": [[293, "module-neural_compressor.tensorflow.keras.layers.dense", false]], "neural_compressor.tensorflow.keras.layers.depthwise_conv2d": [[294, "module-neural_compressor.tensorflow.keras.layers.depthwise_conv2d", false]], "neural_compressor.tensorflow.keras.layers.layer_initializer": [[296, "module-neural_compressor.tensorflow.keras.layers.layer_initializer", false]], "neural_compressor.tensorflow.keras.layers.pool2d": [[297, "module-neural_compressor.tensorflow.keras.layers.pool2d", false]], "neural_compressor.tensorflow.keras.layers.separable_conv2d": [[298, "module-neural_compressor.tensorflow.keras.layers.separable_conv2d", false]], "neural_compressor.tensorflow.keras.quantization": [[300, "module-neural_compressor.tensorflow.keras.quantization", false]], "neural_compressor.tensorflow.keras.quantization.config": [[299, "module-neural_compressor.tensorflow.keras.quantization.config", false]], "neural_compressor.tensorflow.quantization": [[304, "module-neural_compressor.tensorflow.quantization", false]], "neural_compressor.tensorflow.quantization.algorithm_entry": [[301, "module-neural_compressor.tensorflow.quantization.algorithm_entry", false]], "neural_compressor.tensorflow.quantization.autotune": [[302, "module-neural_compressor.tensorflow.quantization.autotune", false]], "neural_compressor.tensorflow.quantization.config": [[303, "module-neural_compressor.tensorflow.quantization.config", false]], "neural_compressor.tensorflow.quantization.quantize": [[305, "module-neural_compressor.tensorflow.quantization.quantize", false]], "neural_compressor.tensorflow.quantization.utils": [[361, "module-neural_compressor.tensorflow.quantization.utils", false]], "neural_compressor.tensorflow.quantization.utils.graph_converter": [[306, "module-neural_compressor.tensorflow.quantization.utils.graph_converter", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter": [[344, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16": [[309, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert": [[307, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer": [[308, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic": [[333, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd": [[310, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout": [[311, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu": [[312, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random": [[313, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const": [[314, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction": [[315, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd": [[316, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer": [[317, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape": [[318, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm": [[319, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant": [[320, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add": [[321, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul": [[322, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math": [[323, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn": [[324, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in": [[325, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu": [[326, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm": [[327, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv": [[328, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv": [[329, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose": [[330, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer": [[331, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass": [[332, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node": [[334, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu": [[335, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize": [[336, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes": [[337, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm": [[338, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input": [[339, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes": [[340, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes": [[341, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer": [[342, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base": [[343, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8": [[351, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant": [[345, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value": [[346, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize": [[347, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize": [[348, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize": [[349, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize": [[350, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer": [[352, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter": [[353, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse": [[354, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation": [[355, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq": [[356, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern": [[357, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq": [[358, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern": [[359, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern", false]], "neural_compressor.tensorflow.quantization.utils.graph_util": [[360, "module-neural_compressor.tensorflow.quantization.utils.graph_util", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph": [[362, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq": [[370, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn": [[363, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2": [[364, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv": [[365, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv": [[366, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in": [[367, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul": [[368, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling": [[369, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq": [[371, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base": [[372, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn": [[373, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2": [[374, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv": [[375, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu": [[376, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul": [[377, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling": [[378, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph_common": [[379, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph_common", false]], "neural_compressor.tensorflow.quantization.utils.transform_graph": [[382, "module-neural_compressor.tensorflow.quantization.utils.transform_graph", false]], "neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction": [[380, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction", false]], "neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base": [[381, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base", false]], "neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging": [[383, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging", false]], "neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat": [[384, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat", false]], "neural_compressor.tensorflow.quantization.utils.utility": [[385, "module-neural_compressor.tensorflow.quantization.utils.utility", false]], "neural_compressor.tensorflow.utils": [[388, "module-neural_compressor.tensorflow.utils", false]], "neural_compressor.tensorflow.utils.constants": [[386, "module-neural_compressor.tensorflow.utils.constants", false]], "neural_compressor.tensorflow.utils.data": [[387, "module-neural_compressor.tensorflow.utils.data", false]], "neural_compressor.tensorflow.utils.model": [[389, "module-neural_compressor.tensorflow.utils.model", false]], "neural_compressor.tensorflow.utils.model_wrappers": [[390, "module-neural_compressor.tensorflow.utils.model_wrappers", false]], "neural_compressor.tensorflow.utils.utility": [[391, "module-neural_compressor.tensorflow.utils.utility", false]], "neural_compressor.torch": [[436, "module-neural_compressor.torch", false]], "neural_compressor.torch.algorithms": [[394, "module-neural_compressor.torch.algorithms", false]], "neural_compressor.torch.algorithms.base_algorithm": [[392, "module-neural_compressor.torch.algorithms.base_algorithm", false]], "neural_compressor.torch.algorithms.fp8_quant.utils.logger": [[393, "module-neural_compressor.torch.algorithms.fp8_quant.utils.logger", false]], "neural_compressor.torch.algorithms.layer_wise": [[395, "module-neural_compressor.torch.algorithms.layer_wise", false]], "neural_compressor.torch.algorithms.layer_wise.load": [[396, "module-neural_compressor.torch.algorithms.layer_wise.load", false]], "neural_compressor.torch.algorithms.layer_wise.modified_pickle": [[397, "module-neural_compressor.torch.algorithms.layer_wise.modified_pickle", false]], "neural_compressor.torch.algorithms.layer_wise.utils": [[398, "module-neural_compressor.torch.algorithms.layer_wise.utils", false]], "neural_compressor.torch.algorithms.mixed_precision": [[400, "module-neural_compressor.torch.algorithms.mixed_precision", false]], "neural_compressor.torch.algorithms.mixed_precision.half_precision_convert": [[399, "module-neural_compressor.torch.algorithms.mixed_precision.half_precision_convert", false]], "neural_compressor.torch.algorithms.mixed_precision.module_wrappers": [[401, "module-neural_compressor.torch.algorithms.mixed_precision.module_wrappers", false]], "neural_compressor.torch.algorithms.mx_quant": [[402, "module-neural_compressor.torch.algorithms.mx_quant", false]], "neural_compressor.torch.algorithms.mx_quant.mx": [[403, "module-neural_compressor.torch.algorithms.mx_quant.mx", false]], "neural_compressor.torch.algorithms.mx_quant.utils": [[404, "module-neural_compressor.torch.algorithms.mx_quant.utils", false]], "neural_compressor.torch.algorithms.pt2e_quant": [[407, "module-neural_compressor.torch.algorithms.pt2e_quant", false]], "neural_compressor.torch.algorithms.pt2e_quant.core": [[405, "module-neural_compressor.torch.algorithms.pt2e_quant.core", false]], "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter": [[406, "module-neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter", false]], "neural_compressor.torch.algorithms.pt2e_quant.save_load": [[408, "module-neural_compressor.torch.algorithms.pt2e_quant.save_load", false]], "neural_compressor.torch.algorithms.pt2e_quant.utility": [[409, "module-neural_compressor.torch.algorithms.pt2e_quant.utility", false]], "neural_compressor.torch.algorithms.smooth_quant": [[410, "module-neural_compressor.torch.algorithms.smooth_quant", false]], "neural_compressor.torch.algorithms.smooth_quant.save_load": [[411, "module-neural_compressor.torch.algorithms.smooth_quant.save_load", false]], "neural_compressor.torch.algorithms.smooth_quant.smooth_quant": [[412, "module-neural_compressor.torch.algorithms.smooth_quant.smooth_quant", false]], "neural_compressor.torch.algorithms.smooth_quant.utility": [[413, "module-neural_compressor.torch.algorithms.smooth_quant.utility", false]], "neural_compressor.torch.algorithms.static_quant": [[414, "module-neural_compressor.torch.algorithms.static_quant", false]], "neural_compressor.torch.algorithms.static_quant.save_load": [[415, "module-neural_compressor.torch.algorithms.static_quant.save_load", false]], "neural_compressor.torch.algorithms.static_quant.static_quant": [[416, "module-neural_compressor.torch.algorithms.static_quant.static_quant", false]], "neural_compressor.torch.algorithms.static_quant.utility": [[417, "module-neural_compressor.torch.algorithms.static_quant.utility", false]], "neural_compressor.torch.algorithms.weight_only": [[428, "module-neural_compressor.torch.algorithms.weight_only", false]], "neural_compressor.torch.algorithms.weight_only.autoround": [[418, "module-neural_compressor.torch.algorithms.weight_only.autoround", false]], "neural_compressor.torch.algorithms.weight_only.awq": [[419, "module-neural_compressor.torch.algorithms.weight_only.awq", false]], "neural_compressor.torch.algorithms.weight_only.gptq": [[420, "module-neural_compressor.torch.algorithms.weight_only.gptq", false]], "neural_compressor.torch.algorithms.weight_only.hqq": [[424, "module-neural_compressor.torch.algorithms.weight_only.hqq", false]], "neural_compressor.torch.algorithms.weight_only.hqq.bitpack": [[421, "module-neural_compressor.torch.algorithms.weight_only.hqq.bitpack", false]], "neural_compressor.torch.algorithms.weight_only.hqq.config": [[422, "module-neural_compressor.torch.algorithms.weight_only.hqq.config", false]], "neural_compressor.torch.algorithms.weight_only.hqq.core": [[423, "module-neural_compressor.torch.algorithms.weight_only.hqq.core", false]], "neural_compressor.torch.algorithms.weight_only.hqq.optimizer": [[425, "module-neural_compressor.torch.algorithms.weight_only.hqq.optimizer", false]], "neural_compressor.torch.algorithms.weight_only.hqq.qtensor": [[426, "module-neural_compressor.torch.algorithms.weight_only.hqq.qtensor", false]], "neural_compressor.torch.algorithms.weight_only.hqq.quantizer": [[427, "module-neural_compressor.torch.algorithms.weight_only.hqq.quantizer", false]], "neural_compressor.torch.algorithms.weight_only.modules": [[429, "module-neural_compressor.torch.algorithms.weight_only.modules", false]], "neural_compressor.torch.algorithms.weight_only.rtn": [[430, "module-neural_compressor.torch.algorithms.weight_only.rtn", false]], "neural_compressor.torch.algorithms.weight_only.save_load": [[431, "module-neural_compressor.torch.algorithms.weight_only.save_load", false]], "neural_compressor.torch.algorithms.weight_only.teq": [[432, "module-neural_compressor.torch.algorithms.weight_only.teq", false]], "neural_compressor.torch.algorithms.weight_only.utility": [[433, "module-neural_compressor.torch.algorithms.weight_only.utility", false]], "neural_compressor.torch.export": [[434, "module-neural_compressor.torch.export", false]], "neural_compressor.torch.export.pt2e_export": [[435, "module-neural_compressor.torch.export.pt2e_export", false]], "neural_compressor.torch.quantization": [[440, "module-neural_compressor.torch.quantization", false]], "neural_compressor.torch.quantization.algorithm_entry": [[437, "module-neural_compressor.torch.quantization.algorithm_entry", false]], "neural_compressor.torch.quantization.autotune": [[438, "module-neural_compressor.torch.quantization.autotune", false]], "neural_compressor.torch.quantization.config": [[439, "module-neural_compressor.torch.quantization.config", false]], "neural_compressor.torch.quantization.load_entry": [[441, "module-neural_compressor.torch.quantization.load_entry", false]], "neural_compressor.torch.quantization.quantize": [[442, "module-neural_compressor.torch.quantization.quantize", false]], "neural_compressor.torch.utils": [[446, "module-neural_compressor.torch.utils", false]], "neural_compressor.torch.utils.auto_accelerator": [[443, "module-neural_compressor.torch.utils.auto_accelerator", false]], "neural_compressor.torch.utils.constants": [[444, "module-neural_compressor.torch.utils.constants", false]], "neural_compressor.torch.utils.environ": [[445, "module-neural_compressor.torch.utils.environ", false]], "neural_compressor.torch.utils.utility": [[447, "module-neural_compressor.torch.utils.utility", false]], "neural_compressor.training": [[448, "module-neural_compressor.training", false]], "neural_compressor.transformers.quantization.utils": [[449, "module-neural_compressor.transformers.quantization.utils", false]], "neural_compressor.transformers.utils": [[450, "module-neural_compressor.transformers.utils", false]], "neural_compressor.transformers.utils.quantization_config": [[451, "module-neural_compressor.transformers.utils.quantization_config", false]], "neural_compressor.utils": [[459, "module-neural_compressor.utils", false]], "neural_compressor.utils.collect_layer_histogram": [[452, "module-neural_compressor.utils.collect_layer_histogram", false]], "neural_compressor.utils.constant": [[453, "module-neural_compressor.utils.constant", false]], "neural_compressor.utils.create_obj_from_config": [[454, "module-neural_compressor.utils.create_obj_from_config", false]], "neural_compressor.utils.export": [[455, "module-neural_compressor.utils.export", false]], "neural_compressor.utils.export.qlinear2qdq": [[456, "module-neural_compressor.utils.export.qlinear2qdq", false]], "neural_compressor.utils.export.tf2onnx": [[457, "module-neural_compressor.utils.export.tf2onnx", false]], "neural_compressor.utils.export.torch2onnx": [[458, "module-neural_compressor.utils.export.torch2onnx", false]], "neural_compressor.utils.kl_divergence": [[460, "module-neural_compressor.utils.kl_divergence", false]], "neural_compressor.utils.load_huggingface": [[461, "module-neural_compressor.utils.load_huggingface", false]], "neural_compressor.utils.logger": [[462, "module-neural_compressor.utils.logger", false]], "neural_compressor.utils.options": [[463, "module-neural_compressor.utils.options", false]], "neural_compressor.utils.pytorch": [[464, "module-neural_compressor.utils.pytorch", false]], "neural_compressor.utils.utility": [[465, "module-neural_compressor.utils.utility", false]], "neural_compressor.utils.weights_details": [[466, "module-neural_compressor.utils.weights_details", false]], "neural_compressor.version": [[467, "module-neural_compressor.version", false]], "node_collector (class in neural_compressor.adaptor.torch_utils.hawq_metric)": [[135, "neural_compressor.adaptor.torch_utils.hawq_metric.Node_collector", false]], "node_from_map() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.node_from_map", false]], "node_from_map() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.node_from_map", false]], "node_from_map() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm)": [[55, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm.node_from_map", false]], "node_from_map() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.node_from_map", false]], "node_from_map() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.node_from_map", false]], "node_from_map() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm)": [[327, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm.node_from_map", false]], "node_name_from_input() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.node_name_from_input", false]], "node_name_from_input() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.node_name_from_input", false]], "node_name_from_input() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm)": [[55, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm.node_name_from_input", false]], "node_name_from_input() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.node_name_from_input", false]], "node_name_from_input() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.node_name_from_input", false]], "node_name_from_input() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm)": [[327, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm.node_name_from_input", false]], "nondigit_punct_re (neural_compressor.metric.bleu.unicoderegex attribute)": [[227, "neural_compressor.metric.bleu.UnicodeRegex.nondigit_punct_re", false]], "normalizationoperator (class in neural_compressor.adaptor.ox_utils.operators.norm)": [[20, "neural_compressor.adaptor.ox_utils.operators.norm.NormalizationOperator", false]], "normalize_answer() (in module neural_compressor.metric.f1)": [[232, "neural_compressor.metric.f1.normalize_answer", false]], "normalizetftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.NormalizeTFTransform", false]], "normalizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.NormalizeTransform", false]], "num_correct (neural_compressor.metric.metric.generaltopk attribute)": [[234, "neural_compressor.metric.metric.GeneralTopK.num_correct", false]], "num_correct (neural_compressor.metric.metric.tensorflowtopk attribute)": [[234, "neural_compressor.metric.metric.TensorflowTopK.num_correct", false]], "num_sample (neural_compressor.metric.metric.generaltopk attribute)": [[234, "neural_compressor.metric.metric.GeneralTopK.num_sample", false]], "num_sample (neural_compressor.metric.metric.tensorflowtopk attribute)": [[234, "neural_compressor.metric.metric.TensorflowTopK.num_sample", false]], "objective (class in neural_compressor.objective)": [[245, "neural_compressor.objective.Objective", false]], "objective_custom_registry() (in module neural_compressor.objective)": [[245, "neural_compressor.objective.objective_custom_registry", false]], "objective_registry() (in module neural_compressor.objective)": [[245, "neural_compressor.objective.objective_registry", false]], "oneshotscheduler (class in neural_compressor.compression.pruner.schedulers)": [[190, "neural_compressor.compression.pruner.schedulers.OneshotScheduler", false]], "onnx (class in neural_compressor.config)": [[195, "neural_compressor.config.ONNX", false]], "onnx_qlinear_to_qdq() (in module neural_compressor.utils.export.qlinear2qdq)": [[456, "neural_compressor.utils.export.qlinear2qdq.onnx_qlinear_to_qdq", false]], "onnxbilinearimagenettransform (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.OnnxBilinearImagenetTransform", false]], "onnxgraph (class in neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph)": [[87, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph.OnnxGraph", false]], "onnxmodel (class in neural_compressor.model.onnx_model)": [[242, "neural_compressor.model.onnx_model.ONNXModel", false]], "onnxnode (class in neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node)": [[88, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node.OnnxNode", false]], "onnxopschema (class in neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema)": [[89, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema.OnnxOpSchema", false]], "onnxprofilingparser (class in neural_compressor.profiling.parser.onnx_parser.parser)": [[249, "neural_compressor.profiling.parser.onnx_parser.parser.OnnxProfilingParser", false]], "onnxqlinear2qdqconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.ONNXQlinear2QDQConfig", false]], "onnxresizecropimagenettransform (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.ONNXResizeCropImagenetTransform", false]], "onnxrt (class in neural_compressor.utils.options)": [[463, "neural_compressor.utils.options.onnxrt", false]], "onnxrtaugment (class in neural_compressor.adaptor.ox_utils.calibration)": [[2, "neural_compressor.adaptor.ox_utils.calibration.ONNXRTAugment", false]], "onnxrtbertdataloader (class in neural_compressor.data.dataloaders.onnxrt_dataloader)": [[205, "neural_compressor.data.dataloaders.onnxrt_dataloader.ONNXRTBertDataLoader", false]], "onnxrtbertdataset (class in neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.ONNXRTBertDataset", false]], "onnxrtcroptoboundingbox (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ONNXRTCropToBoundingBox", false]], "onnxrtdataloader (class in neural_compressor.data.dataloaders.onnxrt_dataloader)": [[205, "neural_compressor.data.dataloaders.onnxrt_dataloader.ONNXRTDataLoader", false]], "onnxrtglue (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.ONNXRTGLUE", false]], "onnxrtimagenetdataset (class in neural_compressor.data.datasets.imagenet_dataset)": [[214, "neural_compressor.data.datasets.imagenet_dataset.ONNXRTImagenetDataset", false]], "onnxrtitdatasets (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.ONNXRTITDatasets", false]], "onnxrtitfilters (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.ONNXRTITFilters", false]], "onnxrtitmetrics (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.ONNXRTITMetrics", false]], "onnxrtittransforms (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ONNXRTITTransforms", false]], "onnxrtparserfactory (class in neural_compressor.profiling.parser.onnx_parser.factory)": [[248, "neural_compressor.profiling.parser.onnx_parser.factory.OnnxrtParserFactory", false]], "onnxrtqldatasets (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.ONNXRTQLDatasets", false]], "onnxrtqlfilters (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.ONNXRTQLFilters", false]], "onnxrtqlmetrics (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.ONNXRTQLMetrics", false]], "onnxrtqltransforms (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ONNXRTQLTransforms", false]], "op_level (neural_compressor.common.tuning_param.paramlevel attribute)": [[156, "neural_compressor.common.tuning_param.ParamLevel.OP_LEVEL", false]], "op_registry() (in module neural_compressor.adaptor.ox_utils.operators.ops)": [[21, "neural_compressor.adaptor.ox_utils.operators.ops.op_registry", false]], "op_type_level (neural_compressor.common.tuning_param.paramlevel attribute)": [[156, "neural_compressor.common.tuning_param.ParamLevel.OP_TYPE_LEVEL", false]], "opentry (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.OpEntry", false]], "operator (class in neural_compressor.adaptor.ox_utils.operators.ops)": [[21, "neural_compressor.adaptor.ox_utils.operators.ops.Operator", false]], "operatorconfig (class in neural_compressor.tensorflow.keras.quantization.config)": [[299, "neural_compressor.tensorflow.keras.quantization.config.OperatorConfig", false]], "operatorconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.OperatorConfig", false]], "optimize_weights_proximal_legacy() (in module neural_compressor.torch.algorithms.weight_only.hqq.optimizer)": [[425, "neural_compressor.torch.algorithms.weight_only.hqq.optimizer.optimize_weights_proximal_legacy", false]], "optimizedmodel (class in neural_compressor.utils.load_huggingface)": [[461, "neural_compressor.utils.load_huggingface.OptimizedModel", false]], "optimizeqdqgraph (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq)": [[116, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq.OptimizeQDQGraph", false]], "optimizeqdqgraph (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq)": [[371, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq.OptimizeQDQGraph", false]], "optimizer_registry() (in module neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.optimizer_registry", false]], "optimizers (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.Optimizers", false]], "options (class in neural_compressor.config)": [[195, "neural_compressor.config.Options", false]], "optuningconfig (class in neural_compressor.strategy.utils.tuning_structs)": [[279, "neural_compressor.strategy.utils.tuning_structs.OpTuningConfig", false]], "optype (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.OpType", false]], "optypewisetuningsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.OpTypeWiseTuningSampler", false]], "opwisetuningsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.OpWiseTuningSampler", false]], "ordereddefaultdict (class in neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.OrderedDefaultDict", false]], "ortsmoothquant (class in neural_compressor.adaptor.ox_utils.smooth_quant)": [[29, "neural_compressor.adaptor.ox_utils.smooth_quant.ORTSmoothQuant", false]], "packer (class in neural_compressor.torch.algorithms.weight_only.hqq.bitpack)": [[421, "neural_compressor.torch.algorithms.weight_only.hqq.bitpack.Packer", false]], "packing (neural_compressor.torch.algorithms.weight_only.hqq.qtensor.qtensormetainfo attribute)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo.packing", false]], "pad_tensor() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.pad_tensor", false]], "paddedcentercroptransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PaddedCenterCropTransform", false]], "padoperator (class in neural_compressor.adaptor.ox_utils.operators.pad)": [[22, "neural_compressor.adaptor.ox_utils.operators.pad.PadOperator", false]], "paramlevel (class in neural_compressor.common.tuning_param)": [[156, "neural_compressor.common.tuning_param.ParamLevel", false]], "params_list (neural_compressor.common.base_config.baseconfig attribute)": [[152, "neural_compressor.common.base_config.BaseConfig.params_list", false]], "parse_auto_slim_config() (in module neural_compressor.compression.pruner.model_slim.auto_slim)": [[171, "neural_compressor.compression.pruner.model_slim.auto_slim.parse_auto_slim_config", false]], "parse_cfgs() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.parse_cfgs", false]], "parse_last_linear() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.parse_last_linear", false]], "parse_last_linear_tf() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.parse_last_linear_tf", false]], "parse_saved_model() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.parse_saved_model", false]], "parse_saved_model() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.parse_saved_model", false]], "parse_str2list() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.parse_str2list", false]], "parse_to_prune() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.parse_to_prune", false]], "parse_to_prune_tf() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.parse_to_prune_tf", false]], "parse_tune_config() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.parse_tune_config", false]], "parse_valid_pruner_types() (in module neural_compressor.compression.pruner.pruners)": [[183, "neural_compressor.compression.pruner.pruners.parse_valid_pruner_types", false]], "parsedecodebert (class in neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.ParseDecodeBert", false]], "parsedecodecoco (class in neural_compressor.data.datasets.coco_dataset)": [[210, "neural_compressor.data.datasets.coco_dataset.ParseDecodeCoco", false]], "parsedecodeimagenet (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.ParseDecodeImagenet", false]], "parsedecodeimagenettransform (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.ParseDecodeImagenetTransform", false]], "parsedecodevoctransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ParseDecodeVocTransform", false]], "parserfactory (class in neural_compressor.profiling.parser.factory)": [[247, "neural_compressor.profiling.parser.factory.ParserFactory", false]], "paser_cfgs() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.paser_cfgs", false]], "patch_hqq_moduile() (in module neural_compressor.torch.algorithms.weight_only.hqq.quantizer)": [[427, "neural_compressor.torch.algorithms.weight_only.hqq.quantizer.patch_hqq_moduile", false]], "pattern (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.pattern", false]], "pattern (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.pattern", false]], "pattern (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.basic.kerasbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.KerasBasicPruner.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.basic.pytorchbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.PytorchBasicPruner.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.block_mask.pytorchblockmaskpruner attribute)": [[182, "neural_compressor.compression.pruner.pruners.block_mask.PytorchBlockMaskPruner.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.retrain_free.pytorchretrainfreepruner attribute)": [[187, "neural_compressor.compression.pruner.pruners.retrain_free.PytorchRetrainFreePruner.pattern", false]], "pattern_factory() (in module neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.pattern_factory", false]], "pattern_to_internal() (in module neural_compressor.strategy.utils.tuning_space)": [[278, "neural_compressor.strategy.utils.tuning_space.pattern_to_internal", false]], "pattern_to_path() (in module neural_compressor.strategy.utils.tuning_space)": [[278, "neural_compressor.strategy.utils.tuning_space.pattern_to_path", false]], "patternmha (class in neural_compressor.compression.pruner.patterns.mha)": [[177, "neural_compressor.compression.pruner.patterns.mha.PatternMHA", false]], "patternpair (class in neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.PatternPair", false]], "percentilecalibrator (class in neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.PercentileCalibrator", false]], "performance (class in neural_compressor.objective)": [[245, "neural_compressor.objective.Performance", false]], "pickleerror": [[138, "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle.PickleError", false], [397, "neural_compressor.torch.algorithms.layer_wise.modified_pickle.PickleError", false]], "picklingerror": [[138, "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle.PicklingError", false], [397, "neural_compressor.torch.algorithms.layer_wise.modified_pickle.PicklingError", false]], "pooloperator (class in neural_compressor.adaptor.ox_utils.operators.pooling)": [[23, "neural_compressor.adaptor.ox_utils.operators.pooling.PoolOperator", false]], "postcompressionutils (class in neural_compressor.compression.pruner.model_slim.weight_slim)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.PostCompressionUtils", false]], "postcseoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse)": [[83, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse.PostCseOptimizer", false]], "postcseoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse)": [[354, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse.PostCseOptimizer", false]], "posthostconstconverter (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter)": [[82, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter.PostHostConstConverter", false]], "posthostconstconverter (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter)": [[353, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter.PostHostConstConverter", false]], "postprocess (class in neural_compressor.data.transforms.postprocess)": [[223, "neural_compressor.data.transforms.postprocess.Postprocess", false]], "postprocess_model() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.postprocess_model", false]], "posttrainingquantconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.PostTrainingQuantConfig", false]], "pred_list (neural_compressor.metric.metric.accuracy attribute)": [[234, "neural_compressor.metric.metric.Accuracy.pred_list", false]], "pred_list (neural_compressor.metric.metric.mae attribute)": [[234, "neural_compressor.metric.metric.MAE.pred_list", false]], "pred_list (neural_compressor.metric.metric.mse attribute)": [[234, "neural_compressor.metric.metric.MSE.pred_list", false]], "predictions (neural_compressor.metric.bleu.bleu attribute)": [[227, "neural_compressor.metric.bleu.BLEU.predictions", false]], "preoptimization (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize)": [[64, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize.PreOptimization", false]], "preoptimization (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize)": [[336, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize.PreOptimization", false]], "prepare() (in module neural_compressor.torch.quantization.quantize)": [[442, "neural_compressor.torch.quantization.quantize.prepare", false]], "prepare_compression() (in module neural_compressor.training)": [[448, "neural_compressor.training.prepare_compression", false]], "prepare_dataloader() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.prepare_dataloader", false]], "prepare_inputs() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.prepare_inputs", false]], "prepare_model() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.prepare_model", false]], "prepare_model_data() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.prepare_model_data", false]], "prepare_pruning() (in module neural_compressor.compression.pruner)": [[170, "neural_compressor.compression.pruner.prepare_pruning", false]], "preprocess_user_cfg() (in module neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.preprocess_user_cfg", false]], "print_iterables() (in module neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.print_iterables", false]], "print_op_list() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.print_op_list", false]], "print_table() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.print_table", false]], "process_and_check_config() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.process_and_check_config", false]], "process_config() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.process_config", false]], "process_weight_config() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.process_weight_config", false]], "process_yaml_config() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.process_yaml_config", false]], "processortype (class in neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.ProcessorType", false]], "profile() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.profile", false]], "profiler (class in neural_compressor.profiling.profiler.onnxrt_profiler.profiler)": [[256, "neural_compressor.profiling.profiler.onnxrt_profiler.profiler.Profiler", false]], "profiler (class in neural_compressor.profiling.profiler.profiler)": [[258, "neural_compressor.profiling.profiler.profiler.Profiler", false]], "profiler (class in neural_compressor.profiling.profiler.tensorflow_profiler.profiler)": [[260, "neural_compressor.profiling.profiler.tensorflow_profiler.profiler.Profiler", false]], "profilerfactory (class in neural_compressor.profiling.profiler.factory)": [[254, "neural_compressor.profiling.profiler.factory.ProfilerFactory", false]], "profilerfactory (class in neural_compressor.profiling.profiler.onnxrt_profiler.factory)": [[255, "neural_compressor.profiling.profiler.onnxrt_profiler.factory.ProfilerFactory", false]], "profilerfactory (class in neural_compressor.profiling.profiler.tensorflow_profiler.factory)": [[259, "neural_compressor.profiling.profiler.tensorflow_profiler.factory.ProfilerFactory", false]], "profilingparser (class in neural_compressor.profiling.parser.parser)": [[250, "neural_compressor.profiling.parser.parser.ProfilingParser", false]], "profilingresult (class in neural_compressor.profiling.parser.result)": [[251, "neural_compressor.profiling.parser.result.ProfilingResult", false]], "pruner_info (neural_compressor.compression.pruner.pruning.basepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasePruning.pruner_info", false]], "pruner_info (neural_compressor.compression.pruner.pruning.basicpruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasicPruning.pruner_info", false]], "pruner_info (neural_compressor.compression.pruner.pruning.retrainfreepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.RetrainFreePruning.pruner_info", false]], "pruners (neural_compressor.compression.pruner.pruning.basepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasePruning.pruners", false]], "pruners (neural_compressor.compression.pruner.pruning.basicpruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasicPruning.pruners", false]], "pruners (neural_compressor.compression.pruner.pruning.retrainfreepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.RetrainFreePruning.pruners", false]], "pruning_frequency (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.pruning_frequency", false]], "pruning_frequency (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.pruning_frequency", false]], "pruning_frequency (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.pruning_frequency", false]], "pruningcallbacks (class in neural_compressor.compression.callbacks)": [[162, "neural_compressor.compression.callbacks.PruningCallbacks", false]], "pruningcriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.PruningCriterion", false]], "pruningcriterion (class in neural_compressor.compression.pruner.tf_criteria)": [[191, "neural_compressor.compression.pruner.tf_criteria.PruningCriterion", false]], "pruningscheduler (class in neural_compressor.compression.pruner.schedulers)": [[190, "neural_compressor.compression.pruner.schedulers.PruningScheduler", false]], "pt2e_dynamic_quant_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.pt2e_dynamic_quant_entry", false]], "pt2e_static_quant_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.pt2e_static_quant_entry", false]], "punct_nondigit_re (neural_compressor.metric.bleu.unicoderegex attribute)": [[227, "neural_compressor.metric.bleu.UnicodeRegex.punct_nondigit_re", false]], "pythonmultiheadattentionpruner (class in neural_compressor.compression.pruner.pruners.mha)": [[184, "neural_compressor.compression.pruner.pruners.mha.PythonMultiheadAttentionPruner", false]], "pytorch (class in neural_compressor.config)": [[195, "neural_compressor.config.PyTorch", false]], "pytorchalignimagechannel (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PyTorchAlignImageChannel", false]], "pytorchbasemodel (class in neural_compressor.model.torch_model)": [[244, "neural_compressor.model.torch_model.PyTorchBaseModel", false]], "pytorchbasepattern (class in neural_compressor.compression.pruner.patterns.base)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern", false]], "pytorchbasepruner (class in neural_compressor.compression.pruner.pruners.base)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner", false]], "pytorchbasicpruner (class in neural_compressor.compression.pruner.pruners.basic)": [[181, "neural_compressor.compression.pruner.pruners.basic.PytorchBasicPruner", false]], "pytorchbertdataset (class in neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.PytorchBertDataset", false]], "pytorchblockmaskpruner (class in neural_compressor.compression.pruner.pruners.block_mask)": [[182, "neural_compressor.compression.pruner.pruners.block_mask.PytorchBlockMaskPruner", false]], "pytorchcifar10 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PytorchCIFAR10", false]], "pytorchcifar100 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PytorchCIFAR100", false]], "pytorchcriterions (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchCriterions", false]], "pytorchcropresizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PyTorchCropResizeTransform", false]], "pytorchcrossentropyloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchCrossEntropyLoss", false]], "pytorchdataloader (class in neural_compressor.data.dataloaders.pytorch_dataloader)": [[206, "neural_compressor.data.dataloaders.pytorch_dataloader.PyTorchDataLoader", false]], "pytorchdatasets (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PyTorchDatasets", false]], "pytorchfashionmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PytorchFashionMNIST", false]], "pytorchfilters (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.PyTorchFilters", false]], "pytorchfxmodel (class in neural_compressor.model.torch_model)": [[244, "neural_compressor.model.torch_model.PyTorchFXModel", false]], "pytorchimagenetraw (class in neural_compressor.data.datasets.imagenet_dataset)": [[214, "neural_compressor.data.datasets.imagenet_dataset.PytorchImagenetRaw", false]], "pytorchintermediatelayersknowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchIntermediateLayersKnowledgeDistillationLoss", false]], "pytorchintermediatelayersknowledgedistillationlosswrapper (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchIntermediateLayersKnowledgeDistillationLossWrapper", false]], "pytorchknowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchKnowledgeDistillationLoss", false]], "pytorchknowledgedistillationlosswrapper (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchKnowledgeDistillationLossWrapper", false]], "pytorchloss (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.PyTorchLoss", false]], "pytorchmetrics (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.PyTorchMetrics", false]], "pytorchmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PytorchMNIST", false]], "pytorchmodel (class in neural_compressor.model.torch_model)": [[244, "neural_compressor.model.torch_model.PyTorchModel", false]], "pytorchmxnettransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PytorchMxnetTransform", false]], "pytorchmxnetwrapdataset (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PytorchMxnetWrapDataset", false]], "pytorchmxnetwrapfunction (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PytorchMxnetWrapFunction", false]], "pytorchmxnetwrapfunction (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PytorchMxnetWrapFunction", false]], "pytorchnormalizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PyTorchNormalizeTransform", false]], "pytorchoptimizers (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.PyTorchOptimizers", false]], "pytorchpatternlockpruner (class in neural_compressor.compression.pruner.pruners.pattern_lock)": [[185, "neural_compressor.compression.pruner.pruners.pattern_lock.PytorchPatternLockPruner", false]], "pytorchpatternninm (class in neural_compressor.compression.pruner.patterns.ninm)": [[178, "neural_compressor.compression.pruner.patterns.ninm.PytorchPatternNInM", false]], "pytorchpatternnxm (class in neural_compressor.compression.pruner.patterns.nxm)": [[179, "neural_compressor.compression.pruner.patterns.nxm.PytorchPatternNxM", false]], "pytorchprogressivepruner (class in neural_compressor.compression.pruner.pruners.progressive)": [[186, "neural_compressor.compression.pruner.pruners.progressive.PytorchProgressivePruner", false]], "pytorchretrainfreepruner (class in neural_compressor.compression.pruner.pruners.retrain_free)": [[187, "neural_compressor.compression.pruner.pruners.retrain_free.PytorchRetrainFreePruner", false]], "pytorchselfknowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchSelfKnowledgeDistillationLoss", false]], "pytorchselfknowledgedistillationlosswrapper (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchSelfKnowledgeDistillationLossWrapper", false]], "pytorchsgd (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.PyTorchSGD", false]], "pytorchtransforms (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PyTorchTransforms", false]], "pytorchtranspose (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PyTorchTranspose", false]], "qactivationoperator (class in neural_compressor.adaptor.ox_utils.operators.activation)": [[5, "neural_compressor.adaptor.ox_utils.operators.activation.QActivationOperator", false]], "qargmaxoperator (class in neural_compressor.adaptor.ox_utils.operators.argmax)": [[6, "neural_compressor.adaptor.ox_utils.operators.argmax.QArgMaxOperator", false]], "qat_clone_function() (in module neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper)": [[101, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper.qat_clone_function", false]], "qattentionoperator (class in neural_compressor.adaptor.ox_utils.operators.attention)": [[7, "neural_compressor.adaptor.ox_utils.operators.attention.QAttentionOperator", false]], "qavgpool2d (class in neural_compressor.tensorflow.keras.layers.pool2d)": [[297, "neural_compressor.tensorflow.keras.layers.pool2d.QAvgPool2D", false]], "qbinaryoperator (class in neural_compressor.adaptor.ox_utils.operators.binary_op)": [[8, "neural_compressor.adaptor.ox_utils.operators.binary_op.QBinaryOperator", false]], "qconcatoperator (class in neural_compressor.adaptor.ox_utils.operators.concat)": [[9, "neural_compressor.adaptor.ox_utils.operators.concat.QConcatOperator", false]], "qconv2d (class in neural_compressor.tensorflow.keras.layers.conv2d)": [[292, "neural_compressor.tensorflow.keras.layers.conv2d.QConv2D", false]], "qconvoperator (class in neural_compressor.adaptor.ox_utils.operators.conv)": [[10, "neural_compressor.adaptor.ox_utils.operators.conv.QConvOperator", false]], "qdense (class in neural_compressor.tensorflow.keras.layers.dense)": [[293, "neural_compressor.tensorflow.keras.layers.dense.QDense", false]], "qdepthwiseconv2d (class in neural_compressor.tensorflow.keras.layers.depthwise_conv2d)": [[294, "neural_compressor.tensorflow.keras.layers.depthwise_conv2d.QDepthwiseConv2D", false]], "qdirectoperator (class in neural_compressor.adaptor.ox_utils.operators.direct_q8)": [[11, "neural_compressor.adaptor.ox_utils.operators.direct_q8.QDirectOperator", false]], "qdq_quantize() (in module neural_compressor.torch.algorithms.smooth_quant.smooth_quant)": [[412, "neural_compressor.torch.algorithms.smooth_quant.smooth_quant.qdq_quantize", false]], "qdq_tensor() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.qdq_tensor", false]], "qdq_weight_actor() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.qdq_weight_actor", false]], "qdq_weight_asym() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.qdq_weight_asym", false]], "qdq_weight_sym() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.qdq_weight_sym", false]], "qdqlayer (class in neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.QDQLayer", false]], "qdqlayer (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.QDQLayer", false]], "qembedlayernormalizationoperator (class in neural_compressor.adaptor.ox_utils.operators.embed_layernorm)": [[12, "neural_compressor.adaptor.ox_utils.operators.embed_layernorm.QEmbedLayerNormalizationOperator", false]], "qgatheroperator (class in neural_compressor.adaptor.ox_utils.operators.gather)": [[13, "neural_compressor.adaptor.ox_utils.operators.gather.QGatherOperator", false]], "qgemmoperator (class in neural_compressor.adaptor.ox_utils.operators.gemm)": [[15, "neural_compressor.adaptor.ox_utils.operators.gemm.QGemmOperator", false]], "qglobalaveragepooloperator (class in neural_compressor.adaptor.ox_utils.operators.gavgpool)": [[14, "neural_compressor.adaptor.ox_utils.operators.gavgpool.QGlobalAveragePoolOperator", false]], "qmatmuloperator (class in neural_compressor.adaptor.ox_utils.operators.matmul)": [[18, "neural_compressor.adaptor.ox_utils.operators.matmul.QMatMulOperator", false]], "qmaxpool2d (class in neural_compressor.tensorflow.keras.layers.pool2d)": [[297, "neural_compressor.tensorflow.keras.layers.pool2d.QMaxPool2D", false]], "qmaxpooloperator (class in neural_compressor.adaptor.ox_utils.operators.maxpool)": [[19, "neural_compressor.adaptor.ox_utils.operators.maxpool.QMaxPoolOperator", false]], "qop_registry() (in module neural_compressor.adaptor.ox_utils.operators.ops)": [[21, "neural_compressor.adaptor.ox_utils.operators.ops.qop_registry", false]], "qoperator (class in neural_compressor.adaptor.ox_utils.operators.ops)": [[21, "neural_compressor.adaptor.ox_utils.operators.ops.QOperator", false]], "qpadoperator (class in neural_compressor.adaptor.ox_utils.operators.pad)": [[22, "neural_compressor.adaptor.ox_utils.operators.pad.QPadOperator", false]], "qpooloperator (class in neural_compressor.adaptor.ox_utils.operators.pooling)": [[23, "neural_compressor.adaptor.ox_utils.operators.pooling.QPoolOperator", false]], "qresizeoperator (class in neural_compressor.adaptor.ox_utils.operators.resize)": [[25, "neural_compressor.adaptor.ox_utils.operators.resize.QResizeOperator", false]], "qseparableconv2d (class in neural_compressor.tensorflow.keras.layers.separable_conv2d)": [[298, "neural_compressor.tensorflow.keras.layers.separable_conv2d.QSeparableConv2D", false]], "qsplitoperator (class in neural_compressor.adaptor.ox_utils.operators.split)": [[26, "neural_compressor.adaptor.ox_utils.operators.split.QSplitOperator", false]], "qtensor (class in neural_compressor.torch.algorithms.weight_only.hqq.qtensor)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensor", false]], "qtensorconfig (class in neural_compressor.torch.algorithms.weight_only.hqq.config)": [[422, "neural_compressor.torch.algorithms.weight_only.hqq.config.QTensorConfig", false]], "qtensormetainfo (class in neural_compressor.torch.algorithms.weight_only.hqq.qtensor)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo", false]], "quant_dequant_data() (in module neural_compressor.adaptor.ox_utils.smooth_quant)": [[29, "neural_compressor.adaptor.ox_utils.smooth_quant.quant_dequant_data", false]], "quant_dequant_w_v1() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.quant_dequant_w_v1", false]], "quant_dequant_x_v1() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.quant_dequant_x_v1", false]], "quant_mode_from_pattern() (in module neural_compressor.strategy.utils.tuning_space)": [[278, "neural_compressor.strategy.utils.tuning_space.quant_mode_from_pattern", false]], "quant_tensor() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.quant_tensor", false]], "quant_tensor() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.quant_tensor", false]], "quant_weight_w_scale() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.quant_weight_w_scale", false]], "quantformat (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.QuantFormat", false]], "quantizationawaretrainingcallbacks (class in neural_compressor.compression.callbacks)": [[162, "neural_compressor.compression.callbacks.QuantizationAwareTrainingCallbacks", false]], "quantizationawaretrainingconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.QuantizationAwareTrainingConfig", false]], "quantizationmethod (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.QuantizationMethod", false]], "quantizationmode (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.QuantizationMode", false]], "quantize() (in module neural_compressor.torch.quantization.quantize)": [[442, "neural_compressor.torch.quantization.quantize.quantize", false]], "quantize_4bit() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.quantize_4bit", false]], "quantize_data() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.quantize_data", false]], "quantize_data_per_channel() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.quantize_data_per_channel", false]], "quantize_data_with_scale_zero() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.quantize_data_with_scale_zero", false]], "quantize_elemwise_op() (in module neural_compressor.torch.algorithms.mx_quant.utils)": [[404, "neural_compressor.torch.algorithms.mx_quant.utils.quantize_elemwise_op", false]], "quantize_model() (in module neural_compressor.tensorflow.quantization.quantize)": [[305, "neural_compressor.tensorflow.quantization.quantize.quantize_model", false]], "quantize_model_with_single_config() (in module neural_compressor.tensorflow.quantization.quantize)": [[305, "neural_compressor.tensorflow.quantization.quantize.quantize_model_with_single_config", false]], "quantize_mx_op() (in module neural_compressor.torch.algorithms.mx_quant.utils)": [[404, "neural_compressor.torch.algorithms.mx_quant.utils.quantize_mx_op", false]], "quantize_nparray() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.quantize_nparray", false]], "quantize_sym_model() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.quantize_sym_model", false]], "quantizeconfig (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config)": [[100, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config.QuantizeConfig", false]], "quantizedinitializer (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.QuantizedInitializer", false]], "quantizedinput (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.QuantizedInput", false]], "quantizedrnnconverter (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert)": [[84, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert.QuantizedRNNConverter", false]], "quantizedvalue (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.QuantizedValue", false]], "quantizedvaluetype (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.QuantizedValueType", false]], "quantizegraphbase (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base)": [[117, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base.QuantizeGraphBase", false]], "quantizegraphbase (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base)": [[372, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base.QuantizeGraphBase", false]], "quantizegraphforintel (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu)": [[121, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu.QuantizeGraphForIntel", false]], "quantizegraphforintel (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu)": [[376, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu.QuantizeGraphForIntel", false]], "quantizegraphhelper (class in neural_compressor.adaptor.tf_utils.quantize_graph_common)": [[124, "neural_compressor.adaptor.tf_utils.quantize_graph_common.QuantizeGraphHelper", false]], "quantizegraphhelper (class in neural_compressor.tensorflow.quantization.utils.quantize_graph_common)": [[379, "neural_compressor.tensorflow.quantization.utils.quantize_graph_common.QuantizeGraphHelper", false]], "quantizelayeradd (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add)": [[104, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add.QuantizeLayerAdd", false]], "quantizelayerbase (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base)": [[105, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base.QuantizeLayerBase", false]], "quantizelayerbatchnormalization (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn)": [[106, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn.QuantizeLayerBatchNormalization", false]], "quantizenodebase (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base)": [[117, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base.QuantizeNodeBase", false]], "quantizenodebase (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base)": [[372, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base.QuantizeNodeBase", false]], "quantizer (class in neural_compressor.adaptor.ox_utils.quantizer)": [[28, "neural_compressor.adaptor.ox_utils.quantizer.Quantizer", false]], "quantizer (class in neural_compressor.torch.algorithms.base_algorithm)": [[392, "neural_compressor.torch.algorithms.base_algorithm.Quantizer", false]], "quantizer (class in neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.Quantizer", false]], "quantizewrapper (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper)": [[107, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper.QuantizeWrapper", false]], "quantizewrapperbase (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper)": [[107, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper.QuantizeWrapperBase", false]], "quantoptions (class in neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.QuantOptions", false]], "quanttype (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.QuantType", false]], "quanttype (class in neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.QuantType", false]], "query_quantizable_nodes() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.query_quantizable_nodes", false]], "randomcroptftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomCropTFTransform", false]], "randomcroptransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomCropTransform", false]], "randomhorizontalflip (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomHorizontalFlip", false]], "randomresizedcropmxnettransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomResizedCropMXNetTransform", false]], "randomresizedcroppytorchtransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomResizedCropPytorchTransform", false]], "randomresizedcroptftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomResizedCropTFTransform", false]], "randomresizedcroptransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomResizedCropTransform", false]], "randomtunestrategy (class in neural_compressor.strategy.random)": [[273, "neural_compressor.strategy.random.RandomTuneStrategy", false]], "randomverticalflip (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomVerticalFlip", false]], "rawgptquantizer (class in neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.RAWGPTQuantizer", false]], "read_graph() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.read_graph", false]], "read_graph() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.read_graph", false]], "read_squad_examples() (in module neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.read_squad_examples", false]], "read_tensorflow_node_attrs() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.read_tensorflow_node_attrs", false]], "recipe (neural_compressor.compression.pruner.model_slim.pattern_analyzer.recipesearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.RecipeSearcher.recipe", false]], "recipesearcher (class in neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.RecipeSearcher", false]], "reconstruct_saved_model() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.reconstruct_saved_model", false]], "reconstruct_saved_model() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.reconstruct_saved_model", false]], "record_output() (in module neural_compressor.compression.distillation.utility)": [[166, "neural_compressor.compression.distillation.utility.record_output", false]], "recover() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.recover", false]], "recover_forward() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.recover_forward", false]], "recover_model_from_json() (in module neural_compressor.torch.algorithms.smooth_quant.save_load)": [[411, "neural_compressor.torch.algorithms.smooth_quant.save_load.recover_model_from_json", false]], "recover_model_from_json() (in module neural_compressor.utils.pytorch)": [[464, "neural_compressor.utils.pytorch.recover_model_from_json", false]], "reduceminmaxoperator (class in neural_compressor.adaptor.ox_utils.operators.reduce)": [[24, "neural_compressor.adaptor.ox_utils.operators.reduce.ReduceMinMaxOperator", false]], "reduceoperator (class in neural_compressor.adaptor.ox_utils.operators.reduce)": [[24, "neural_compressor.adaptor.ox_utils.operators.reduce.ReduceOperator", false]], "reg (neural_compressor.compression.pruner.pruners.basic.kerasbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.KerasBasicPruner.reg", false]], "reg (neural_compressor.compression.pruner.pruners.basic.pytorchbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.PytorchBasicPruner.reg", false]], "reg (neural_compressor.compression.pruner.pruners.block_mask.pytorchblockmaskpruner attribute)": [[182, "neural_compressor.compression.pruner.pruners.block_mask.PytorchBlockMaskPruner.reg", false]], "reg (neural_compressor.compression.pruner.pruners.retrain_free.pytorchretrainfreepruner attribute)": [[187, "neural_compressor.compression.pruner.pruners.retrain_free.PytorchRetrainFreePruner.reg", false]], "reg_terms (neural_compressor.compression.pruner.regs.grouplasso attribute)": [[189, "neural_compressor.compression.pruner.regs.GroupLasso.reg_terms", false]], "register_accelerator() (in module neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.register_accelerator", false]], "register_algo() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.register_algo", false]], "register_algo() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.register_algo", false]], "register_autotune() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.register_autotune", false]], "register_config() (in module neural_compressor.common.base_config)": [[152, "neural_compressor.common.base_config.register_config", false]], "register_criterion() (in module neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.register_criterion", false]], "register_criterion() (in module neural_compressor.compression.pruner.tf_criteria)": [[191, "neural_compressor.compression.pruner.tf_criteria.register_criterion", false]], "register_customer_metric() (in module neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.register_customer_metric", false]], "register_pattern() (in module neural_compressor.compression.pruner.patterns.base)": [[175, "neural_compressor.compression.pruner.patterns.base.register_pattern", false]], "register_pruner() (in module neural_compressor.compression.pruner.pruners.base)": [[180, "neural_compressor.compression.pruner.pruners.base.register_pruner", false]], "register_pruning() (in module neural_compressor.compression.pruner.pruning)": [[188, "neural_compressor.compression.pruner.pruning.register_pruning", false]], "register_reg() (in module neural_compressor.compression.pruner.regs)": [[189, "neural_compressor.compression.pruner.regs.register_reg", false]], "register_scheduler() (in module neural_compressor.compression.pruner.schedulers)": [[190, "neural_compressor.compression.pruner.schedulers.register_scheduler", false]], "register_supported_configs_for_fwk() (in module neural_compressor.common.base_config)": [[152, "neural_compressor.common.base_config.register_supported_configs_for_fwk", false]], "register_weight_hooks() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.register_weight_hooks", false]], "removableactivationoperator (class in neural_compressor.adaptor.ox_utils.operators.activation)": [[5, "neural_compressor.adaptor.ox_utils.operators.activation.RemovableActivationOperator", false]], "remove_init_from_model_input() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.remove_init_from_model_input", false]], "removetrainingnodesoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes)": [[65, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes.RemoveTrainingNodesOptimizer", false]], "removetrainingnodesoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes)": [[337, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes.RemoveTrainingNodesOptimizer", false]], "renamebatchnormoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm)": [[66, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm.RenameBatchNormOptimizer", false]], "renamebatchnormoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm)": [[338, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm.RenameBatchNormOptimizer", false]], "replace_forward() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.replace_forward", false]], "replace_pattern (neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.patternpair attribute)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.PatternPair.replace_pattern", false]], "replacement_fn() (in module neural_compressor.torch.algorithms.weight_only.hqq.quantizer)": [[427, "neural_compressor.torch.algorithms.weight_only.hqq.quantizer.replacement_fn", false]], "rerangequantizedconcat (class in neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat)": [[132, "neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat.RerangeQuantizedConcat", false]], "rerangequantizedconcat (class in neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat)": [[384, "neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat.RerangeQuantizedConcat", false]], "rescalekeraspretraintransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RescaleKerasPretrainTransform", false]], "rescaletftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RescaleTFTransform", false]], "rescaletransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RescaleTransform", false]], "reset_none_to_default() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.reset_none_to_default", false]], "reshape_in_channel_to_last() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.reshape_in_channel_to_last", false]], "reshape_scale_as_input() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.reshape_scale_as_input", false]], "reshape_scale_as_weight() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.reshape_scale_as_weight", false]], "resizemxnettransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ResizeMXNetTransform", false]], "resizeoperator (class in neural_compressor.adaptor.ox_utils.operators.resize)": [[25, "neural_compressor.adaptor.ox_utils.operators.resize.ResizeOperator", false]], "resizepytorchtransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ResizePytorchTransform", false]], "resizetftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ResizeTFTransform", false]], "resizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ResizeTransform", false]], "resizewithaspectratio (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.ResizeWithAspectRatio", false]], "resizewithratio (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ResizeWithRatio", false]], "retrainfreecriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.RetrainFreeCriterion", false]], "retrainfreepruning (class in neural_compressor.compression.pruner.pruning)": [[188, "neural_compressor.compression.pruner.pruning.RetrainFreePruning", false]], "reverted_data_type() (in module neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.reverted_data_type", false]], "rmse (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.RMSE", false]], "roc (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.ROC", false]], "roundingmode (class in neural_compressor.torch.algorithms.mx_quant.utils)": [[404, "neural_compressor.torch.algorithms.mx_quant.utils.RoundingMode", false]], "rtn_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.rtn_entry", false]], "rtn_quantize() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.rtn_quantize", false]], "rtnconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.RTNConfig", false]], "rtnconfig (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.RtnConfig", false]], "rtnquantizer (class in neural_compressor.torch.algorithms.weight_only.rtn)": [[430, "neural_compressor.torch.algorithms.weight_only.rtn.RTNQuantizer", false]], "run_forward() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.run_forward", false]], "run_instance() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.run_instance", false]], "run_multi_instance_command() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.run_multi_instance_command", false]], "sample (neural_compressor.metric.metric.accuracy attribute)": [[234, "neural_compressor.metric.metric.Accuracy.sample", false]], "sample (neural_compressor.metric.metric.loss attribute)": [[234, "neural_compressor.metric.metric.Loss.sample", false]], "sampler (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.Sampler", false]], "sampler (class in neural_compressor.data.dataloaders.sampler)": [[207, "neural_compressor.data.dataloaders.sampler.Sampler", false]], "save() (in module neural_compressor.compression.pruner)": [[170, "neural_compressor.compression.pruner.save", false]], "save() (in module neural_compressor.torch.algorithms.pt2e_quant.save_load)": [[408, "neural_compressor.torch.algorithms.pt2e_quant.save_load.save", false]], "save() (in module neural_compressor.torch.algorithms.static_quant.save_load)": [[415, "neural_compressor.torch.algorithms.static_quant.save_load.save", false]], "save() (in module neural_compressor.torch.algorithms.weight_only.save_load)": [[431, "neural_compressor.torch.algorithms.weight_only.save_load.save", false]], "save_config_mapping() (in module neural_compressor.common.utils.save_load)": [[160, "neural_compressor.common.utils.save_load.save_config_mapping", false]], "save_for_huggingface_upstream() (in module neural_compressor.utils.load_huggingface)": [[461, "neural_compressor.utils.load_huggingface.save_for_huggingface_upstream", false]], "save_protobuf() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.save_protobuf", false]], "saved_model_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.saved_model_session", false]], "saved_model_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.saved_model_session", false]], "scalepropagationtransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation)": [[85, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation.ScaleProPagationTransformer", false]], "scalepropagationtransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation)": [[355, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation.ScaleProPagationTransformer", false]], "scheduler (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.scheduler", false]], "scheduler (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.scheduler", false]], "scheduler (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.scheduler", false]], "scheduler (neural_compressor.compression.pruner.pruners.basic.kerasbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.KerasBasicPruner.scheduler", false]], "scheduler (neural_compressor.compression.pruner.pruners.basic.pytorchbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.PytorchBasicPruner.scheduler", false]], "scheduler (neural_compressor.compression.pruner.pruners.block_mask.pytorchblockmaskpruner attribute)": [[182, "neural_compressor.compression.pruner.pruners.block_mask.PytorchBlockMaskPruner.scheduler", false]], "scheduler (neural_compressor.compression.pruner.pruners.retrain_free.pytorchretrainfreepruner attribute)": [[187, "neural_compressor.compression.pruner.pruners.retrain_free.PytorchRetrainFreePruner.scheduler", false]], "scores (neural_compressor.compression.pruner.criteria.blockmaskcriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.BlockMaskCriterion.scores", false]], "scores (neural_compressor.compression.pruner.criteria.gradientcriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.GradientCriterion.scores", false]], "scores (neural_compressor.compression.pruner.criteria.magnitudecriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.MagnitudeCriterion.scores", false]], "scores (neural_compressor.compression.pruner.criteria.pruningcriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.PruningCriterion.scores", false]], "scores (neural_compressor.compression.pruner.criteria.retrainfreecriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.RetrainFreeCriterion.scores", false]], "scores (neural_compressor.compression.pruner.criteria.snipcriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.SnipCriterion.scores", false]], "scores (neural_compressor.compression.pruner.criteria.snipmomentumcriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.SnipMomentumCriterion.scores", false]], "scores (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.scores", false]], "scores (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.scores", false]], "scores (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.scores", false]], "scores (neural_compressor.compression.pruner.tf_criteria.magnitudecriterion attribute)": [[191, "neural_compressor.compression.pruner.tf_criteria.MagnitudeCriterion.scores", false]], "scores (neural_compressor.compression.pruner.tf_criteria.pruningcriterion attribute)": [[191, "neural_compressor.compression.pruner.tf_criteria.PruningCriterion.scores", false]], "search_clip() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.search_clip", false]], "search_pattern (neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.patternpair attribute)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.PatternPair.search_pattern", false]], "searching_results (neural_compressor.compression.pruner.model_slim.pattern_analyzer.jitbasicsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher.searching_results", false]], "searching_results (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.searching_results", false]], "searching_results (neural_compressor.compression.pruner.model_slim.pattern_analyzer.recipesearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.RecipeSearcher.searching_results", false]], "selfknowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.SelfKnowledgeDistillationLoss", false]], "selfknowledgedistillationlossconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.SelfKnowledgeDistillationLossConfig", false]], "selfmhasearcher (class in neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.SelfMHASearcher", false]], "seqtype (class in neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.SeqType", false]], "sequentialsampler (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.SequentialSampler", false]], "sequentialsampler (class in neural_compressor.data.dataloaders.sampler)": [[207, "neural_compressor.data.dataloaders.sampler.SequentialSampler", false]], "sequentialsampler (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.SequentialSampler", false]], "set_all_env_var() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.set_all_env_var", false]], "set_cores_for_instance() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.set_cores_for_instance", false]], "set_eager_execution() (in module neural_compressor.profiling.profiler.tensorflow_profiler.utils)": [[261, "neural_compressor.profiling.profiler.tensorflow_profiler.utils.set_eager_execution", false]], "set_env_var() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.set_env_var", false]], "set_module() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.set_module", false]], "set_module() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.set_module", false]], "set_module() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.set_module", false]], "set_module() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.set_module", false]], "set_name() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.set_name", false]], "set_random_seed() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.set_random_seed", false]], "set_random_seed() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.set_random_seed", false]], "set_resume_from() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.set_resume_from", false]], "set_resume_from() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.set_resume_from", false]], "set_tensorboard() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.set_tensorboard", false]], "set_tensorboard() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.set_tensorboard", false]], "set_workspace() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.set_workspace", false]], "set_workspace() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.set_workspace", false]], "shape (neural_compressor.torch.algorithms.weight_only.hqq.qtensor.qtensormetainfo attribute)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo.shape", false]], "shareqdqforitexypatternoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern)": [[94, "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern.ShareQDQForItexYPatternOptimizer", false]], "shareqdqforitexypatternoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern)": [[359, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern.ShareQDQForItexYPatternOptimizer", false]], "show_memory_info() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.show_memory_info", false]], "sigopttunestrategy (class in neural_compressor.contrib.strategy.sigopt)": [[198, "neural_compressor.contrib.strategy.sigopt.SigOptTuneStrategy", false]], "simple_inference() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.simple_inference", false]], "simple_inference() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.simple_inference", false]], "simple_progress_bar() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.simple_progress_bar", false]], "singleton() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.singleton", false]], "singleton() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.singleton", false]], "singleton() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.singleton", false]], "slim_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.slim_session", false]], "slim_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.slim_session", false]], "smooth_distribution() (in module neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.smooth_distribution", false]], "smooth_quant_entry() (in module neural_compressor.tensorflow.quantization.algorithm_entry)": [[301, "neural_compressor.tensorflow.quantization.algorithm_entry.smooth_quant_entry", false]], "smooth_quant_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.smooth_quant_entry", false]], "smoothquant (class in neural_compressor.algorithm.smooth_quant)": [[149, "neural_compressor.algorithm.smooth_quant.SmoothQuant", false]], "smoothquant (class in neural_compressor.tensorflow.algorithms.smoother.core)": [[284, "neural_compressor.tensorflow.algorithms.smoother.core.SmoothQuant", false]], "smoothquantcalibration (class in neural_compressor.adaptor.tf_utils.smooth_quant_calibration)": [[125, "neural_compressor.adaptor.tf_utils.smooth_quant_calibration.SmoothQuantCalibration", false]], "smoothquantcalibration (class in neural_compressor.tensorflow.algorithms.smoother.calibration)": [[283, "neural_compressor.tensorflow.algorithms.smoother.calibration.SmoothQuantCalibration", false]], "smoothquantcalibrationllm (class in neural_compressor.adaptor.tf_utils.smooth_quant_calibration)": [[125, "neural_compressor.adaptor.tf_utils.smooth_quant_calibration.SmoothQuantCalibrationLLM", false]], "smoothquantcalibrationllm (class in neural_compressor.tensorflow.algorithms.smoother.calibration)": [[283, "neural_compressor.tensorflow.algorithms.smoother.calibration.SmoothQuantCalibrationLLM", false]], "smoothquantconfig (class in neural_compressor.tensorflow.quantization.config)": [[303, "neural_compressor.tensorflow.quantization.config.SmoothQuantConfig", false]], "smoothquantconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.SmoothQuantConfig", false]], "smoothquantquantizer (class in neural_compressor.torch.algorithms.smooth_quant.smooth_quant)": [[412, "neural_compressor.torch.algorithms.smooth_quant.smooth_quant.SmoothQuantQuantizer", false]], "smoothquantsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.SmoothQuantSampler", false]], "smoothquantscaler (class in neural_compressor.adaptor.tf_utils.smooth_quant_scaler)": [[126, "neural_compressor.adaptor.tf_utils.smooth_quant_scaler.SmoothQuantScaler", false]], "smoothquantscaler (class in neural_compressor.tensorflow.algorithms.smoother.scaler)": [[286, "neural_compressor.tensorflow.algorithms.smoother.scaler.SmoothQuantScaler", false]], "smoothquantscalerllm (class in neural_compressor.adaptor.tf_utils.smooth_quant_scaler)": [[126, "neural_compressor.adaptor.tf_utils.smooth_quant_scaler.SmoothQuantScalerLLM", false]], "smoothquantscalerllm (class in neural_compressor.tensorflow.algorithms.smoother.scaler)": [[286, "neural_compressor.tensorflow.algorithms.smoother.scaler.SmoothQuantScalerLLM", false]], "snipcriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.SnipCriterion", false]], "snipmomentumcriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.SnipMomentumCriterion", false]], "sparsedummydataset (class in neural_compressor.data.datasets.dummy_dataset_v2)": [[213, "neural_compressor.data.datasets.dummy_dataset_v2.SparseDummyDataset", false]], "sparsegptpruning (class in neural_compressor.compression.pruner.pruning)": [[188, "neural_compressor.compression.pruner.pruning.SparseGPTPruning", false]], "split_shared_bias() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.split_shared_bias", false]], "splitoperator (class in neural_compressor.adaptor.ox_utils.operators.split)": [[26, "neural_compressor.adaptor.ox_utils.operators.split.SplitOperator", false]], "splitsharedinputoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input)": [[67, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input.SplitSharedInputOptimizer", false]], "splitsharedinputoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input)": [[339, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input.SplitSharedInputOptimizer", false]], "sqlinearwrapper (class in neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.SQLinearWrapper", false]], "squadexample (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.SquadExample", false]], "squadf1 (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.SquadF1", false]], "start_step (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.start_step", false]], "start_step (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.start_step", false]], "start_step (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.start_step", false]], "static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcher.static_graph", false]], "static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearchertf attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcherTF.static_graph", false]], "static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.jitbasicsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher.static_graph", false]], "static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.static_graph", false]], "static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.selfmhasearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.SelfMHASearcher.static_graph", false]], "static_quant_entry() (in module neural_compressor.tensorflow.quantization.algorithm_entry)": [[301, "neural_compressor.tensorflow.quantization.algorithm_entry.static_quant_entry", false]], "static_quant_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.static_quant_entry", false]], "static_quant_export() (in module neural_compressor.utils.export.torch2onnx)": [[458, "neural_compressor.utils.export.torch2onnx.static_quant_export", false]], "staticquantconfig (class in neural_compressor.tensorflow.keras.quantization.config)": [[299, "neural_compressor.tensorflow.keras.quantization.config.StaticQuantConfig", false]], "staticquantconfig (class in neural_compressor.tensorflow.quantization.config)": [[303, "neural_compressor.tensorflow.quantization.config.StaticQuantConfig", false]], "staticquantconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.StaticQuantConfig", false]], "staticquantquantizer (class in neural_compressor.torch.algorithms.static_quant.static_quant)": [[416, "neural_compressor.torch.algorithms.static_quant.static_quant.StaticQuantQuantizer", false]], "statistics (class in neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.Statistics", false]], "statistics (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.Statistics", false]], "str2array() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.str2array", false]], "strategy_registry() (in module neural_compressor.strategy.strategy)": [[274, "neural_compressor.strategy.strategy.strategy_registry", false]], "strip_equivalent_nodes() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.strip_equivalent_nodes", false]], "strip_equivalent_nodes() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.strip_equivalent_nodes", false]], "strip_unused_nodes() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.strip_unused_nodes", false]], "strip_unused_nodes() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.strip_unused_nodes", false]], "stripequivalentnodesoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes)": [[68, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes.StripEquivalentNodesOptimizer", false]], "stripequivalentnodesoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes)": [[340, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes.StripEquivalentNodesOptimizer", false]], "stripunusednodesoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes)": [[69, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes.StripUnusedNodesOptimizer", false]], "stripunusednodesoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes)": [[341, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes.StripUnusedNodesOptimizer", false]], "styletransferdataset (class in neural_compressor.data.datasets.style_transfer_dataset)": [[216, "neural_compressor.data.datasets.style_transfer_dataset.StyleTransferDataset", false]], "sum (neural_compressor.metric.metric.loss attribute)": [[234, "neural_compressor.metric.metric.Loss.sum", false]], "summary_benchmark() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.summary_benchmark", false]], "summary_latency_throughput() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.summary_latency_throughput", false]], "switchoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer)": [[70, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer.SwitchOptimizer", false]], "switchoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer)": [[342, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer.SwitchOptimizer", false]], "symbol_re (neural_compressor.metric.bleu.unicoderegex attribute)": [[227, "neural_compressor.metric.bleu.UnicodeRegex.symbol_re", false]], "symbolic_trace() (in module neural_compressor.adaptor.torch_utils.symbolic_trace)": [[144, "neural_compressor.adaptor.torch_utils.symbolic_trace.symbolic_trace", false]], "target_layers (neural_compressor.compression.pruner.model_slim.pattern_analyzer.jitbasicsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher.target_layers", false]], "target_layers (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.target_layers", false]], "target_op_lut (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.target_op_lut", false]], "target_sparsity (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.target_sparsity", false]], "target_sparsity (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.target_sparsity", false]], "target_sparsity (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.target_sparsity", false]], "target_sparsity_ratio (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.target_sparsity_ratio", false]], "target_sparsity_ratio (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.target_sparsity_ratio", false]], "target_sparsity_ratio (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.target_sparsity_ratio", false]], "targets (neural_compressor.compression.pruner.model_slim.pattern_analyzer.recipesearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.RecipeSearcher.targets", false]], "targetspace (class in neural_compressor.strategy.bayesian)": [[266, "neural_compressor.strategy.bayesian.TargetSpace", false]], "tensorcollector (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.TensorCollector", false]], "tensorflow (class in neural_compressor.config)": [[195, "neural_compressor.config.TensorFlow", false]], "tensorflow (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.Tensorflow", false]], "tensorflow_itexadaptor (class in neural_compressor.adaptor.tensorflow)": [[32, "neural_compressor.adaptor.tensorflow.Tensorflow_ITEXAdaptor", false]], "tensorflow_itexadaptor (class in neural_compressor.tensorflow.algorithms.static_quant.tensorflow)": [[289, "neural_compressor.tensorflow.algorithms.static_quant.tensorflow.Tensorflow_ITEXAdaptor", false]], "tensorflowadam (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.TensorFlowAdam", false]], "tensorflowadamw (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.TensorFlowAdamW", false]], "tensorflowadaptor (class in neural_compressor.adaptor.tensorflow)": [[32, "neural_compressor.adaptor.tensorflow.TensorFlowAdaptor", false]], "tensorflowadaptor (class in neural_compressor.tensorflow.algorithms.static_quant.tensorflow)": [[289, "neural_compressor.tensorflow.algorithms.static_quant.tensorflow.TensorFlowAdaptor", false]], "tensorflowbasemodel (class in neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.TensorflowBaseModel", false]], "tensorflowbasemodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.TensorflowBaseModel", false]], "tensorflowbertdataloader (class in neural_compressor.data.dataloaders.tensorflow_dataloader)": [[208, "neural_compressor.data.dataloaders.tensorflow_dataloader.TensorflowBertDataLoader", false]], "tensorflowbertdataset (class in neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.TensorflowBertDataset", false]], "tensorflowcheckpointmodel (class in neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.TensorflowCheckpointModel", false]], "tensorflowcheckpointmodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.TensorflowCheckpointModel", false]], "tensorflowcifar10 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowCIFAR10", false]], "tensorflowcifar100 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowCIFAR100", false]], "tensorflowcocomap (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.TensorflowCOCOMAP", false]], "tensorflowconfig (class in neural_compressor.tensorflow.algorithms.static_quant.tensorflow)": [[289, "neural_compressor.tensorflow.algorithms.static_quant.tensorflow.TensorFlowConfig", false]], "tensorflowconfigconverter (class in neural_compressor.tensorflow.algorithms.static_quant.tensorflow)": [[289, "neural_compressor.tensorflow.algorithms.static_quant.tensorflow.TensorflowConfigConverter", false]], "tensorflowcriterions (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.TensorflowCriterions", false]], "tensorflowcroptoboundingbox (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowCropToBoundingBox", false]], "tensorflowcrossentropyloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.TensorFlowCrossEntropyLoss", false]], "tensorflowdataloader (class in neural_compressor.data.dataloaders.tensorflow_dataloader)": [[208, "neural_compressor.data.dataloaders.tensorflow_dataloader.TensorflowDataLoader", false]], "tensorflowdatasets (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowDatasets", false]], "tensorflowfashionmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowFashionMNIST", false]], "tensorflowfilters (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.TensorflowFilters", false]], "tensorflowglobalconfig (class in neural_compressor.tensorflow.utils.model)": [[389, "neural_compressor.tensorflow.utils.model.TensorflowGlobalConfig", false]], "tensorflowimagenetdataset (class in neural_compressor.data.datasets.imagenet_dataset)": [[214, "neural_compressor.data.datasets.imagenet_dataset.TensorflowImagenetDataset", false]], "tensorflowimagenetraw (class in neural_compressor.data.datasets.imagenet_dataset)": [[214, "neural_compressor.data.datasets.imagenet_dataset.TensorflowImagenetRaw", false]], "tensorflowimagerecord (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowImageRecord", false]], "tensorflowknowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.TensorflowKnowledgeDistillationLoss", false]], "tensorflowknowledgedistillationlossexternal (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.TensorflowKnowledgeDistillationLossExternal", false]], "tensorflowknowledgedistillationlosswrapper (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.TensorflowKnowledgeDistillationLossWrapper", false]], "tensorflowllmmodel (class in neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.TensorflowLLMModel", false]], "tensorflowllmmodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.TensorflowLLMModel", false]], "tensorflowmap (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.TensorflowMAP", false]], "tensorflowmetrics (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.TensorflowMetrics", false]], "tensorflowmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowMNIST", false]], "tensorflowmodel (class in neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.TensorflowModel", false]], "tensorflowmodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.TensorflowModel", false]], "tensorflowmodelzoobertdataloader (class in neural_compressor.data.dataloaders.tensorflow_dataloader)": [[208, "neural_compressor.data.dataloaders.tensorflow_dataloader.TensorflowModelZooBertDataLoader", false]], "tensorflowmodelzoobertdataset (class in neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.TensorflowModelZooBertDataset", false]], "tensorflowoptimizers (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.TensorflowOptimizers", false]], "tensorflowparserfactory (class in neural_compressor.profiling.parser.tensorflow_parser.factory)": [[252, "neural_compressor.profiling.parser.tensorflow_parser.factory.TensorFlowParserFactory", false]], "tensorflowprofilingparser (class in neural_compressor.profiling.parser.tensorflow_parser.parser)": [[253, "neural_compressor.profiling.parser.tensorflow_parser.parser.TensorFlowProfilingParser", false]], "tensorflowqatmodel (class in neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.TensorflowQATModel", false]], "tensorflowqdqtoonnxqdqconverter (class in neural_compressor.adaptor.tf_utils.tf2onnx_converter)": [[127, "neural_compressor.adaptor.tf_utils.tf2onnx_converter.TensorflowQDQToOnnxQDQConverter", false]], "tensorflowquery (class in neural_compressor.adaptor.tensorflow)": [[32, "neural_compressor.adaptor.tensorflow.TensorflowQuery", false]], "tensorflowquery (class in neural_compressor.tensorflow.algorithms.static_quant.tensorflow)": [[289, "neural_compressor.tensorflow.algorithms.static_quant.tensorflow.TensorflowQuery", false]], "tensorflowrandomhorizontalflip (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowRandomHorizontalFlip", false]], "tensorflowrandomverticalflip (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowRandomVerticalFlip", false]], "tensorflowresizecropimagenettransform (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.TensorflowResizeCropImagenetTransform", false]], "tensorflowresizewithratio (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowResizeWithRatio", false]], "tensorflowsavedmodelmodel (class in neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.TensorflowSavedModelModel", false]], "tensorflowsavedmodelmodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.TensorflowSavedModelModel", false]], "tensorflowsgd (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.TensorFlowSGD", false]], "tensorflowshiftrescale (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.TensorflowShiftRescale", false]], "tensorflowsparsecategoricalcrossentropy (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.TensorFlowSparseCategoricalCrossentropy", false]], "tensorflowtfrecorddataset (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowTFRecordDataset", false]], "tensorflowtopk (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.TensorflowTopK", false]], "tensorflowtransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowTransform", false]], "tensorflowtransforms (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowTransforms", false]], "tensorflowtranspose (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowTranspose", false]], "tensorflowtransposelastchannel (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.TensorflowTransposeLastChannel", false]], "tensorflowvocmap (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.TensorflowVOCMAP", false]], "tensorflowvocrecord (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowVOCRecord", false]], "tensorflowwrapfunction (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowWrapFunction", false]], "teq_quantize_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.teq_quantize_entry", false]], "teqconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.TEQConfig", false]], "teqconfig (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.TeqConfig", false]], "teqlinearfakequant (class in neural_compressor.adaptor.torch_utils.model_wrapper)": [[142, "neural_compressor.adaptor.torch_utils.model_wrapper.TEQLinearFakeQuant", false]], "teqlinearfakequant (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.TEQLinearFakeQuant", false]], "tequantizer (class in neural_compressor.torch.algorithms.weight_only.teq)": [[432, "neural_compressor.torch.algorithms.weight_only.teq.TEQuantizer", false]], "tf2onnxconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.TF2ONNXConfig", false]], "tf_to_fp32_onnx() (in module neural_compressor.utils.export.tf2onnx)": [[457, "neural_compressor.utils.export.tf2onnx.tf_to_fp32_onnx", false]], "tf_to_int8_onnx() (in module neural_compressor.utils.export.tf2onnx)": [[457, "neural_compressor.utils.export.tf2onnx.tf_to_int8_onnx", false]], "tfdatadataloader (class in neural_compressor.data.dataloaders.tensorflow_dataloader)": [[208, "neural_compressor.data.dataloaders.tensorflow_dataloader.TFDataDataLoader", false]], "tfmodelzoocollecttransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TFModelZooCollectTransform", false]], "tfslimnetsfactory (class in neural_compressor.model.nets_factory)": [[241, "neural_compressor.model.nets_factory.TFSlimNetsFactory", false]], "tfslimnetsfactory (class in neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.TFSlimNetsFactory", false]], "tfsquadv1modelzooposttransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TFSquadV1ModelZooPostTransform", false]], "tfsquadv1posttransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TFSquadV1PostTransform", false]], "time_limit() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.time_limit", false]], "to_numpy() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.to_numpy", false]], "toarray (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ToArray", false]], "tondarraytransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ToNDArrayTransform", false]], "torch2onnxconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.Torch2ONNXConfig", false]], "torch_to_fp32_onnx() (in module neural_compressor.utils.export.torch2onnx)": [[458, "neural_compressor.utils.export.torch2onnx.torch_to_fp32_onnx", false]], "torch_to_int8_onnx() (in module neural_compressor.utils.export.torch2onnx)": [[458, "neural_compressor.utils.export.torch2onnx.torch_to_int8_onnx", false]], "torchbaseconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.TorchBaseConfig", false]], "torchsmoothquant (class in neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.TorchSmoothQuant", false]], "tpetunestrategy (class in neural_compressor.contrib.strategy.tpe)": [[199, "neural_compressor.contrib.strategy.tpe.TpeTuneStrategy", false]], "trace_and_fuse_sub_graph() (in module neural_compressor.adaptor.torch_utils.symbolic_trace)": [[144, "neural_compressor.adaptor.torch_utils.symbolic_trace.trace_and_fuse_sub_graph", false]], "trace_gptq_target_blocks() (in module neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.trace_gptq_target_blocks", false]], "trainableequivalenttransformation (class in neural_compressor.torch.algorithms.weight_only.teq)": [[432, "neural_compressor.torch.algorithms.weight_only.teq.TrainableEquivalentTransformation", false]], "transform_registry() (in module neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.transform_registry", false]], "transformation() (in module neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.transformation", false]], "transformerbasedmodelblockpatterndetector (class in neural_compressor.adaptor.torch_utils.pattern_detector)": [[143, "neural_compressor.adaptor.torch_utils.pattern_detector.TransformerBasedModelBlockPatternDetector", false]], "transformerbasedmodelblockpatterndetector (class in neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.TransformerBasedModelBlockPatternDetector", false]], "transforms (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TRANSFORMS", false], [225, "neural_compressor.data.transforms.transform.Transforms", false]], "transpose (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.Transpose", false]], "trt_env_setup() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.trt_env_setup", false]], "try_loading_keras() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.try_loading_keras", false]], "try_loading_keras() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.try_loading_keras", false]], "tunestrategy (class in neural_compressor.strategy.strategy)": [[274, "neural_compressor.strategy.strategy.TuneStrategy", false]], "tunestrategymeta (class in neural_compressor.strategy.strategy)": [[274, "neural_compressor.strategy.strategy.TuneStrategyMeta", false]], "tuningconfig (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.TuningConfig", false]], "tuningcriterion (class in neural_compressor.config)": [[195, "neural_compressor.config.TuningCriterion", false]], "tuningitem (class in neural_compressor.strategy.utils.tuning_space)": [[278, "neural_compressor.strategy.utils.tuning_space.TuningItem", false]], "tuninglogger (class in neural_compressor.common.utils.logger)": [[159, "neural_compressor.common.utils.logger.TuningLogger", false]], "tuningmonitor (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.TuningMonitor", false]], "tuningorder (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.TuningOrder", false]], "tuningparam (class in neural_compressor.common.tuning_param)": [[156, "neural_compressor.common.tuning_param.TuningParam", false]], "tuningsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.TuningSampler", false]], "tuningspace (class in neural_compressor.strategy.utils.tuning_space)": [[278, "neural_compressor.strategy.utils.tuning_space.TuningSpace", false]], "unarydirect8bitoperator (class in neural_compressor.adaptor.ox_utils.operators.unary_op)": [[27, "neural_compressor.adaptor.ox_utils.operators.unary_op.UnaryDirect8BitOperator", false]], "unaryoperator (class in neural_compressor.adaptor.ox_utils.operators.unary_op)": [[27, "neural_compressor.adaptor.ox_utils.operators.unary_op.UnaryOperator", false]], "unicoderegex (class in neural_compressor.metric.bleu)": [[227, "neural_compressor.metric.bleu.UnicodeRegex", false]], "unpackedweightonlylinearparams (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.UnpackedWeightOnlyLinearParams", false]], "unpicklingerror": [[138, "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle.UnpicklingError", false], [397, "neural_compressor.torch.algorithms.layer_wise.modified_pickle.UnpicklingError", false]], "update_module() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.update_module", false]], "update_module() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.update_module", false]], "update_params() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.update_params", false]], "update_sq_scale() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.update_sq_scale", false]], "update_sq_scale() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.update_sq_scale", false]], "valid_keras_format() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.valid_keras_format", false]], "valid_reshape_inputs() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.valid_reshape_inputs", false]], "valid_reshape_inputs() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.valid_reshape_inputs", false]], "valid_reshape_inputs() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.valid_reshape_inputs", false]], "valid_reshape_inputs() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.valid_reshape_inputs", false]], "validate_and_inference_input_output() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.validate_and_inference_input_output", false]], "validate_and_inference_input_output() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.validate_and_inference_input_output", false]], "validate_graph_node() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.validate_graph_node", false]], "validate_graph_node() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.validate_graph_node", false]], "valueinfo (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.ValueInfo", false]], "values_from_const() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.values_from_const", false]], "values_from_const() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.values_from_const", false]], "values_from_const() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm)": [[55, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm.values_from_const", false]], "values_from_const() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.values_from_const", false]], "values_from_const() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.values_from_const", false]], "values_from_const() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm)": [[327, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm.values_from_const", false]], "version1_eq_version2() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.version1_eq_version2", false]], "version1_eq_version2() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.version1_eq_version2", false]], "version1_eq_version2() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.version1_eq_version2", false]], "version1_gt_version2() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.version1_gt_version2", false]], "version1_gt_version2() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.version1_gt_version2", false]], "version1_gt_version2() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.version1_gt_version2", false]], "version1_gte_version2() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.version1_gte_version2", false]], "version1_gte_version2() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.version1_gte_version2", false]], "version1_gte_version2() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.version1_gte_version2", false]], "version1_lt_version2() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.version1_lt_version2", false]], "version1_lt_version2() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.version1_lt_version2", false]], "version1_lt_version2() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.version1_lt_version2", false]], "version1_lte_version2() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.version1_lte_version2", false]], "version1_lte_version2() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.version1_lte_version2", false]], "version1_lte_version2() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.version1_lte_version2", false]], "w8a8pt2equantizer (class in neural_compressor.torch.algorithms.pt2e_quant.core)": [[405, "neural_compressor.torch.algorithms.pt2e_quant.core.W8A8PT2EQuantizer", false]], "warn() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.warn", false]], "warning() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.warning", false]], "weightcorrection (class in neural_compressor.algorithm.weight_correction)": [[150, "neural_compressor.algorithm.weight_correction.WeightCorrection", false]], "weightonlylinear (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.WeightOnlyLinear", false]], "weightonlyquantsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.WeightOnlyQuantSampler", false]], "weightpruningconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.WeightPruningConfig", false]], "weightsdetails (class in neural_compressor.utils.weights_details)": [[466, "neural_compressor.utils.weights_details.WeightsDetails", false]], "weightsstatistics (class in neural_compressor.utils.weights_details)": [[466, "neural_compressor.utils.weights_details.WeightsStatistics", false]], "whitespace_tokenize() (in module neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.whitespace_tokenize", false]], "woqmodelloader (class in neural_compressor.torch.algorithms.weight_only.save_load)": [[431, "neural_compressor.torch.algorithms.weight_only.save_load.WOQModelLoader", false]], "wordpiecetokenizer (class in neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.WordpieceTokenizer", false]], "wrapmxnetmetric (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.WrapMXNetMetric", false]], "wraponnxrtmetric (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.WrapONNXRTMetric", false]], "wrapperlayer (class in neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.WrapperLayer", false]], "wrappytorchmetric (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.WrapPyTorchMetric", false]], "write_graph() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.write_graph", false]], "write_graph() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.write_graph", false]], "xpu_accelerator (class in neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.XPU_Accelerator", false]]}, "objects": {"": [[226, 0, 0, "-", "neural_compressor"]], "neural_compressor": [[148, 0, 0, "-", "algorithm"], [151, 0, 0, "-", "benchmark"], [155, 0, 0, "-", "common"], [195, 0, 0, "-", "config"], [196, 0, 0, "-", "contrib"], [220, 0, 0, "-", "data"], [233, 0, 0, "-", "metric"], [235, 0, 0, "-", "mix_precision"], [237, 0, 0, "-", "model"], [245, 0, 0, "-", "objective"], [246, 0, 0, "-", "profiling"], [262, 0, 0, "-", "quantization"], [270, 0, 0, "-", "strategy"], [290, 0, 0, "-", "tensorflow"], [436, 0, 0, "-", "torch"], [448, 0, 0, "-", "training"], [459, 0, 0, "-", "utils"], [467, 0, 0, "-", "version"]], "neural_compressor.adaptor": [[0, 0, 0, "-", "mxnet_utils"], [4, 0, 0, "-", "ox_utils"], [32, 0, 0, "-", "tensorflow"], [96, 0, 0, "-", "tf_utils"], [136, 0, 0, "-", "torch_utils"]], "neural_compressor.adaptor.mxnet_utils": [[1, 0, 0, "-", "util"]], "neural_compressor.adaptor.mxnet_utils.util": [[1, 1, 1, "", "CalibCollector"], [1, 1, 1, "", "CalibData"], [1, 1, 1, "", "CollectorBase"], [1, 1, 1, "", "DataIterLoader"], [1, 1, 1, "", "DataLoaderWrap"], [1, 1, 1, "", "NameCollector"], [1, 1, 1, "", "OpType"], [1, 1, 1, "", "TensorCollector"], [1, 2, 1, "", "amp_convert"], [1, 2, 1, "", "calib_model"], [1, 2, 1, "", "check_mx_version"], [1, 2, 1, "", "combine_capabilities"], [1, 2, 1, "", "create_data_example"], [1, 2, 1, "", "distribute_calib_tensors"], [1, 2, 1, "", "ensure_list"], [1, 2, 1, "", "fuse"], [1, 2, 1, "", "get_framework_name"], [1, 2, 1, "", "is_model_quantized"], [1, 2, 1, "", "isiterable"], [1, 2, 1, "", "make_module"], [1, 2, 1, "", "make_nc_model"], [1, 2, 1, "", "make_symbol_block"], [1, 2, 1, "", "ndarray_to_device"], [1, 2, 1, "", "parse_tune_config"], [1, 2, 1, "", "prepare_dataloader"], [1, 2, 1, "", "prepare_model"], [1, 2, 1, "", "prepare_model_data"], [1, 2, 1, "", "quantize_sym_model"], [1, 2, 1, "", "query_quantizable_nodes"], [1, 2, 1, "", "run_forward"]], "neural_compressor.adaptor.ox_utils": [[2, 0, 0, "-", "calibration"], [3, 0, 0, "-", "calibrator"], [16, 0, 0, "-", "operators"], [28, 0, 0, "-", "quantizer"], [29, 0, 0, "-", "smooth_quant"], [30, 0, 0, "-", "util"], [31, 0, 0, "-", "weight_only"]], "neural_compressor.adaptor.ox_utils.calibration": [[2, 1, 1, "", "ONNXRTAugment"]], "neural_compressor.adaptor.ox_utils.calibrator": [[3, 1, 1, "", "CalibratorBase"], [3, 1, 1, "", "HistogramCollector"], [3, 1, 1, "", "KLCalibrator"], [3, 1, 1, "", "MinMaxCalibrator"], [3, 1, 1, "", "PercentileCalibrator"], [3, 2, 1, "", "calib_registry"], [3, 2, 1, "", "smooth_distribution"]], "neural_compressor.adaptor.ox_utils.operators": [[5, 0, 0, "-", "activation"], [6, 0, 0, "-", "argmax"], [7, 0, 0, "-", "attention"], [8, 0, 0, "-", "binary_op"], [9, 0, 0, "-", "concat"], [10, 0, 0, "-", "conv"], [11, 0, 0, "-", "direct_q8"], [12, 0, 0, "-", "embed_layernorm"], [13, 0, 0, "-", "gather"], [14, 0, 0, "-", "gavgpool"], [15, 0, 0, "-", "gemm"], [17, 0, 0, "-", "lstm"], [18, 0, 0, "-", "matmul"], [19, 0, 0, "-", "maxpool"], [20, 0, 0, "-", "norm"], [21, 0, 0, "-", "ops"], [22, 0, 0, "-", "pad"], [23, 0, 0, "-", "pooling"], [24, 0, 0, "-", "reduce"], [25, 0, 0, "-", "resize"], [26, 0, 0, "-", "split"], [27, 0, 0, "-", "unary_op"]], "neural_compressor.adaptor.ox_utils.operators.activation": [[5, 1, 1, "", "ActivationOperator"], [5, 1, 1, "", "Float16ActivationOperator"], [5, 1, 1, "", "QActivationOperator"], [5, 1, 1, "", "RemovableActivationOperator"]], "neural_compressor.adaptor.ox_utils.operators.argmax": [[6, 1, 1, "", "ArgMaxOperator"], [6, 1, 1, "", "QArgMaxOperator"]], "neural_compressor.adaptor.ox_utils.operators.attention": [[7, 1, 1, "", "AttentionOperator"], [7, 1, 1, "", "QAttentionOperator"]], "neural_compressor.adaptor.ox_utils.operators.binary_op": [[8, 1, 1, "", "BinaryDirect8BitOperator"], [8, 1, 1, "", "BinaryOperator"], [8, 1, 1, "", "Float16BinaryOperator"], [8, 1, 1, "", "QBinaryOperator"]], "neural_compressor.adaptor.ox_utils.operators.concat": [[9, 1, 1, "", "ConcatOperator"], [9, 1, 1, "", "QConcatOperator"]], "neural_compressor.adaptor.ox_utils.operators.conv": [[10, 1, 1, "", "ConvOperator"], [10, 1, 1, "", "QConvOperator"]], "neural_compressor.adaptor.ox_utils.operators.direct_q8": [[11, 1, 1, "", "Direct8BitOperator"], [11, 1, 1, "", "QDirectOperator"]], "neural_compressor.adaptor.ox_utils.operators.embed_layernorm": [[12, 1, 1, "", "EmbedLayerNormalizationOperator"], [12, 1, 1, "", "QEmbedLayerNormalizationOperator"]], "neural_compressor.adaptor.ox_utils.operators.gather": [[13, 1, 1, "", "GatherOperator"], [13, 1, 1, "", "QGatherOperator"]], "neural_compressor.adaptor.ox_utils.operators.gavgpool": [[14, 1, 1, "", "GlobalAveragePoolOperator"], [14, 1, 1, "", "QGlobalAveragePoolOperator"]], "neural_compressor.adaptor.ox_utils.operators.gemm": [[15, 1, 1, "", "GemmOperator"], [15, 1, 1, "", "QGemmOperator"]], "neural_compressor.adaptor.ox_utils.operators.lstm": [[17, 1, 1, "", "LSTMOperator"]], "neural_compressor.adaptor.ox_utils.operators.matmul": [[18, 1, 1, "", "FusedMatMulOperator"], [18, 1, 1, "", "MatMulOperator"], [18, 1, 1, "", "QMatMulOperator"]], "neural_compressor.adaptor.ox_utils.operators.maxpool": [[19, 1, 1, "", "MaxPoolOperator"], [19, 1, 1, "", "QMaxPoolOperator"]], "neural_compressor.adaptor.ox_utils.operators.norm": [[20, 1, 1, "", "BatchNormalizationOperator"], [20, 1, 1, "", "NormalizationOperator"]], "neural_compressor.adaptor.ox_utils.operators.ops": [[21, 1, 1, "", "Operator"], [21, 1, 1, "", "QOperator"], [21, 2, 1, "", "op_registry"], [21, 2, 1, "", "qop_registry"]], "neural_compressor.adaptor.ox_utils.operators.pad": [[22, 1, 1, "", "PadOperator"], [22, 1, 1, "", "QPadOperator"]], "neural_compressor.adaptor.ox_utils.operators.pooling": [[23, 1, 1, "", "PoolOperator"], [23, 1, 1, "", "QPoolOperator"]], "neural_compressor.adaptor.ox_utils.operators.reduce": [[24, 1, 1, "", "ReduceMinMaxOperator"], [24, 1, 1, "", "ReduceOperator"]], "neural_compressor.adaptor.ox_utils.operators.resize": [[25, 1, 1, "", "QResizeOperator"], [25, 1, 1, "", "ResizeOperator"]], "neural_compressor.adaptor.ox_utils.operators.split": [[26, 1, 1, "", "QSplitOperator"], [26, 1, 1, "", "SplitOperator"]], "neural_compressor.adaptor.ox_utils.operators.unary_op": [[27, 1, 1, "", "UnaryDirect8BitOperator"], [27, 1, 1, "", "UnaryOperator"]], "neural_compressor.adaptor.ox_utils.quantizer": [[28, 1, 1, "", "Quantizer"]], "neural_compressor.adaptor.ox_utils.smooth_quant": [[29, 1, 1, "", "ORTSmoothQuant"], [29, 2, 1, "", "get_quant_dequant_output"], [29, 2, 1, "", "make_sub_graph"], [29, 2, 1, "", "quant_dequant_data"]], "neural_compressor.adaptor.ox_utils.util": [[30, 1, 1, "", "QuantFormat"], [30, 1, 1, "", "QuantType"], [30, 1, 1, "", "QuantizationMode"], [30, 1, 1, "", "QuantizedInitializer"], [30, 1, 1, "", "QuantizedValue"], [30, 1, 1, "", "QuantizedValueType"], [30, 1, 1, "", "ValueInfo"], [30, 2, 1, "", "attribute_to_kwarg"], [30, 2, 1, "", "calculate_scale_zp"], [30, 2, 1, "", "cast_tensor"], [30, 2, 1, "", "collate_preds"], [30, 2, 1, "", "dequantize_data"], [30, 2, 1, "", "dequantize_data_with_scale_zero"], [30, 2, 1, "", "dtype_to_name"], [30, 2, 1, "", "find_by_name"], [30, 2, 1, "", "float_to_bfloat16"], [30, 2, 1, "", "float_to_float16"], [30, 2, 1, "", "get_node_original_name"], [30, 2, 1, "", "infer_shapes"], [30, 2, 1, "", "is_B_transposed"], [30, 2, 1, "", "make_dquant_node"], [30, 2, 1, "", "make_quant_node"], [30, 2, 1, "", "quantize_data"], [30, 2, 1, "", "quantize_data_per_channel"], [30, 2, 1, "", "quantize_data_with_scale_zero"], [30, 2, 1, "", "quantize_nparray"], [30, 2, 1, "", "remove_init_from_model_input"], [30, 2, 1, "", "simple_progress_bar"], [30, 2, 1, "", "split_shared_bias"], [30, 2, 1, "", "to_numpy"], [30, 2, 1, "", "trt_env_setup"]], "neural_compressor.adaptor.ox_utils.weight_only": [[31, 2, 1, "", "apply_awq_clip"], [31, 2, 1, "", "apply_awq_scale"], [31, 2, 1, "", "awq_quantize"], [31, 2, 1, "", "get_blob_size"], [31, 2, 1, "", "get_weight_scale"], [31, 2, 1, "", "gptq"], [31, 2, 1, "", "gptq_quantize"], [31, 2, 1, "", "make_matmul_weight_only_node"], [31, 2, 1, "", "pad_tensor"], [31, 2, 1, "", "prepare_inputs"], [31, 2, 1, "", "qdq_tensor"], [31, 2, 1, "", "quant_tensor"], [31, 2, 1, "", "rtn_quantize"]], "neural_compressor.adaptor.tensorflow": [[32, 1, 1, "", "TensorFlowAdaptor"], [32, 1, 1, "", "TensorflowQuery"], [32, 1, 1, "", "Tensorflow_ITEXAdaptor"]], "neural_compressor.adaptor.tf_utils": [[33, 0, 0, "-", "graph_converter"], [34, 0, 0, "-", "graph_converter_without_calib"], [72, 0, 0, "-", "graph_rewriter"], [95, 0, 0, "-", "graph_util"], [97, 0, 0, "-", "quantize_graph"], [124, 0, 0, "-", "quantize_graph_common"], [125, 0, 0, "-", "smooth_quant_calibration"], [126, 0, 0, "-", "smooth_quant_scaler"], [127, 0, 0, "-", "tf2onnx_converter"], [130, 0, 0, "-", "transform_graph"], [133, 0, 0, "-", "util"]], "neural_compressor.adaptor.tf_utils.graph_converter": [[33, 1, 1, "", "GraphConverter"]], "neural_compressor.adaptor.tf_utils.graph_converter_without_calib": [[34, 1, 1, "", "GraphConverterWithoutCalib"]], "neural_compressor.adaptor.tf_utils.graph_rewriter": [[37, 0, 0, "-", "bf16"], [61, 0, 0, "-", "generic"], [71, 0, 0, "-", "graph_base"], [80, 0, 0, "-", "int8"], [86, 0, 0, "-", "onnx"], [91, 0, 0, "-", "qdq"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16": [[35, 0, 0, "-", "bf16_convert"], [36, 0, 0, "-", "dequantize_cast_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert": [[35, 1, 1, "", "BF16Convert"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer": [[36, 1, 1, "", "DequantizeCastOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic": [[38, 0, 0, "-", "convert_add_to_biasadd"], [39, 0, 0, "-", "convert_layout"], [40, 0, 0, "-", "convert_leakyrelu"], [41, 0, 0, "-", "convert_nan_to_random"], [42, 0, 0, "-", "convert_placeholder_to_const"], [43, 0, 0, "-", "dilated_contraction"], [44, 0, 0, "-", "dummy_biasadd"], [45, 0, 0, "-", "expanddims_optimizer"], [46, 0, 0, "-", "fetch_weight_from_reshape"], [47, 0, 0, "-", "fold_batch_norm"], [48, 0, 0, "-", "fold_constant"], [49, 0, 0, "-", "fuse_biasadd_add"], [50, 0, 0, "-", "fuse_column_wise_mul"], [51, 0, 0, "-", "fuse_conv_with_math"], [52, 0, 0, "-", "fuse_decomposed_bn"], [53, 0, 0, "-", "fuse_decomposed_in"], [54, 0, 0, "-", "fuse_gelu"], [55, 0, 0, "-", "fuse_layer_norm"], [56, 0, 0, "-", "fuse_pad_with_conv"], [57, 0, 0, "-", "fuse_pad_with_fp32_conv"], [58, 0, 0, "-", "fuse_reshape_transpose"], [59, 0, 0, "-", "graph_cse_optimizer"], [60, 0, 0, "-", "grappler_pass"], [62, 0, 0, "-", "insert_print_node"], [63, 0, 0, "-", "move_squeeze_after_relu"], [64, 0, 0, "-", "pre_optimize"], [65, 0, 0, "-", "remove_training_nodes"], [66, 0, 0, "-", "rename_batch_norm"], [67, 0, 0, "-", "split_shared_input"], [68, 0, 0, "-", "strip_equivalent_nodes"], [69, 0, 0, "-", "strip_unused_nodes"], [70, 0, 0, "-", "switch_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd": [[38, 1, 1, "", "ConvertAddToBiasAddOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout": [[39, 1, 1, "", "ConvertLayoutOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu": [[40, 1, 1, "", "ConvertLeakyReluOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random": [[41, 1, 1, "", "ConvertNanToRandom"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const": [[42, 1, 1, "", "ConvertPlaceholderToConst"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction": [[43, 1, 1, "", "DilatedContraction"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd": [[44, 1, 1, "", "InjectDummyBiasAddOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer": [[45, 1, 1, "", "ExpandDimsOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape": [[46, 1, 1, "", "FetchWeightFromReshapeOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm": [[47, 1, 1, "", "FoldBatchNormNodesOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant": [[48, 1, 1, "", "GraphFoldConstantOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add": [[49, 1, 1, "", "FuseBiasAddAndAddOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul": [[50, 1, 1, "", "FuseColumnWiseMulOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math": [[51, 1, 1, "", "FuseConvWithMathOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn": [[52, 1, 1, "", "FuseDecomposedBNOptimizer"], [52, 2, 1, "", "bypass_reshape"], [52, 2, 1, "", "get_const_dim_count"], [52, 2, 1, "", "node_from_map"], [52, 2, 1, "", "node_name_from_input"], [52, 2, 1, "", "valid_reshape_inputs"], [52, 2, 1, "", "values_from_const"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in": [[53, 1, 1, "", "FuseDecomposedINOptimizer"], [53, 2, 1, "", "bypass_reshape"], [53, 2, 1, "", "get_const_dim_count"], [53, 2, 1, "", "node_from_map"], [53, 2, 1, "", "node_name_from_input"], [53, 2, 1, "", "valid_reshape_inputs"], [53, 2, 1, "", "values_from_const"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu": [[54, 1, 1, "", "FuseGeluOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm": [[55, 1, 1, "", "FuseLayerNormOptimizer"], [55, 2, 1, "", "node_from_map"], [55, 2, 1, "", "node_name_from_input"], [55, 2, 1, "", "values_from_const"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv": [[56, 1, 1, "", "FusePadWithConv2DOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv": [[57, 1, 1, "", "FusePadWithFP32Conv2DOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose": [[58, 1, 1, "", "FuseTransposeReshapeOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer": [[59, 1, 1, "", "GraphCseOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass": [[60, 1, 1, "", "GrapplerOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node": [[62, 1, 1, "", "InsertPrintMinMaxNode"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu": [[63, 1, 1, "", "MoveSqueezeAfterReluOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize": [[64, 1, 1, "", "PreOptimization"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes": [[65, 1, 1, "", "RemoveTrainingNodesOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm": [[66, 1, 1, "", "RenameBatchNormOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input": [[67, 1, 1, "", "SplitSharedInputOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes": [[68, 1, 1, "", "StripEquivalentNodesOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes": [[69, 1, 1, "", "StripUnusedNodesOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer": [[70, 1, 1, "", "SwitchOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base": [[71, 1, 1, "", "GraphRewriterBase"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8": [[73, 0, 0, "-", "freeze_fake_quant"], [74, 0, 0, "-", "freeze_value"], [75, 0, 0, "-", "freeze_value_without_calib"], [76, 0, 0, "-", "fuse_conv_redundant_dequantize"], [77, 0, 0, "-", "fuse_conv_requantize"], [78, 0, 0, "-", "fuse_matmul_redundant_dequantize"], [79, 0, 0, "-", "fuse_matmul_requantize"], [81, 0, 0, "-", "meta_op_optimizer"], [82, 0, 0, "-", "post_hostconst_converter"], [83, 0, 0, "-", "post_quantized_op_cse"], [84, 0, 0, "-", "rnn_convert"], [85, 0, 0, "-", "scale_propagation"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant": [[73, 1, 1, "", "FreezeFakeQuantOpOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value": [[74, 1, 1, "", "FreezeValueTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib": [[75, 1, 1, "", "FreezeValueWithoutCalibTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize": [[76, 1, 1, "", "FuseConvRedundantDequantizeTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize": [[77, 1, 1, "", "FuseConvRequantizeTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize": [[78, 1, 1, "", "FuseMatMulRedundantDequantizeTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize": [[79, 1, 1, "", "FuseMatMulRequantizeDequantizeNewAPITransformer"], [79, 1, 1, "", "FuseMatMulRequantizeDequantizeTransformer"], [79, 1, 1, "", "FuseMatMulRequantizeNewAPITransformer"], [79, 1, 1, "", "FuseMatMulRequantizeTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer": [[81, 1, 1, "", "MetaInfoChangingMemOpOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter": [[82, 1, 1, "", "PostHostConstConverter"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse": [[83, 1, 1, "", "PostCseOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert": [[84, 1, 1, "", "QuantizedRNNConverter"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation": [[85, 1, 1, "", "ScaleProPagationTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx": [[87, 0, 0, "-", "onnx_graph"], [88, 0, 0, "-", "onnx_node"], [89, 0, 0, "-", "onnx_schema"], [90, 0, 0, "-", "tf2onnx_utils"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph": [[87, 1, 1, "", "OnnxGraph"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node": [[88, 1, 1, "", "OnnxNode"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema": [[89, 1, 1, "", "OnnxOpSchema"], [89, 2, 1, "", "get_max_supported_opset_version"], [89, 2, 1, "", "get_schema"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils": [[90, 1, 1, "", "SeqType"], [90, 2, 1, "", "add_port_to_name"], [90, 2, 1, "", "are_shapes_equal"], [90, 2, 1, "", "assert_error"], [90, 2, 1, "", "compute_const_folding_using_tf"], [90, 2, 1, "", "convert_tensorflow_tensor_to_onnx"], [90, 2, 1, "", "find_opset"], [90, 2, 1, "", "get_index_from_strided_slice_of_shape"], [90, 2, 1, "", "get_subgraphs_from_onnx"], [90, 2, 1, "", "get_tensorflow_node_attr"], [90, 2, 1, "", "get_tensorflow_node_shape_attr"], [90, 2, 1, "", "get_tensorflow_tensor_data"], [90, 2, 1, "", "get_tensorflow_tensor_shape"], [90, 2, 1, "", "infer_onnx_shape_dtype"], [90, 2, 1, "", "initialize_name_counter"], [90, 2, 1, "", "is_list_or_tuple"], [90, 2, 1, "", "is_onnx_domain"], [90, 2, 1, "", "make_onnx_inputs_outputs"], [90, 2, 1, "", "make_onnx_shape"], [90, 2, 1, "", "map_numpy_to_onnx_dtype"], [90, 2, 1, "", "map_onnx_to_numpy_type"], [90, 2, 1, "", "map_tensorflow_dtype"], [90, 2, 1, "", "read_tensorflow_node_attrs"], [90, 2, 1, "", "save_protobuf"], [90, 2, 1, "", "set_name"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq": [[92, 0, 0, "-", "insert_qdq_pattern"], [93, 0, 0, "-", "merge_duplicated_qdq"], [94, 0, 0, "-", "share_qdq_y_pattern"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern": [[92, 1, 1, "", "GenerateGraphWithQDQPattern"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq": [[93, 1, 1, "", "MergeDuplicatedQDQOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern": [[94, 1, 1, "", "ShareQDQForItexYPatternOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_util": [[95, 1, 1, "", "GraphAnalyzer"], [95, 1, 1, "", "GraphRewriterHelper"]], "neural_compressor.adaptor.tf_utils.quantize_graph": [[99, 0, 0, "-", "qat"], [115, 0, 0, "-", "qdq"], [117, 0, 0, "-", "quantize_graph_base"], [118, 0, 0, "-", "quantize_graph_bn"], [119, 0, 0, "-", "quantize_graph_concatv2"], [120, 0, 0, "-", "quantize_graph_conv"], [121, 0, 0, "-", "quantize_graph_for_intel_cpu"], [122, 0, 0, "-", "quantize_graph_matmul"], [123, 0, 0, "-", "quantize_graph_pooling"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat": [[98, 0, 0, "-", "fake_quantize"], [100, 0, 0, "-", "quantize_config"], [101, 0, 0, "-", "quantize_helper"], [102, 0, 0, "-", "quantize_layers"], [107, 0, 0, "-", "quantize_wrapper"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize": [[98, 1, 1, "", "FakeQuantize"], [98, 1, 1, "", "FakeQuantizeBase"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config": [[100, 1, 1, "", "QuantizeConfig"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper": [[101, 2, 1, "", "init_quantize_config"], [101, 2, 1, "", "qat_clone_function"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers": [[103, 0, 0, "-", "optimize_layer"], [104, 0, 0, "-", "quantize_layer_add"], [105, 0, 0, "-", "quantize_layer_base"], [106, 0, 0, "-", "quantize_layer_bn"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer": [[103, 2, 1, "", "config_quantizable_layers"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add": [[104, 1, 1, "", "QuantizeLayerAdd"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base": [[105, 1, 1, "", "QuantizeLayerBase"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn": [[106, 1, 1, "", "QuantizeLayerBatchNormalization"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper": [[107, 1, 1, "", "QuantizeWrapper"], [107, 1, 1, "", "QuantizeWrapperBase"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq": [[108, 0, 0, "-", "fuse_qdq_bn"], [109, 0, 0, "-", "fuse_qdq_concatv2"], [110, 0, 0, "-", "fuse_qdq_conv"], [111, 0, 0, "-", "fuse_qdq_deconv"], [112, 0, 0, "-", "fuse_qdq_in"], [113, 0, 0, "-", "fuse_qdq_matmul"], [114, 0, 0, "-", "fuse_qdq_pooling"], [116, 0, 0, "-", "optimize_qdq"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn": [[108, 1, 1, "", "FuseNodeStartWithFusedBatchNormV3"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2": [[109, 1, 1, "", "FuseNodeStartWithConcatV2"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv": [[110, 1, 1, "", "FuseNodeStartWithConv2d"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv": [[111, 1, 1, "", "FuseNodeStartWithDeconv2d"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in": [[112, 1, 1, "", "FuseNodeStartWithFusedInstanceNorm"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul": [[113, 1, 1, "", "FuseNodeStartWithMatmul"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling": [[114, 1, 1, "", "FuseNodeStartWithPooling"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq": [[116, 1, 1, "", "OptimizeQDQGraph"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base": [[117, 1, 1, "", "QuantizeGraphBase"], [117, 1, 1, "", "QuantizeNodeBase"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn": [[118, 1, 1, "", "FuseNodeStartWithFusedBatchNormV3"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2": [[119, 1, 1, "", "FuseNodeStartWithConcatV2"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv": [[120, 1, 1, "", "FuseNodeStartWithConv2d"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu": [[121, 1, 1, "", "QuantizeGraphForIntel"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul": [[122, 1, 1, "", "FuseNodeStartWithMatmul"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling": [[123, 1, 1, "", "FuseNodeStartWithPooling"]], "neural_compressor.adaptor.tf_utils.quantize_graph_common": [[124, 1, 1, "", "QuantizeGraphHelper"]], "neural_compressor.adaptor.tf_utils.smooth_quant_calibration": [[125, 1, 1, "", "SmoothQuantCalibration"], [125, 1, 1, "", "SmoothQuantCalibrationLLM"]], "neural_compressor.adaptor.tf_utils.smooth_quant_scaler": [[126, 1, 1, "", "SmoothQuantScaler"], [126, 1, 1, "", "SmoothQuantScalerLLM"]], "neural_compressor.adaptor.tf_utils.tf2onnx_converter": [[127, 1, 1, "", "TensorflowQDQToOnnxQDQConverter"]], "neural_compressor.adaptor.tf_utils.transform_graph": [[128, 0, 0, "-", "bias_correction"], [129, 0, 0, "-", "graph_transform_base"], [131, 0, 0, "-", "insert_logging"], [132, 0, 0, "-", "rerange_quantized_concat"]], "neural_compressor.adaptor.tf_utils.transform_graph.bias_correction": [[128, 1, 1, "", "BiasCorrection"]], "neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base": [[129, 1, 1, "", "GraphTransformBase"]], "neural_compressor.adaptor.tf_utils.transform_graph.insert_logging": [[131, 1, 1, "", "InsertLogging"]], "neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat": [[132, 1, 1, "", "RerangeQuantizedConcat"]], "neural_compressor.adaptor.tf_utils.util": [[133, 2, 1, "", "apply_inlining"], [133, 2, 1, "", "collate_tf_preds"], [133, 2, 1, "", "construct_function_from_graph_def"], [133, 2, 1, "", "disable_random"], [133, 2, 1, "", "fix_ref_type_of_graph_def"], [133, 2, 1, "", "generate_feed_dict"], [133, 2, 1, "", "get_estimator_graph"], [133, 2, 1, "", "get_graph_def"], [133, 2, 1, "", "get_input_output_node_names"], [133, 2, 1, "", "get_model_input_shape"], [133, 2, 1, "", "get_tensor_by_name"], [133, 2, 1, "", "get_tensor_val_from_graph_node"], [133, 2, 1, "", "get_weight_from_input_tensor"], [133, 2, 1, "", "int8_node_name_reverse"], [133, 2, 1, "", "is_ckpt_format"], [133, 2, 1, "", "is_saved_model_format"], [133, 2, 1, "", "iterator_sess_run"], [133, 2, 1, "", "parse_saved_model"], [133, 2, 1, "", "read_graph"], [133, 2, 1, "", "reconstruct_saved_model"], [133, 2, 1, "", "strip_equivalent_nodes"], [133, 2, 1, "", "strip_unused_nodes"], [133, 2, 1, "", "version1_eq_version2"], [133, 2, 1, "", "version1_gt_version2"], [133, 2, 1, "", "version1_gte_version2"], [133, 2, 1, "", "version1_lt_version2"], [133, 2, 1, "", "version1_lte_version2"], [133, 2, 1, "", "write_graph"]], "neural_compressor.adaptor.torch_utils": [[134, 0, 0, "-", "bf16_convert"], [135, 0, 0, "-", "hawq_metric"], [137, 0, 0, "-", "layer_wise_quant"], [142, 0, 0, "-", "model_wrapper"], [143, 0, 0, "-", "pattern_detector"], [144, 0, 0, "-", "symbolic_trace"], [145, 0, 0, "-", "util"]], "neural_compressor.adaptor.torch_utils.bf16_convert": [[134, 1, 1, "", "BF16ModuleWrapper"], [134, 2, 1, "", "Convert"]], "neural_compressor.adaptor.torch_utils.hawq_metric": [[135, 1, 1, "", "HessianTrace"], [135, 1, 1, "", "Node_collector"], [135, 2, 1, "", "compare_weights"], [135, 2, 1, "", "hawq_top"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant": [[138, 0, 0, "-", "modified_pickle"], [139, 0, 0, "-", "quantize"], [140, 0, 0, "-", "torch_load"], [141, 0, 0, "-", "utils"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle": [[138, 3, 1, "", "PickleError"], [138, 3, 1, "", "PicklingError"], [138, 3, 1, "", "UnpicklingError"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize": [[139, 1, 1, "", "LayerWiseQuant"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load": [[140, 2, 1, "", "load"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils": [[141, 2, 1, "", "dowload_hf_model"], [141, 2, 1, "", "get_children"], [141, 2, 1, "", "get_module"], [141, 2, 1, "", "get_named_children"], [141, 2, 1, "", "get_super_module_by_name"], [141, 2, 1, "", "load_empty_model"], [141, 2, 1, "", "load_layer_wise_quantized_model"], [141, 2, 1, "", "load_tensor"], [141, 2, 1, "", "load_tensor_from_shard"], [141, 2, 1, "", "update_module"]], "neural_compressor.adaptor.torch_utils.model_wrapper": [[142, 1, 1, "", "FakeAffineTensorQuantFunction"], [142, 1, 1, "", "MulLinear"], [142, 1, 1, "", "TEQLinearFakeQuant"]], "neural_compressor.adaptor.torch_utils.pattern_detector": [[143, 1, 1, "", "TransformerBasedModelBlockPatternDetector"]], "neural_compressor.adaptor.torch_utils.symbolic_trace": [[144, 2, 1, "", "symbolic_trace"], [144, 2, 1, "", "trace_and_fuse_sub_graph"]], "neural_compressor.adaptor.torch_utils.util": [[145, 2, 1, "", "append_attr"], [145, 2, 1, "", "auto_copy"], [145, 2, 1, "", "calculate_quant_min_max"], [145, 2, 1, "", "calibration"], [145, 2, 1, "", "check_cfg_and_qconfig"], [145, 2, 1, "", "collate_torch_preds"], [145, 2, 1, "", "collect_weight_info"], [145, 2, 1, "", "fetch_module"], [145, 2, 1, "", "forward_wrapper"], [145, 2, 1, "", "generate_activation_observer"], [145, 2, 1, "", "get_absorb_layers"], [145, 2, 1, "", "get_block_prefix"], [145, 2, 1, "", "get_depth"], [145, 2, 1, "", "get_dict_at_depth"], [145, 2, 1, "", "get_element_under_depth"], [145, 2, 1, "", "get_embedding_contiguous"], [145, 2, 1, "", "get_example_input"], [145, 2, 1, "", "get_fallback_order"], [145, 2, 1, "", "get_hidden_states"], [145, 2, 1, "", "get_module_input_output"], [145, 2, 1, "", "get_mse_order_per_fp32"], [145, 2, 1, "", "get_mse_order_per_int8"], [145, 2, 1, "", "get_op_type_by_name"], [145, 2, 1, "", "get_quantizable_ops_from_cfgs"], [145, 2, 1, "", "get_torch_version"], [145, 2, 1, "", "input2tuple"], [145, 2, 1, "", "is_fused_module"], [145, 2, 1, "", "match_datatype_pattern"], [145, 2, 1, "", "move_input_device"], [145, 2, 1, "", "paser_cfgs"], [145, 2, 1, "", "set_module"], [145, 2, 1, "", "simple_inference"], [145, 2, 1, "", "update_sq_scale"]], "neural_compressor.algorithm": [[146, 0, 0, "-", "algorithm"], [147, 0, 0, "-", "fast_bias_correction"], [149, 0, 0, "-", "smooth_quant"], [150, 0, 0, "-", "weight_correction"]], "neural_compressor.algorithm.algorithm": [[146, 1, 1, "", "ALGORITHMS"], [146, 1, 1, "", "Algorithm"], [146, 1, 1, "", "AlgorithmScheduler"], [146, 2, 1, "", "algorithm_registry"]], "neural_compressor.algorithm.fast_bias_correction": [[147, 1, 1, "", "FastBiasCorrection"]], "neural_compressor.algorithm.smooth_quant": [[149, 1, 1, "", "SmoothQuant"]], "neural_compressor.algorithm.weight_correction": [[150, 1, 1, "", "WeightCorrection"]], "neural_compressor.benchmark": [[151, 2, 1, "", "benchmark_with_raw_cmd"], [151, 2, 1, "", "call_one"], [151, 2, 1, "", "config_instance"], [151, 2, 1, "", "fit"], [151, 2, 1, "", "generate_prefix"], [151, 2, 1, "", "get_architecture"], [151, 2, 1, "", "get_bounded_threads"], [151, 2, 1, "", "get_core_ids"], [151, 2, 1, "", "get_physical_ids"], [151, 2, 1, "", "get_threads"], [151, 2, 1, "", "get_threads_per_core"], [151, 2, 1, "", "profile"], [151, 2, 1, "", "run_instance"], [151, 2, 1, "", "set_all_env_var"], [151, 2, 1, "", "set_env_var"], [151, 2, 1, "", "summary_benchmark"]], "neural_compressor.common": [[152, 0, 0, "-", "base_config"], [153, 0, 0, "-", "base_tuning"], [154, 0, 0, "-", "benchmark"], [156, 0, 0, "-", "tuning_param"], [158, 0, 0, "-", "utils"]], "neural_compressor.common.base_config": [[152, 1, 1, "", "BaseConfig"], [152, 1, 1, "", "ComposableConfig"], [152, 1, 1, "", "ConfigRegistry"], [152, 2, 1, "", "get_all_config_set_from_config_registry"], [152, 2, 1, "", "register_config"], [152, 2, 1, "", "register_supported_configs_for_fwk"]], "neural_compressor.common.base_config.BaseConfig": [[152, 4, 1, "", "name"], [152, 4, 1, "", "params_list"]], "neural_compressor.common.base_config.ComposableConfig": [[152, 4, 1, "", "config_list"]], "neural_compressor.common.base_tuning": [[153, 1, 1, "", "ConfigLoader"], [153, 1, 1, "", "ConfigSet"], [153, 1, 1, "", "EvaluationFuncWrapper"], [153, 1, 1, "", "Evaluator"], [153, 1, 1, "", "Sampler"], [153, 1, 1, "", "SequentialSampler"], [153, 1, 1, "", "TuningConfig"], [153, 1, 1, "", "TuningMonitor"], [153, 2, 1, "", "init_tuning"]], "neural_compressor.common.base_tuning.ConfigSet": [[153, 4, 1, "", "config_list"]], "neural_compressor.common.benchmark": [[154, 2, 1, "", "benchmark"], [154, 2, 1, "", "dump_numa_info"], [154, 2, 1, "", "format_list2str"], [154, 2, 1, "", "generate_prefix"], [154, 2, 1, "", "get_linux_numa_info"], [154, 2, 1, "", "get_numa_node"], [154, 2, 1, "", "get_reversed_numa_info"], [154, 2, 1, "", "get_windows_numa_info"], [154, 2, 1, "", "parse_str2list"], [154, 2, 1, "", "run_multi_instance_command"], [154, 2, 1, "", "set_cores_for_instance"], [154, 2, 1, "", "summary_latency_throughput"]], "neural_compressor.common.tuning_param": [[156, 1, 1, "", "ParamLevel"], [156, 1, 1, "", "TuningParam"]], "neural_compressor.common.tuning_param.ParamLevel": [[156, 4, 1, "", "MODEL_LEVEL"], [156, 4, 1, "", "OP_LEVEL"], [156, 4, 1, "", "OP_TYPE_LEVEL"]], "neural_compressor.common.utils": [[157, 0, 0, "-", "constants"], [159, 0, 0, "-", "logger"], [160, 0, 0, "-", "save_load"], [161, 0, 0, "-", "utility"]], "neural_compressor.common.utils.constants": [[157, 1, 1, "", "Mode"]], "neural_compressor.common.utils.logger": [[159, 1, 1, "", "Logger"], [159, 1, 1, "", "TuningLogger"]], "neural_compressor.common.utils.save_load": [[160, 2, 1, "", "load_config_mapping"], [160, 2, 1, "", "save_config_mapping"]], "neural_compressor.common.utils.utility": [[161, 1, 1, "", "CpuInfo"], [161, 1, 1, "", "LazyImport"], [161, 1, 1, "", "ProcessorType"], [161, 1, 1, "", "Statistics"], [161, 2, 1, "", "call_counter"], [161, 2, 1, "", "detect_processor_type_based_on_hw"], [161, 2, 1, "", "dump_elapsed_time"], [161, 2, 1, "", "get_workspace"], [161, 2, 1, "", "log_process"], [161, 2, 1, "", "set_random_seed"], [161, 2, 1, "", "set_resume_from"], [161, 2, 1, "", "set_tensorboard"], [161, 2, 1, "", "set_workspace"], [161, 2, 1, "", "singleton"]], "neural_compressor.compression": [[162, 0, 0, "-", "callbacks"], [164, 0, 0, "-", "distillation"], [167, 0, 0, "-", "hpo"], [170, 0, 0, "-", "pruner"]], "neural_compressor.compression.callbacks": [[162, 1, 1, "", "BaseCallbacks"], [162, 1, 1, "", "DistillationCallbacks"], [162, 1, 1, "", "PruningCallbacks"], [162, 1, 1, "", "QuantizationAwareTrainingCallbacks"]], "neural_compressor.compression.callbacks.DistillationCallbacks": [[162, 4, 1, "", "_epoch_ran"], [162, 4, 1, "", "best_model"], [162, 4, 1, "", "best_score"], [162, 4, 1, "", "eval_frequency"]], "neural_compressor.compression.distillation": [[163, 0, 0, "-", "criterions"], [165, 0, 0, "-", "optimizers"], [166, 0, 0, "-", "utility"]], "neural_compressor.compression.distillation.criterions": [[163, 1, 1, "", "Criterions"], [163, 1, 1, "", "IntermediateLayersKnowledgeDistillationLoss"], [163, 1, 1, "", "KnowledgeDistillationFramework"], [163, 1, 1, "", "KnowledgeDistillationLoss"], [163, 1, 1, "", "PyTorchCriterions"], [163, 1, 1, "", "PyTorchCrossEntropyLoss"], [163, 1, 1, "", "PyTorchIntermediateLayersKnowledgeDistillationLoss"], [163, 1, 1, "", "PyTorchIntermediateLayersKnowledgeDistillationLossWrapper"], [163, 1, 1, "", "PyTorchKnowledgeDistillationLoss"], [163, 1, 1, "", "PyTorchKnowledgeDistillationLossWrapper"], [163, 1, 1, "", "PyTorchSelfKnowledgeDistillationLoss"], [163, 1, 1, "", "PyTorchSelfKnowledgeDistillationLossWrapper"], [163, 1, 1, "", "SelfKnowledgeDistillationLoss"], [163, 1, 1, "", "TensorFlowCrossEntropyLoss"], [163, 1, 1, "", "TensorFlowSparseCategoricalCrossentropy"], [163, 1, 1, "", "TensorflowCriterions"], [163, 1, 1, "", "TensorflowKnowledgeDistillationLoss"], [163, 1, 1, "", "TensorflowKnowledgeDistillationLossExternal"], [163, 1, 1, "", "TensorflowKnowledgeDistillationLossWrapper"], [163, 2, 1, "", "criterion_registry"]], "neural_compressor.compression.distillation.optimizers": [[165, 1, 1, "", "Optimizers"], [165, 1, 1, "", "PyTorchOptimizers"], [165, 1, 1, "", "PyTorchSGD"], [165, 1, 1, "", "TensorFlowAdam"], [165, 1, 1, "", "TensorFlowAdamW"], [165, 1, 1, "", "TensorFlowSGD"], [165, 1, 1, "", "TensorflowOptimizers"], [165, 2, 1, "", "optimizer_registry"]], "neural_compressor.compression.distillation.utility": [[166, 2, 1, "", "get_activation"], [166, 2, 1, "", "record_output"]], "neural_compressor.compression.hpo": [[168, 0, 0, "-", "sa_optimizer"]], "neural_compressor.compression.pruner": [[169, 0, 0, "-", "criteria"], [172, 0, 0, "-", "model_slim"], [176, 0, 0, "-", "patterns"], [170, 2, 1, "", "prepare_pruning"], [183, 0, 0, "-", "pruners"], [188, 0, 0, "-", "pruning"], [189, 0, 0, "-", "regs"], [170, 2, 1, "", "save"], [190, 0, 0, "-", "schedulers"], [191, 0, 0, "-", "tf_criteria"], [192, 0, 0, "-", "utils"], [193, 0, 0, "-", "wanda"]], "neural_compressor.compression.pruner.criteria": [[169, 1, 1, "", "BlockMaskCriterion"], [169, 1, 1, "", "GradientCriterion"], [169, 1, 1, "", "MagnitudeCriterion"], [169, 1, 1, "", "PruningCriterion"], [169, 1, 1, "", "RetrainFreeCriterion"], [169, 1, 1, "", "SnipCriterion"], [169, 1, 1, "", "SnipMomentumCriterion"], [169, 2, 1, "", "get_criterion"], [169, 2, 1, "", "register_criterion"]], "neural_compressor.compression.pruner.criteria.BlockMaskCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.criteria.GradientCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.criteria.MagnitudeCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.criteria.PruningCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.criteria.RetrainFreeCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.criteria.SnipCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.criteria.SnipMomentumCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.model_slim": [[171, 0, 0, "-", "auto_slim"], [173, 0, 0, "-", "pattern_analyzer"], [174, 0, 0, "-", "weight_slim"]], "neural_compressor.compression.pruner.model_slim.auto_slim": [[171, 2, 1, "", "generate_ffn2_pruning_config"], [171, 2, 1, "", "generate_mha_pruning_config"], [171, 2, 1, "", "model_slim"], [171, 2, 1, "", "model_slim_ffn2"], [171, 2, 1, "", "model_slim_mha"], [171, 2, 1, "", "parse_auto_slim_config"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer": [[173, 1, 1, "", "ClassifierHeadSearcher"], [173, 1, 1, "", "ClassifierHeadSearcherTF"], [173, 1, 1, "", "JitBasicSearcher"], [173, 1, 1, "", "Linear2LinearSearcher"], [173, 1, 1, "", "RecipeSearcher"], [173, 1, 1, "", "SelfMHASearcher"], [173, 2, 1, "", "get_attributes"], [173, 2, 1, "", "get_common_module"], [173, 2, 1, "", "print_iterables"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcher": [[173, 4, 1, "", "device"], [173, 4, 1, "", "flatten_static_graph"], [173, 4, 1, "", "model"], [173, 4, 1, "", "static_graph"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcherTF": [[173, 4, 1, "", "device"], [173, 4, 1, "", "flatten_static_graph"], [173, 4, 1, "", "model"], [173, 4, 1, "", "static_graph"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher": [[173, 4, 1, "", "device"], [173, 4, 1, "", "flatten_static_graph"], [173, 4, 1, "", "model"], [173, 4, 1, "", "searching_results"], [173, 4, 1, "", "static_graph"], [173, 4, 1, "", "target_layers"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher": [[173, 4, 1, "", "current_pattern"], [173, 4, 1, "", "device"], [173, 4, 1, "", "flatten_static_graph"], [173, 4, 1, "", "model"], [173, 4, 1, "", "searching_results"], [173, 4, 1, "", "static_graph"], [173, 4, 1, "", "target_layers"], [173, 4, 1, "", "target_op_lut"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer.RecipeSearcher": [[173, 4, 1, "", "model"], [173, 4, 1, "", "recipe"], [173, 4, 1, "", "searching_results"], [173, 4, 1, "", "targets"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer.SelfMHASearcher": [[173, 4, 1, "", "device"], [173, 4, 1, "", "flatten_static_graph"], [173, 4, 1, "", "model"], [173, 4, 1, "", "static_graph"]], "neural_compressor.compression.pruner.model_slim.weight_slim": [[174, 1, 1, "", "LinearCompression"], [174, 1, 1, "", "LinearCompressionIterator"], [174, 1, 1, "", "PostCompressionUtils"]], "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompression": [[174, 4, 1, "", "device"], [174, 4, 1, "", "layer_1"], [174, 4, 1, "", "layer_2"]], "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompressionIterator": [[174, 4, 1, "", "linear_patterns"]], "neural_compressor.compression.pruner.patterns": [[175, 0, 0, "-", "base"], [176, 2, 1, "", "get_pattern"], [177, 0, 0, "-", "mha"], [178, 0, 0, "-", "ninm"], [179, 0, 0, "-", "nxm"]], "neural_compressor.compression.pruner.patterns.base": [[175, 1, 1, "", "BasePattern"], [175, 1, 1, "", "KerasBasePattern"], [175, 1, 1, "", "PytorchBasePattern"], [175, 2, 1, "", "register_pattern"]], "neural_compressor.compression.pruner.patterns.base.BasePattern": [[175, 4, 1, "", "config"], [175, 4, 1, "", "invalid_layers"], [175, 4, 1, "", "is_global"], [175, 4, 1, "", "keep_mask_layers"], [175, 4, 1, "", "max_sparsity_ratio_per_op"], [175, 4, 1, "", "min_sparsity_ratio_per_op"], [175, 4, 1, "", "modules"], [175, 4, 1, "", "pattern"], [175, 4, 1, "", "target_sparsity"]], "neural_compressor.compression.pruner.patterns.base.KerasBasePattern": [[175, 4, 1, "", "config"], [175, 4, 1, "", "invalid_layers"], [175, 4, 1, "", "is_global"], [175, 4, 1, "", "keep_mask_layers"], [175, 4, 1, "", "max_sparsity_ratio_per_op"], [175, 4, 1, "", "min_sparsity_ratio_per_op"], [175, 4, 1, "", "modules"], [175, 4, 1, "", "pattern"], [175, 4, 1, "", "target_sparsity"]], "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern": [[175, 4, 1, "", "config"], [175, 4, 1, "", "invalid_layers"], [175, 4, 1, "", "is_global"], [175, 4, 1, "", "keep_mask_layers"], [175, 4, 1, "", "max_sparsity_ratio_per_op"], [175, 4, 1, "", "min_sparsity_ratio_per_op"], [175, 4, 1, "", "modules"], [175, 4, 1, "", "pattern"], [175, 4, 1, "", "target_sparsity"]], "neural_compressor.compression.pruner.patterns.mha": [[177, 1, 1, "", "PatternMHA"]], "neural_compressor.compression.pruner.patterns.mha.PatternMHA": [[177, 4, 1, "", "M"], [177, 4, 1, "", "N"]], "neural_compressor.compression.pruner.patterns.ninm": [[178, 1, 1, "", "PytorchPatternNInM"]], "neural_compressor.compression.pruner.patterns.ninm.PytorchPatternNInM": [[178, 4, 1, "", "M"], [178, 4, 1, "", "N"]], "neural_compressor.compression.pruner.patterns.nxm": [[179, 1, 1, "", "KerasPatternNxM"], [179, 1, 1, "", "PytorchPatternNxM"]], "neural_compressor.compression.pruner.patterns.nxm.KerasPatternNxM": [[179, 4, 1, "", "block_size"]], "neural_compressor.compression.pruner.patterns.nxm.PytorchPatternNxM": [[179, 4, 1, "", "block_size"]], "neural_compressor.compression.pruner.pruners": [[180, 0, 0, "-", "base"], [181, 0, 0, "-", "basic"], [182, 0, 0, "-", "block_mask"], [183, 2, 1, "", "get_pruner"], [184, 0, 0, "-", "mha"], [183, 2, 1, "", "parse_valid_pruner_types"], [185, 0, 0, "-", "pattern_lock"], [186, 0, 0, "-", "progressive"], [187, 0, 0, "-", "retrain_free"]], "neural_compressor.compression.pruner.pruners.base": [[180, 1, 1, "", "BasePruner"], [180, 1, 1, "", "KerasBasePruner"], [180, 1, 1, "", "PytorchBasePruner"], [180, 2, 1, "", "register_pruner"]], "neural_compressor.compression.pruner.pruners.base.BasePruner": [[180, 4, 1, "", "config"], [180, 4, 1, "", "current_sparsity_ratio"], [180, 4, 1, "", "end_step"], [180, 4, 1, "", "global_step"], [180, 4, 1, "", "masks"], [180, 4, 1, "", "max_sparsity_ratio_per_op"], [180, 4, 1, "", "modules"], [180, 4, 1, "", "pattern"], [180, 4, 1, "", "pruning_frequency"], [180, 4, 1, "", "scheduler"], [180, 4, 1, "", "scores"], [180, 4, 1, "", "start_step"], [180, 4, 1, "", "target_sparsity_ratio"]], "neural_compressor.compression.pruner.pruners.base.KerasBasePruner": [[180, 4, 1, "", "config"], [180, 4, 1, "", "current_sparsity_ratio"], [180, 4, 1, "", "end_step"], [180, 4, 1, "", "global_step"], [180, 4, 1, "", "masks"], [180, 4, 1, "", "max_sparsity_ratio_per_op"], [180, 4, 1, "", "modules"], [180, 4, 1, "", "pattern"], [180, 4, 1, "", "pruning_frequency"], [180, 4, 1, "", "scheduler"], [180, 4, 1, "", "scores"], [180, 4, 1, "", "start_step"], [180, 4, 1, "", "target_sparsity_ratio"]], "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner": [[180, 4, 1, "", "config"], [180, 4, 1, "", "current_sparsity_ratio"], [180, 4, 1, "", "end_step"], [180, 4, 1, "", "global_step"], [180, 4, 1, "", "masks"], [180, 4, 1, "", "max_sparsity_ratio_per_op"], [180, 4, 1, "", "modules"], [180, 4, 1, "", "pattern"], [180, 4, 1, "", "pruning_frequency"], [180, 4, 1, "", "scheduler"], [180, 4, 1, "", "scores"], [180, 4, 1, "", "start_step"], [180, 4, 1, "", "target_sparsity_ratio"]], "neural_compressor.compression.pruner.pruners.basic": [[181, 1, 1, "", "KerasBasicPruner"], [181, 1, 1, "", "PytorchBasicPruner"]], "neural_compressor.compression.pruner.pruners.basic.KerasBasicPruner": [[181, 4, 1, "", "criterion"], [181, 4, 1, "", "pattern"], [181, 4, 1, "", "reg"], [181, 4, 1, "", "scheduler"]], "neural_compressor.compression.pruner.pruners.basic.PytorchBasicPruner": [[181, 4, 1, "", "criterion"], [181, 4, 1, "", "pattern"], [181, 4, 1, "", "reg"], [181, 4, 1, "", "scheduler"]], "neural_compressor.compression.pruner.pruners.block_mask": [[182, 1, 1, "", "PytorchBlockMaskPruner"]], "neural_compressor.compression.pruner.pruners.block_mask.PytorchBlockMaskPruner": [[182, 4, 1, "", "criterion"], [182, 4, 1, "", "pattern"], [182, 4, 1, "", "reg"], [182, 4, 1, "", "scheduler"]], "neural_compressor.compression.pruner.pruners.mha": [[184, 1, 1, "", "PythonMultiheadAttentionPruner"]], "neural_compressor.compression.pruner.pruners.mha.PythonMultiheadAttentionPruner": [[184, 4, 1, "", "head_masks"], [184, 4, 1, "", "linear_layers"], [184, 4, 1, "", "mha_compressions"], [184, 4, 1, "", "mha_scores"]], "neural_compressor.compression.pruner.pruners.pattern_lock": [[185, 1, 1, "", "PytorchPatternLockPruner"]], "neural_compressor.compression.pruner.pruners.progressive": [[186, 1, 1, "", "PytorchProgressivePruner"]], "neural_compressor.compression.pruner.pruners.retrain_free": [[187, 1, 1, "", "PytorchRetrainFreePruner"]], "neural_compressor.compression.pruner.pruners.retrain_free.PytorchRetrainFreePruner": [[187, 4, 1, "", "criterion"], [187, 4, 1, "", "pattern"], [187, 4, 1, "", "reg"], [187, 4, 1, "", "scheduler"]], "neural_compressor.compression.pruner.pruning": [[188, 1, 1, "", "BasePruning"], [188, 1, 1, "", "BasicPruning"], [188, 1, 1, "", "RetrainFreePruning"], [188, 1, 1, "", "SparseGPTPruning"], [188, 2, 1, "", "register_pruning"]], "neural_compressor.compression.pruner.pruning.BasePruning": [[188, 4, 1, "", "config_file_path"], [188, 4, 1, "", "model"], [188, 4, 1, "", "pruner_info"], [188, 4, 1, "", "pruners"]], "neural_compressor.compression.pruner.pruning.BasicPruning": [[188, 4, 1, "", "config_file_path"], [188, 4, 1, "", "model"], [188, 4, 1, "", "pruner_info"], [188, 4, 1, "", "pruners"]], "neural_compressor.compression.pruner.pruning.RetrainFreePruning": [[188, 4, 1, "", "config_file_path"], [188, 4, 1, "", "model"], [188, 4, 1, "", "pruner_info"], [188, 4, 1, "", "pruners"]], "neural_compressor.compression.pruner.regs": [[189, 1, 1, "", "BaseReg"], [189, 1, 1, "", "GroupLasso"], [189, 2, 1, "", "get_reg"], [189, 2, 1, "", "get_reg_type"], [189, 2, 1, "", "register_reg"]], "neural_compressor.compression.pruner.regs.GroupLasso": [[189, 4, 1, "", "alpha"], [189, 4, 1, "", "reg_terms"]], "neural_compressor.compression.pruner.schedulers": [[190, 1, 1, "", "IterativeScheduler"], [190, 1, 1, "", "OneshotScheduler"], [190, 1, 1, "", "PruningScheduler"], [190, 2, 1, "", "get_scheduler"], [190, 2, 1, "", "register_scheduler"]], "neural_compressor.compression.pruner.schedulers.PruningScheduler": [[190, 4, 1, "", "config"]], "neural_compressor.compression.pruner.tf_criteria": [[191, 1, 1, "", "MagnitudeCriterion"], [191, 1, 1, "", "PruningCriterion"], [191, 2, 1, "", "get_tf_criterion"], [191, 2, 1, "", "register_criterion"]], "neural_compressor.compression.pruner.tf_criteria.MagnitudeCriterion": [[191, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.tf_criteria.PruningCriterion": [[191, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.utils": [[192, 2, 1, "", "check_config"], [192, 2, 1, "", "check_key_validity"], [192, 2, 1, "", "collect_layer_inputs"], [192, 2, 1, "", "get_layers"], [192, 2, 1, "", "get_sparsity_ratio"], [192, 2, 1, "", "get_sparsity_ratio_tf"], [192, 2, 1, "", "parse_last_linear"], [192, 2, 1, "", "parse_last_linear_tf"], [192, 2, 1, "", "parse_to_prune"], [192, 2, 1, "", "parse_to_prune_tf"], [192, 2, 1, "", "process_and_check_config"], [192, 2, 1, "", "process_config"], [192, 2, 1, "", "process_weight_config"], [192, 2, 1, "", "process_yaml_config"], [192, 2, 1, "", "reset_none_to_default"], [192, 2, 1, "", "update_params"]], "neural_compressor.compression.pruner.wanda": [[194, 0, 0, "-", "utils"]], "neural_compressor.compression.pruner.wanda.utils": [[194, 2, 1, "", "find_layers"]], "neural_compressor.config": [[195, 1, 1, "", "AccuracyCriterion"], [195, 1, 1, "", "BenchmarkConfig"], [195, 1, 1, "", "DistillationConfig"], [195, 1, 1, "", "DotDict"], [195, 1, 1, "", "ExportConfig"], [195, 1, 1, "", "HPOConfig"], [195, 1, 1, "", "IntermediateLayersKnowledgeDistillationLossConfig"], [195, 1, 1, "", "Keras"], [195, 1, 1, "", "KnowledgeDistillationLossConfig"], [195, 1, 1, "", "MXNet"], [195, 1, 1, "", "MixedPrecisionConfig"], [195, 1, 1, "", "NASConfig"], [195, 1, 1, "", "ONNX"], [195, 1, 1, "", "ONNXQlinear2QDQConfig"], [195, 1, 1, "", "Options"], [195, 1, 1, "", "PostTrainingQuantConfig"], [195, 1, 1, "", "PyTorch"], [195, 1, 1, "", "QuantizationAwareTrainingConfig"], [195, 1, 1, "", "SelfKnowledgeDistillationLossConfig"], [195, 1, 1, "", "TF2ONNXConfig"], [195, 1, 1, "", "TensorFlow"], [195, 1, 1, "", "Torch2ONNXConfig"], [195, 1, 1, "", "TuningCriterion"], [195, 1, 1, "", "WeightPruningConfig"]], "neural_compressor.contrib": [[197, 0, 0, "-", "strategy"]], "neural_compressor.contrib.strategy": [[198, 0, 0, "-", "sigopt"], [199, 0, 0, "-", "tpe"]], "neural_compressor.contrib.strategy.sigopt": [[198, 1, 1, "", "SigOptTuneStrategy"]], "neural_compressor.contrib.strategy.tpe": [[199, 1, 1, "", "TpeTuneStrategy"]], "neural_compressor.data": [[215, 0, 0, "-", "datasets"], [219, 0, 0, "-", "filters"], [222, 0, 0, "-", "transforms"]], "neural_compressor.data.dataloaders": [[200, 0, 0, "-", "base_dataloader"], [201, 0, 0, "-", "dataloader"], [202, 0, 0, "-", "default_dataloader"], [203, 0, 0, "-", "fetcher"], [204, 0, 0, "-", "mxnet_dataloader"], [205, 0, 0, "-", "onnxrt_dataloader"], [206, 0, 0, "-", "pytorch_dataloader"], [207, 0, 0, "-", "sampler"], [208, 0, 0, "-", "tensorflow_dataloader"]], "neural_compressor.data.dataloaders.base_dataloader": [[200, 1, 1, "", "BaseDataLoader"]], "neural_compressor.data.dataloaders.dataloader": [[201, 1, 1, "", "DataLoader"], [201, 2, 1, "", "check_dataloader"]], "neural_compressor.data.dataloaders.default_dataloader": [[202, 1, 1, "", "DefaultDataLoader"], [202, 2, 1, "", "default_collate"]], "neural_compressor.data.dataloaders.fetcher": [[203, 1, 1, "", "Fetcher"], [203, 1, 1, "", "IndexFetcher"], [203, 1, 1, "", "IterableFetcher"]], "neural_compressor.data.dataloaders.mxnet_dataloader": [[204, 1, 1, "", "MXNetDataLoader"]], "neural_compressor.data.dataloaders.onnxrt_dataloader": [[205, 1, 1, "", "ONNXRTBertDataLoader"], [205, 1, 1, "", "ONNXRTDataLoader"]], "neural_compressor.data.dataloaders.pytorch_dataloader": [[206, 1, 1, "", "PyTorchDataLoader"]], "neural_compressor.data.dataloaders.sampler": [[207, 1, 1, "", "BatchSampler"], [207, 1, 1, "", "IterableSampler"], [207, 1, 1, "", "Sampler"], [207, 1, 1, "", "SequentialSampler"]], "neural_compressor.data.dataloaders.tensorflow_dataloader": [[208, 1, 1, "", "TFDataDataLoader"], [208, 1, 1, "", "TensorflowBertDataLoader"], [208, 1, 1, "", "TensorflowDataLoader"], [208, 1, 1, "", "TensorflowModelZooBertDataLoader"]], "neural_compressor.data.datasets": [[209, 0, 0, "-", "bert_dataset"], [210, 0, 0, "-", "coco_dataset"], [211, 0, 0, "-", "dataset"], [212, 0, 0, "-", "dummy_dataset"], [213, 0, 0, "-", "dummy_dataset_v2"], [214, 0, 0, "-", "imagenet_dataset"], [216, 0, 0, "-", "style_transfer_dataset"]], "neural_compressor.data.datasets.bert_dataset": [[209, 1, 1, "", "InputFeatures"], [209, 1, 1, "", "ONNXRTBertDataset"], [209, 1, 1, "", "ParseDecodeBert"], [209, 1, 1, "", "PytorchBertDataset"], [209, 1, 1, "", "TensorflowBertDataset"], [209, 1, 1, "", "TensorflowModelZooBertDataset"], [209, 2, 1, "", "convert_examples_to_features"], [209, 2, 1, "", "load_and_cache_examples"]], "neural_compressor.data.datasets.coco_dataset": [[210, 1, 1, "", "COCONpy"], [210, 1, 1, "", "COCORaw"], [210, 1, 1, "", "COCORecordDataset"], [210, 1, 1, "", "ParseDecodeCoco"]], "neural_compressor.data.datasets.dataset": [[211, 1, 1, "", "CIFAR10"], [211, 1, 1, "", "CIFAR100"], [211, 1, 1, "", "Dataset"], [211, 1, 1, "", "Datasets"], [211, 1, 1, "", "FashionMNIST"], [211, 1, 1, "", "ImageFolder"], [211, 1, 1, "", "IterableDataset"], [211, 1, 1, "", "MNIST"], [211, 1, 1, "", "MXNetCIFAR10"], [211, 1, 1, "", "MXNetCIFAR100"], [211, 1, 1, "", "MXNetDatasets"], [211, 1, 1, "", "MXNetFashionMNIST"], [211, 1, 1, "", "MXNetImageFolder"], [211, 1, 1, "", "MXNetMNIST"], [211, 1, 1, "", "ONNXRTITDatasets"], [211, 1, 1, "", "ONNXRTQLDatasets"], [211, 1, 1, "", "PyTorchDatasets"], [211, 1, 1, "", "PytorchCIFAR10"], [211, 1, 1, "", "PytorchCIFAR100"], [211, 1, 1, "", "PytorchFashionMNIST"], [211, 1, 1, "", "PytorchMNIST"], [211, 1, 1, "", "PytorchMxnetWrapDataset"], [211, 1, 1, "", "PytorchMxnetWrapFunction"], [211, 1, 1, "", "Tensorflow"], [211, 1, 1, "", "TensorflowCIFAR10"], [211, 1, 1, "", "TensorflowCIFAR100"], [211, 1, 1, "", "TensorflowDatasets"], [211, 1, 1, "", "TensorflowFashionMNIST"], [211, 1, 1, "", "TensorflowImageRecord"], [211, 1, 1, "", "TensorflowMNIST"], [211, 1, 1, "", "TensorflowTFRecordDataset"], [211, 1, 1, "", "TensorflowVOCRecord"], [211, 2, 1, "", "calculate_md5"], [211, 2, 1, "", "check_integrity"], [211, 2, 1, "", "dataset_registry"], [211, 2, 1, "", "download_url"], [211, 5, 1, "", "framework_datasets"], [211, 2, 1, "", "gen_bar_updater"]], "neural_compressor.data.datasets.dummy_dataset": [[212, 1, 1, "", "DummyDataset"]], "neural_compressor.data.datasets.dummy_dataset_v2": [[213, 1, 1, "", "DummyDataset"], [213, 1, 1, "", "SparseDummyDataset"]], "neural_compressor.data.datasets.imagenet_dataset": [[214, 1, 1, "", "ImagenetRaw"], [214, 1, 1, "", "MXNetImagenetRaw"], [214, 1, 1, "", "ONNXRTImagenetDataset"], [214, 1, 1, "", "PytorchImagenetRaw"], [214, 1, 1, "", "TensorflowImagenetDataset"], [214, 1, 1, "", "TensorflowImagenetRaw"]], "neural_compressor.data.datasets.style_transfer_dataset": [[216, 1, 1, "", "StyleTransferDataset"]], "neural_compressor.data.filters": [[217, 0, 0, "-", "coco_filter"], [218, 0, 0, "-", "filter"]], "neural_compressor.data.filters.coco_filter": [[217, 1, 1, "", "LabelBalanceCOCORawFilter"], [217, 1, 1, "", "LabelBalanceCOCORecordFilter"]], "neural_compressor.data.filters.filter": [[218, 1, 1, "", "FILTERS"], [218, 1, 1, "", "Filter"], [218, 1, 1, "", "MXNetFilters"], [218, 1, 1, "", "ONNXRTITFilters"], [218, 1, 1, "", "ONNXRTQLFilters"], [218, 1, 1, "", "PyTorchFilters"], [218, 1, 1, "", "TensorflowFilters"], [218, 2, 1, "", "filter_registry"]], "neural_compressor.data.transforms": [[221, 0, 0, "-", "imagenet_transform"], [223, 0, 0, "-", "postprocess"], [224, 0, 0, "-", "tokenization"], [225, 0, 0, "-", "transform"]], "neural_compressor.data.transforms.imagenet_transform": [[221, 1, 1, "", "BilinearImagenetTransform"], [221, 1, 1, "", "LabelShift"], [221, 1, 1, "", "ONNXResizeCropImagenetTransform"], [221, 1, 1, "", "OnnxBilinearImagenetTransform"], [221, 1, 1, "", "ParseDecodeImagenet"], [221, 1, 1, "", "ParseDecodeImagenetTransform"], [221, 1, 1, "", "QuantizedInput"], [221, 1, 1, "", "ResizeWithAspectRatio"], [221, 1, 1, "", "TensorflowResizeCropImagenetTransform"], [221, 1, 1, "", "TensorflowShiftRescale"], [221, 1, 1, "", "TensorflowTransposeLastChannel"]], "neural_compressor.data.transforms.postprocess": [[223, 1, 1, "", "Postprocess"]], "neural_compressor.data.transforms.tokenization": [[224, 1, 1, "", "BasicTokenizer"], [224, 1, 1, "", "FullTokenizer"], [224, 1, 1, "", "WordpieceTokenizer"], [224, 2, 1, "", "convert_by_vocab"], [224, 2, 1, "", "convert_to_unicode"], [224, 2, 1, "", "load_vocab"], [224, 2, 1, "", "whitespace_tokenize"]], "neural_compressor.data.transforms.transform": [[225, 1, 1, "", "AlignImageChannelTransform"], [225, 1, 1, "", "BaseTransform"], [225, 1, 1, "", "CastONNXTransform"], [225, 1, 1, "", "CastPyTorchTransform"], [225, 1, 1, "", "CastTFTransform"], [225, 1, 1, "", "CenterCropTFTransform"], [225, 1, 1, "", "CenterCropTransform"], [225, 1, 1, "", "CollectTransform"], [225, 1, 1, "", "ComposeTransform"], [225, 1, 1, "", "CropResizeTFTransform"], [225, 1, 1, "", "CropResizeTransform"], [225, 1, 1, "", "CropToBoundingBox"], [225, 1, 1, "", "InputFeatures"], [225, 1, 1, "", "MXNetCropResizeTransform"], [225, 1, 1, "", "MXNetCropToBoundingBox"], [225, 1, 1, "", "MXNetNormalizeTransform"], [225, 1, 1, "", "MXNetTransforms"], [225, 1, 1, "", "MXNetTranspose"], [225, 1, 1, "", "NormalizeTFTransform"], [225, 1, 1, "", "NormalizeTransform"], [225, 1, 1, "", "ONNXRTCropToBoundingBox"], [225, 1, 1, "", "ONNXRTITTransforms"], [225, 1, 1, "", "ONNXRTQLTransforms"], [225, 1, 1, "", "PaddedCenterCropTransform"], [225, 1, 1, "", "ParseDecodeVocTransform"], [225, 1, 1, "", "PyTorchAlignImageChannel"], [225, 1, 1, "", "PyTorchCropResizeTransform"], [225, 1, 1, "", "PyTorchNormalizeTransform"], [225, 1, 1, "", "PyTorchTransforms"], [225, 1, 1, "", "PyTorchTranspose"], [225, 1, 1, "", "PytorchMxnetTransform"], [225, 1, 1, "", "PytorchMxnetWrapFunction"], [225, 1, 1, "", "RandomCropTFTransform"], [225, 1, 1, "", "RandomCropTransform"], [225, 1, 1, "", "RandomHorizontalFlip"], [225, 1, 1, "", "RandomResizedCropMXNetTransform"], [225, 1, 1, "", "RandomResizedCropPytorchTransform"], [225, 1, 1, "", "RandomResizedCropTFTransform"], [225, 1, 1, "", "RandomResizedCropTransform"], [225, 1, 1, "", "RandomVerticalFlip"], [225, 1, 1, "", "RescaleKerasPretrainTransform"], [225, 1, 1, "", "RescaleTFTransform"], [225, 1, 1, "", "RescaleTransform"], [225, 1, 1, "", "ResizeMXNetTransform"], [225, 1, 1, "", "ResizePytorchTransform"], [225, 1, 1, "", "ResizeTFTransform"], [225, 1, 1, "", "ResizeTransform"], [225, 1, 1, "", "ResizeWithRatio"], [225, 1, 1, "", "SquadExample"], [225, 1, 1, "", "TFModelZooCollectTransform"], [225, 1, 1, "", "TFSquadV1ModelZooPostTransform"], [225, 1, 1, "", "TFSquadV1PostTransform"], [225, 1, 1, "", "TRANSFORMS"], [225, 1, 1, "", "TensorflowCropToBoundingBox"], [225, 1, 1, "", "TensorflowRandomHorizontalFlip"], [225, 1, 1, "", "TensorflowRandomVerticalFlip"], [225, 1, 1, "", "TensorflowResizeWithRatio"], [225, 1, 1, "", "TensorflowTransform"], [225, 1, 1, "", "TensorflowTransforms"], [225, 1, 1, "", "TensorflowTranspose"], [225, 1, 1, "", "TensorflowWrapFunction"], [225, 1, 1, "", "ToArray"], [225, 1, 1, "", "ToNDArrayTransform"], [225, 1, 1, "", "Transforms"], [225, 1, 1, "", "Transpose"], [225, 2, 1, "", "convert_examples_to_features"], [225, 2, 1, "", "get_final_text"], [225, 2, 1, "", "get_torchvision_map"], [225, 2, 1, "", "read_squad_examples"], [225, 2, 1, "", "transform_registry"]], "neural_compressor.metric": [[227, 0, 0, "-", "bleu"], [228, 0, 0, "-", "bleu_util"], [229, 0, 0, "-", "coco_label_map"], [230, 0, 0, "-", "coco_tools"], [231, 0, 0, "-", "evaluate_squad"], [232, 0, 0, "-", "f1"], [234, 0, 0, "-", "metric"]], "neural_compressor.metric.bleu": [[227, 1, 1, "", "BLEU"], [227, 1, 1, "", "UnicodeRegex"], [227, 2, 1, "", "bleu_tokenize"]], "neural_compressor.metric.bleu.BLEU": [[227, 4, 1, "", "labels"], [227, 4, 1, "", "predictions"]], "neural_compressor.metric.bleu.UnicodeRegex": [[227, 4, 1, "", "nondigit_punct_re"], [227, 4, 1, "", "punct_nondigit_re"], [227, 4, 1, "", "symbol_re"]], "neural_compressor.metric.bleu_util": [[228, 2, 1, "", "compute_bleu"]], "neural_compressor.metric.coco_tools": [[230, 1, 1, "", "COCOEvalWrapper"], [230, 1, 1, "", "COCOWrapper"], [230, 2, 1, "", "ExportSingleImageDetectionBoxesToCoco"], [230, 2, 1, "", "ExportSingleImageDetectionMasksToCoco"], [230, 2, 1, "", "ExportSingleImageGroundtruthToCoco"]], "neural_compressor.metric.coco_tools.COCOWrapper": [[230, 4, 1, "", "dataset"], [230, 4, 1, "", "detection_type"]], "neural_compressor.metric.evaluate_squad": [[231, 2, 1, "", "evaluate"], [231, 2, 1, "", "exact_match_score"], [231, 2, 1, "", "f1_score"], [231, 2, 1, "", "metric_max_over_ground_truths"]], "neural_compressor.metric.f1": [[232, 2, 1, "", "evaluate"], [232, 2, 1, "", "f1_score"], [232, 2, 1, "", "metric_max_over_ground_truths"], [232, 2, 1, "", "normalize_answer"]], "neural_compressor.metric.metric": [[234, 1, 1, "", "Accuracy"], [234, 1, 1, "", "BaseMetric"], [234, 1, 1, "", "COCOmAPv2"], [234, 1, 1, "", "F1"], [234, 1, 1, "", "GeneralTopK"], [234, 1, 1, "", "Loss"], [234, 1, 1, "", "MAE"], [234, 1, 1, "", "METRICS"], [234, 1, 1, "", "MSE"], [234, 1, 1, "", "MXNetMetrics"], [234, 1, 1, "", "Metric"], [234, 1, 1, "", "ONNXRTGLUE"], [234, 1, 1, "", "ONNXRTITMetrics"], [234, 1, 1, "", "ONNXRTQLMetrics"], [234, 1, 1, "", "PyTorchLoss"], [234, 1, 1, "", "PyTorchMetrics"], [234, 1, 1, "", "RMSE"], [234, 1, 1, "", "ROC"], [234, 1, 1, "", "SquadF1"], [234, 1, 1, "", "TensorflowCOCOMAP"], [234, 1, 1, "", "TensorflowMAP"], [234, 1, 1, "", "TensorflowMetrics"], [234, 1, 1, "", "TensorflowTopK"], [234, 1, 1, "", "TensorflowVOCMAP"], [234, 1, 1, "", "WrapMXNetMetric"], [234, 1, 1, "", "WrapONNXRTMetric"], [234, 1, 1, "", "WrapPyTorchMetric"], [234, 1, 1, "", "mIOU"], [234, 2, 1, "", "metric_registry"], [234, 2, 1, "", "register_customer_metric"]], "neural_compressor.metric.metric.Accuracy": [[234, 4, 1, "", "label_list"], [234, 4, 1, "", "pred_list"], [234, 4, 1, "", "sample"]], "neural_compressor.metric.metric.GeneralTopK": [[234, 4, 1, "", "k"], [234, 4, 1, "", "num_correct"], [234, 4, 1, "", "num_sample"]], "neural_compressor.metric.metric.Loss": [[234, 4, 1, "", "sample"], [234, 4, 1, "", "sum"]], "neural_compressor.metric.metric.MAE": [[234, 4, 1, "", "compare_label"], [234, 4, 1, "", "label_list"], [234, 4, 1, "", "pred_list"]], "neural_compressor.metric.metric.METRICS": [[234, 4, 1, "", "metrics"]], "neural_compressor.metric.metric.MSE": [[234, 4, 1, "", "compare_label"], [234, 4, 1, "", "label_list"], [234, 4, 1, "", "pred_list"]], "neural_compressor.metric.metric.MXNetMetrics": [[234, 4, 1, "", "metrics"]], "neural_compressor.metric.metric.ONNXRTITMetrics": [[234, 4, 1, "", "metrics"]], "neural_compressor.metric.metric.ONNXRTQLMetrics": [[234, 4, 1, "", "metrics"]], "neural_compressor.metric.metric.PyTorchMetrics": [[234, 4, 1, "", "metrics"]], "neural_compressor.metric.metric.RMSE": [[234, 4, 1, "", "mse"]], "neural_compressor.metric.metric.TensorflowMetrics": [[234, 4, 1, "", "metrics"]], "neural_compressor.metric.metric.TensorflowTopK": [[234, 4, 1, "", "k"], [234, 4, 1, "", "num_correct"], [234, 4, 1, "", "num_sample"]], "neural_compressor.mix_precision": [[235, 2, 1, "", "fit"]], "neural_compressor.model": [[236, 0, 0, "-", "base_model"], [238, 0, 0, "-", "keras_model"], [239, 0, 0, "-", "model"], [240, 0, 0, "-", "mxnet_model"], [241, 0, 0, "-", "nets_factory"], [242, 0, 0, "-", "onnx_model"], [243, 0, 0, "-", "tensorflow_model"], [244, 0, 0, "-", "torch_model"]], "neural_compressor.model.base_model": [[236, 1, 1, "", "BaseModel"]], "neural_compressor.model.keras_model": [[238, 1, 1, "", "KerasModel"]], "neural_compressor.model.model": [[239, 1, 1, "", "Model"], [239, 2, 1, "", "get_model_fwk_name"]], "neural_compressor.model.mxnet_model": [[240, 1, 1, "", "MXNetModel"]], "neural_compressor.model.nets_factory": [[241, 1, 1, "", "TFSlimNetsFactory"]], "neural_compressor.model.onnx_model": [[242, 1, 1, "", "ONNXModel"]], "neural_compressor.model.tensorflow_model": [[243, 1, 1, "", "TensorflowBaseModel"], [243, 1, 1, "", "TensorflowCheckpointModel"], [243, 1, 1, "", "TensorflowLLMModel"], [243, 1, 1, "", "TensorflowModel"], [243, 1, 1, "", "TensorflowQATModel"], [243, 1, 1, "", "TensorflowSavedModelModel"], [243, 2, 1, "", "checkpoint_session"], [243, 2, 1, "", "estimator_session"], [243, 2, 1, "", "frozen_pb_session"], [243, 2, 1, "", "get_model_type"], [243, 2, 1, "", "graph_def_session"], [243, 2, 1, "", "graph_session"], [243, 2, 1, "", "keras_session"], [243, 2, 1, "", "load_saved_model"], [243, 2, 1, "", "saved_model_session"], [243, 2, 1, "", "slim_session"], [243, 2, 1, "", "try_loading_keras"], [243, 2, 1, "", "validate_and_inference_input_output"], [243, 2, 1, "", "validate_graph_node"]], "neural_compressor.model.torch_model": [[244, 1, 1, "", "IPEXModel"], [244, 1, 1, "", "PyTorchBaseModel"], [244, 1, 1, "", "PyTorchFXModel"], [244, 1, 1, "", "PyTorchModel"]], "neural_compressor.objective": [[245, 1, 1, "", "Accuracy"], [245, 1, 1, "", "Footprint"], [245, 1, 1, "", "ModelSize"], [245, 1, 1, "", "MultiObjective"], [245, 1, 1, "", "Objective"], [245, 1, 1, "", "Performance"], [245, 2, 1, "", "objective_custom_registry"], [245, 2, 1, "", "objective_registry"]], "neural_compressor.profiling.parser": [[247, 0, 0, "-", "factory"], [250, 0, 0, "-", "parser"], [251, 0, 0, "-", "result"]], "neural_compressor.profiling.parser.factory": [[247, 1, 1, "", "ParserFactory"]], "neural_compressor.profiling.parser.onnx_parser": [[248, 0, 0, "-", "factory"], [249, 0, 0, "-", "parser"]], "neural_compressor.profiling.parser.onnx_parser.factory": [[248, 1, 1, "", "OnnxrtParserFactory"]], "neural_compressor.profiling.parser.onnx_parser.parser": [[249, 1, 1, "", "OnnxProfilingParser"]], "neural_compressor.profiling.parser.parser": [[250, 1, 1, "", "ProfilingParser"]], "neural_compressor.profiling.parser.result": [[251, 1, 1, "", "ProfilingResult"]], "neural_compressor.profiling.parser.tensorflow_parser": [[252, 0, 0, "-", "factory"], [253, 0, 0, "-", "parser"]], "neural_compressor.profiling.parser.tensorflow_parser.factory": [[252, 1, 1, "", "TensorFlowParserFactory"]], "neural_compressor.profiling.parser.tensorflow_parser.parser": [[253, 1, 1, "", "TensorFlowProfilingParser"]], "neural_compressor.profiling.profiler": [[254, 0, 0, "-", "factory"], [258, 0, 0, "-", "profiler"]], "neural_compressor.profiling.profiler.factory": [[254, 1, 1, "", "ProfilerFactory"]], "neural_compressor.profiling.profiler.onnxrt_profiler": [[255, 0, 0, "-", "factory"], [256, 0, 0, "-", "profiler"], [257, 0, 0, "-", "utils"]], "neural_compressor.profiling.profiler.onnxrt_profiler.factory": [[255, 1, 1, "", "ProfilerFactory"]], "neural_compressor.profiling.profiler.onnxrt_profiler.profiler": [[256, 1, 1, "", "Profiler"]], "neural_compressor.profiling.profiler.onnxrt_profiler.utils": [[257, 2, 1, "", "create_onnx_config"]], "neural_compressor.profiling.profiler.profiler": [[258, 1, 1, "", "Profiler"]], "neural_compressor.profiling.profiler.tensorflow_profiler": [[259, 0, 0, "-", "factory"], [260, 0, 0, "-", "profiler"], [261, 0, 0, "-", "utils"]], "neural_compressor.profiling.profiler.tensorflow_profiler.factory": [[259, 1, 1, "", "ProfilerFactory"]], "neural_compressor.profiling.profiler.tensorflow_profiler.profiler": [[260, 1, 1, "", "Profiler"]], "neural_compressor.profiling.profiler.tensorflow_profiler.utils": [[261, 2, 1, "", "create_tf_config"], [261, 2, 1, "", "delete_assign"], [261, 2, 1, "", "set_eager_execution"]], "neural_compressor.quantization": [[262, 2, 1, "", "fit"]], "neural_compressor.strategy": [[263, 0, 0, "-", "auto"], [264, 0, 0, "-", "auto_mixed_precision"], [265, 0, 0, "-", "basic"], [266, 0, 0, "-", "bayesian"], [267, 0, 0, "-", "conservative"], [268, 0, 0, "-", "exhaustive"], [269, 0, 0, "-", "hawq_v2"], [271, 0, 0, "-", "mse"], [272, 0, 0, "-", "mse_v2"], [273, 0, 0, "-", "random"], [274, 0, 0, "-", "strategy"], [276, 0, 0, "-", "utils"]], "neural_compressor.strategy.auto": [[263, 1, 1, "", "AutoTuneStrategy"]], "neural_compressor.strategy.auto_mixed_precision": [[264, 1, 1, "", "AutoMixedPrecisionTuneStrategy"]], "neural_compressor.strategy.basic": [[265, 1, 1, "", "BasicTuneStrategy"]], "neural_compressor.strategy.bayesian": [[266, 1, 1, "", "BayesianOptimization"], [266, 1, 1, "", "BayesianTuneStrategy"], [266, 1, 1, "", "TargetSpace"], [266, 2, 1, "", "acq_max"]], "neural_compressor.strategy.conservative": [[267, 1, 1, "", "ConservativeTuneStrategy"]], "neural_compressor.strategy.exhaustive": [[268, 1, 1, "", "ExhaustiveTuneStrategy"]], "neural_compressor.strategy.hawq_v2": [[269, 1, 1, "", "HAWQ_V2TuneStrategy"]], "neural_compressor.strategy.mse": [[271, 1, 1, "", "MSETuneStrategy"]], "neural_compressor.strategy.mse_v2": [[272, 1, 1, "", "MSE_V2TuneStrategy"]], "neural_compressor.strategy.random": [[273, 1, 1, "", "RandomTuneStrategy"]], "neural_compressor.strategy.strategy": [[274, 1, 1, "", "TuneStrategy"], [274, 1, 1, "", "TuneStrategyMeta"], [274, 2, 1, "", "strategy_registry"]], "neural_compressor.strategy.utils": [[275, 0, 0, "-", "constant"], [277, 0, 0, "-", "tuning_sampler"], [278, 0, 0, "-", "tuning_space"], [279, 0, 0, "-", "tuning_structs"], [280, 0, 0, "-", "utility"]], "neural_compressor.strategy.utils.tuning_sampler": [[277, 1, 1, "", "BlockFallbackTuningSampler"], [277, 1, 1, "", "FallbackTuningSampler"], [277, 1, 1, "", "LowerBitsSampler"], [277, 1, 1, "", "ModelWiseTuningSampler"], [277, 1, 1, "", "OpTypeWiseTuningSampler"], [277, 1, 1, "", "OpWiseTuningSampler"], [277, 1, 1, "", "SmoothQuantSampler"], [277, 1, 1, "", "TuningOrder"], [277, 1, 1, "", "TuningSampler"], [277, 1, 1, "", "WeightOnlyQuantSampler"]], "neural_compressor.strategy.utils.tuning_space": [[278, 1, 1, "", "TuningItem"], [278, 1, 1, "", "TuningSpace"], [278, 2, 1, "", "initial_tuning_cfg_with_quant_mode"], [278, 2, 1, "", "pattern_to_internal"], [278, 2, 1, "", "pattern_to_path"], [278, 2, 1, "", "quant_mode_from_pattern"]], "neural_compressor.strategy.utils.tuning_structs": [[279, 1, 1, "", "OpTuningConfig"]], "neural_compressor.strategy.utils.utility": [[280, 1, 1, "", "ClassRegister"], [280, 1, 1, "", "OrderedDefaultDict"], [280, 1, 1, "", "QuantOptions"], [280, 1, 1, "", "QuantType"], [280, 2, 1, "", "build_slave_faker_model"], [280, 2, 1, "", "extract_data_type"], [280, 2, 1, "", "get_adaptor_name"], [280, 2, 1, "", "preprocess_user_cfg"], [280, 2, 1, "", "reverted_data_type"]], "neural_compressor.template": [[281, 0, 0, "-", "api_doc_example"]], "neural_compressor.template.api_doc_example": [[281, 1, 1, "", "ExampleClass"], [281, 4, 1, "", "attribute1"], [281, 2, 1, "", "function1"], [281, 2, 1, "", "function2"], [281, 2, 1, "", "function3"], [281, 2, 1, "", "generator1"], [281, 5, 1, "", "module_debug_level1"]], "neural_compressor.template.api_doc_example.ExampleClass": [[281, 4, 1, "", "attr1"], [281, 4, 1, "", "attr2"], [281, 4, 1, "", "attr5"]], "neural_compressor.tensorflow": [[282, 0, 0, "-", "algorithms"], [291, 0, 0, "-", "keras"], [304, 0, 0, "-", "quantization"], [388, 0, 0, "-", "utils"]], "neural_compressor.tensorflow.algorithms": [[285, 0, 0, "-", "smoother"], [287, 0, 0, "-", "static_quant"]], "neural_compressor.tensorflow.algorithms.smoother": [[283, 0, 0, "-", "calibration"], [284, 0, 0, "-", "core"], [286, 0, 0, "-", "scaler"]], "neural_compressor.tensorflow.algorithms.smoother.calibration": [[283, 1, 1, "", "SmoothQuantCalibration"], [283, 1, 1, "", "SmoothQuantCalibrationLLM"]], "neural_compressor.tensorflow.algorithms.smoother.core": [[284, 1, 1, "", "SmoothQuant"]], "neural_compressor.tensorflow.algorithms.smoother.scaler": [[286, 1, 1, "", "SmoothQuantScaler"], [286, 1, 1, "", "SmoothQuantScalerLLM"]], "neural_compressor.tensorflow.algorithms.static_quant": [[288, 0, 0, "-", "keras"], [289, 0, 0, "-", "tensorflow"]], "neural_compressor.tensorflow.algorithms.static_quant.keras": [[288, 1, 1, "", "KerasAdaptor"], [288, 1, 1, "", "KerasConfigConverter"], [288, 1, 1, "", "KerasQuery"], [288, 1, 1, "", "KerasSurgery"]], "neural_compressor.tensorflow.algorithms.static_quant.tensorflow": [[289, 1, 1, "", "TensorFlowAdaptor"], [289, 1, 1, "", "TensorFlowConfig"], [289, 1, 1, "", "TensorflowConfigConverter"], [289, 1, 1, "", "TensorflowQuery"], [289, 1, 1, "", "Tensorflow_ITEXAdaptor"]], "neural_compressor.tensorflow.keras": [[295, 0, 0, "-", "layers"], [300, 0, 0, "-", "quantization"]], "neural_compressor.tensorflow.keras.layers": [[292, 0, 0, "-", "conv2d"], [293, 0, 0, "-", "dense"], [294, 0, 0, "-", "depthwise_conv2d"], [296, 0, 0, "-", "layer_initializer"], [297, 0, 0, "-", "pool2d"], [298, 0, 0, "-", "separable_conv2d"]], "neural_compressor.tensorflow.keras.layers.conv2d": [[292, 1, 1, "", "QConv2D"], [292, 2, 1, "", "initialize_int8_conv2d"]], "neural_compressor.tensorflow.keras.layers.dense": [[293, 1, 1, "", "QDense"], [293, 2, 1, "", "initialize_int8_dense"]], "neural_compressor.tensorflow.keras.layers.depthwise_conv2d": [[294, 1, 1, "", "QDepthwiseConv2D"], [294, 2, 1, "", "initialize_int8_depthwise_conv2d"]], "neural_compressor.tensorflow.keras.layers.pool2d": [[297, 1, 1, "", "QAvgPool2D"], [297, 1, 1, "", "QMaxPool2D"], [297, 2, 1, "", "initialize_int8_avgpool"], [297, 2, 1, "", "initialize_int8_maxpool"]], "neural_compressor.tensorflow.keras.layers.separable_conv2d": [[298, 1, 1, "", "QSeparableConv2D"], [298, 2, 1, "", "initialize_int8_separable_conv2d"]], "neural_compressor.tensorflow.keras.quantization": [[299, 0, 0, "-", "config"]], "neural_compressor.tensorflow.keras.quantization.config": [[299, 1, 1, "", "OperatorConfig"], [299, 1, 1, "", "StaticQuantConfig"], [299, 2, 1, "", "get_all_registered_configs"], [299, 2, 1, "", "get_default_static_quant_config"]], "neural_compressor.tensorflow.quantization": [[301, 0, 0, "-", "algorithm_entry"], [302, 0, 0, "-", "autotune"], [303, 0, 0, "-", "config"], [305, 0, 0, "-", "quantize"], [361, 0, 0, "-", "utils"]], "neural_compressor.tensorflow.quantization.algorithm_entry": [[301, 2, 1, "", "smooth_quant_entry"], [301, 2, 1, "", "static_quant_entry"]], "neural_compressor.tensorflow.quantization.autotune": [[302, 2, 1, "", "autotune"], [302, 2, 1, "", "get_all_config_set"]], "neural_compressor.tensorflow.quantization.config": [[303, 1, 1, "", "SmoothQuantConfig"], [303, 1, 1, "", "StaticQuantConfig"], [303, 2, 1, "", "get_default_sq_config"], [303, 2, 1, "", "get_default_static_quant_config"]], "neural_compressor.tensorflow.quantization.quantize": [[305, 2, 1, "", "need_apply"], [305, 2, 1, "", "quantize_model"], [305, 2, 1, "", "quantize_model_with_single_config"]], "neural_compressor.tensorflow.quantization.utils": [[306, 0, 0, "-", "graph_converter"], [344, 0, 0, "-", "graph_rewriter"], [360, 0, 0, "-", "graph_util"], [362, 0, 0, "-", "quantize_graph"], [379, 0, 0, "-", "quantize_graph_common"], [382, 0, 0, "-", "transform_graph"], [385, 0, 0, "-", "utility"]], "neural_compressor.tensorflow.quantization.utils.graph_converter": [[306, 1, 1, "", "GraphConverter"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter": [[309, 0, 0, "-", "bf16"], [333, 0, 0, "-", "generic"], [343, 0, 0, "-", "graph_base"], [351, 0, 0, "-", "int8"], [356, 0, 0, "-", "qdq"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16": [[307, 0, 0, "-", "bf16_convert"], [308, 0, 0, "-", "dequantize_cast_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert": [[307, 1, 1, "", "BF16Convert"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer": [[308, 1, 1, "", "DequantizeCastOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic": [[310, 0, 0, "-", "convert_add_to_biasadd"], [311, 0, 0, "-", "convert_layout"], [312, 0, 0, "-", "convert_leakyrelu"], [313, 0, 0, "-", "convert_nan_to_random"], [314, 0, 0, "-", "convert_placeholder_to_const"], [315, 0, 0, "-", "dilated_contraction"], [316, 0, 0, "-", "dummy_biasadd"], [317, 0, 0, "-", "expanddims_optimizer"], [318, 0, 0, "-", "fetch_weight_from_reshape"], [319, 0, 0, "-", "fold_batch_norm"], [320, 0, 0, "-", "fold_constant"], [321, 0, 0, "-", "fuse_biasadd_add"], [322, 0, 0, "-", "fuse_column_wise_mul"], [323, 0, 0, "-", "fuse_conv_with_math"], [324, 0, 0, "-", "fuse_decomposed_bn"], [325, 0, 0, "-", "fuse_decomposed_in"], [326, 0, 0, "-", "fuse_gelu"], [327, 0, 0, "-", "fuse_layer_norm"], [328, 0, 0, "-", "fuse_pad_with_conv"], [329, 0, 0, "-", "fuse_pad_with_fp32_conv"], [330, 0, 0, "-", "fuse_reshape_transpose"], [331, 0, 0, "-", "graph_cse_optimizer"], [332, 0, 0, "-", "grappler_pass"], [334, 0, 0, "-", "insert_print_node"], [335, 0, 0, "-", "move_squeeze_after_relu"], [336, 0, 0, "-", "pre_optimize"], [337, 0, 0, "-", "remove_training_nodes"], [338, 0, 0, "-", "rename_batch_norm"], [339, 0, 0, "-", "split_shared_input"], [340, 0, 0, "-", "strip_equivalent_nodes"], [341, 0, 0, "-", "strip_unused_nodes"], [342, 0, 0, "-", "switch_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd": [[310, 1, 1, "", "ConvertAddToBiasAddOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout": [[311, 1, 1, "", "ConvertLayoutOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu": [[312, 1, 1, "", "ConvertLeakyReluOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random": [[313, 1, 1, "", "ConvertNanToRandom"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const": [[314, 1, 1, "", "ConvertPlaceholderToConst"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction": [[315, 1, 1, "", "DilatedContraction"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd": [[316, 1, 1, "", "InjectDummyBiasAddOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer": [[317, 1, 1, "", "ExpandDimsOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape": [[318, 1, 1, "", "FetchWeightFromReshapeOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm": [[319, 1, 1, "", "FoldBatchNormNodesOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant": [[320, 1, 1, "", "GraphFoldConstantOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add": [[321, 1, 1, "", "FuseBiasAddAndAddOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul": [[322, 1, 1, "", "FuseColumnWiseMulOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math": [[323, 1, 1, "", "FuseConvWithMathOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn": [[324, 1, 1, "", "FuseDecomposedBNOptimizer"], [324, 2, 1, "", "bypass_reshape"], [324, 2, 1, "", "get_const_dim_count"], [324, 2, 1, "", "node_from_map"], [324, 2, 1, "", "node_name_from_input"], [324, 2, 1, "", "valid_reshape_inputs"], [324, 2, 1, "", "values_from_const"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in": [[325, 1, 1, "", "FuseDecomposedINOptimizer"], [325, 2, 1, "", "bypass_reshape"], [325, 2, 1, "", "get_const_dim_count"], [325, 2, 1, "", "node_from_map"], [325, 2, 1, "", "node_name_from_input"], [325, 2, 1, "", "valid_reshape_inputs"], [325, 2, 1, "", "values_from_const"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu": [[326, 1, 1, "", "FuseGeluOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm": [[327, 1, 1, "", "FuseLayerNormOptimizer"], [327, 2, 1, "", "node_from_map"], [327, 2, 1, "", "node_name_from_input"], [327, 2, 1, "", "values_from_const"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv": [[328, 1, 1, "", "FusePadWithConv2DOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv": [[329, 1, 1, "", "FusePadWithFP32Conv2DOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose": [[330, 1, 1, "", "FuseTransposeReshapeOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer": [[331, 1, 1, "", "GraphCseOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass": [[332, 1, 1, "", "GrapplerOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node": [[334, 1, 1, "", "InsertPrintMinMaxNode"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu": [[335, 1, 1, "", "MoveSqueezeAfterReluOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize": [[336, 1, 1, "", "PreOptimization"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes": [[337, 1, 1, "", "RemoveTrainingNodesOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm": [[338, 1, 1, "", "RenameBatchNormOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input": [[339, 1, 1, "", "SplitSharedInputOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes": [[340, 1, 1, "", "StripEquivalentNodesOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes": [[341, 1, 1, "", "StripUnusedNodesOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer": [[342, 1, 1, "", "SwitchOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base": [[343, 1, 1, "", "GraphRewriterBase"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8": [[345, 0, 0, "-", "freeze_fake_quant"], [346, 0, 0, "-", "freeze_value"], [347, 0, 0, "-", "fuse_conv_redundant_dequantize"], [348, 0, 0, "-", "fuse_conv_requantize"], [349, 0, 0, "-", "fuse_matmul_redundant_dequantize"], [350, 0, 0, "-", "fuse_matmul_requantize"], [352, 0, 0, "-", "meta_op_optimizer"], [353, 0, 0, "-", "post_hostconst_converter"], [354, 0, 0, "-", "post_quantized_op_cse"], [355, 0, 0, "-", "scale_propagation"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant": [[345, 1, 1, "", "FreezeFakeQuantOpOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value": [[346, 1, 1, "", "FreezeValueTransformer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize": [[347, 1, 1, "", "FuseConvRedundantDequantizeTransformer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize": [[348, 1, 1, "", "FuseConvRequantizeTransformer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize": [[349, 1, 1, "", "FuseMatMulRedundantDequantizeTransformer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize": [[350, 1, 1, "", "FuseMatMulRequantizeDequantizeNewAPITransformer"], [350, 1, 1, "", "FuseMatMulRequantizeDequantizeTransformer"], [350, 1, 1, "", "FuseMatMulRequantizeNewAPITransformer"], [350, 1, 1, "", "FuseMatMulRequantizeTransformer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer": [[352, 1, 1, "", "MetaInfoChangingMemOpOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter": [[353, 1, 1, "", "PostHostConstConverter"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse": [[354, 1, 1, "", "PostCseOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation": [[355, 1, 1, "", "ScaleProPagationTransformer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq": [[357, 0, 0, "-", "insert_qdq_pattern"], [358, 0, 0, "-", "merge_duplicated_qdq"], [359, 0, 0, "-", "share_qdq_y_pattern"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern": [[357, 1, 1, "", "GenerateGraphWithQDQPattern"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq": [[358, 1, 1, "", "MergeDuplicatedQDQOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern": [[359, 1, 1, "", "ShareQDQForItexYPatternOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_util": [[360, 1, 1, "", "GraphAnalyzer"], [360, 1, 1, "", "GraphRewriterHelper"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph": [[370, 0, 0, "-", "qdq"], [372, 0, 0, "-", "quantize_graph_base"], [373, 0, 0, "-", "quantize_graph_bn"], [374, 0, 0, "-", "quantize_graph_concatv2"], [375, 0, 0, "-", "quantize_graph_conv"], [376, 0, 0, "-", "quantize_graph_for_intel_cpu"], [377, 0, 0, "-", "quantize_graph_matmul"], [378, 0, 0, "-", "quantize_graph_pooling"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq": [[363, 0, 0, "-", "fuse_qdq_bn"], [364, 0, 0, "-", "fuse_qdq_concatv2"], [365, 0, 0, "-", "fuse_qdq_conv"], [366, 0, 0, "-", "fuse_qdq_deconv"], [367, 0, 0, "-", "fuse_qdq_in"], [368, 0, 0, "-", "fuse_qdq_matmul"], [369, 0, 0, "-", "fuse_qdq_pooling"], [371, 0, 0, "-", "optimize_qdq"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn": [[363, 1, 1, "", "FuseNodeStartWithFusedBatchNormV3"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2": [[364, 1, 1, "", "FuseNodeStartWithConcatV2"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv": [[365, 1, 1, "", "FuseNodeStartWithConv2d"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv": [[366, 1, 1, "", "FuseNodeStartWithDeconv2d"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in": [[367, 1, 1, "", "FuseNodeStartWithFusedInstanceNorm"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul": [[368, 1, 1, "", "FuseNodeStartWithMatmul"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling": [[369, 1, 1, "", "FuseNodeStartWithPooling"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq": [[371, 1, 1, "", "OptimizeQDQGraph"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base": [[372, 1, 1, "", "QuantizeGraphBase"], [372, 1, 1, "", "QuantizeNodeBase"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn": [[373, 1, 1, "", "FuseNodeStartWithFusedBatchNormV3"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2": [[374, 1, 1, "", "FuseNodeStartWithConcatV2"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv": [[375, 1, 1, "", "FuseNodeStartWithConv2d"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu": [[376, 1, 1, "", "QuantizeGraphForIntel"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul": [[377, 1, 1, "", "FuseNodeStartWithMatmul"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling": [[378, 1, 1, "", "FuseNodeStartWithPooling"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph_common": [[379, 1, 1, "", "QuantizeGraphHelper"]], "neural_compressor.tensorflow.quantization.utils.transform_graph": [[380, 0, 0, "-", "bias_correction"], [381, 0, 0, "-", "graph_transform_base"], [383, 0, 0, "-", "insert_logging"], [384, 0, 0, "-", "rerange_quantized_concat"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction": [[380, 1, 1, "", "BiasCorrection"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base": [[381, 1, 1, "", "GraphTransformBase"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging": [[383, 1, 1, "", "InsertLogging"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat": [[384, 1, 1, "", "RerangeQuantizedConcat"]], "neural_compressor.tensorflow.quantization.utils.utility": [[385, 2, 1, "", "apply_inlining"], [385, 2, 1, "", "collate_tf_preds"], [385, 2, 1, "", "construct_function_from_graph_def"], [385, 2, 1, "", "fix_ref_type_of_graph_def"], [385, 2, 1, "", "generate_feed_dict"], [385, 2, 1, "", "get_graph_def"], [385, 2, 1, "", "get_input_output_node_names"], [385, 2, 1, "", "get_model_input_shape"], [385, 2, 1, "", "get_tensor_by_name"], [385, 2, 1, "", "is_ckpt_format"], [385, 2, 1, "", "is_saved_model_format"], [385, 2, 1, "", "iterator_sess_run"], [385, 2, 1, "", "parse_saved_model"], [385, 2, 1, "", "read_graph"], [385, 2, 1, "", "reconstruct_saved_model"], [385, 2, 1, "", "strip_equivalent_nodes"], [385, 2, 1, "", "strip_unused_nodes"], [385, 2, 1, "", "write_graph"]], "neural_compressor.tensorflow.utils": [[386, 0, 0, "-", "constants"], [387, 0, 0, "-", "data"], [389, 0, 0, "-", "model"], [390, 0, 0, "-", "model_wrappers"], [391, 0, 0, "-", "utility"]], "neural_compressor.tensorflow.utils.data": [[387, 1, 1, "", "BaseDataLoader"], [387, 1, 1, "", "BatchSampler"], [387, 1, 1, "", "DummyDataset"], [387, 1, 1, "", "DummyDatasetV2"], [387, 1, 1, "", "IndexFetcher"], [387, 1, 1, "", "IterableFetcher"], [387, 1, 1, "", "IterableSampler"], [387, 1, 1, "", "SequentialSampler"], [387, 2, 1, "", "default_collate"]], "neural_compressor.tensorflow.utils.model": [[389, 1, 1, "", "Model"], [389, 1, 1, "", "TensorflowGlobalConfig"]], "neural_compressor.tensorflow.utils.model_wrappers": [[390, 1, 1, "", "BaseModel"], [390, 1, 1, "", "KerasModel"], [390, 1, 1, "", "TensorflowBaseModel"], [390, 1, 1, "", "TensorflowCheckpointModel"], [390, 1, 1, "", "TensorflowLLMModel"], [390, 1, 1, "", "TensorflowModel"], [390, 1, 1, "", "TensorflowSavedModelModel"], [390, 2, 1, "", "checkpoint_session"], [390, 2, 1, "", "estimator_session"], [390, 2, 1, "", "frozen_pb_session"], [390, 2, 1, "", "get_model_type"], [390, 2, 1, "", "get_tf_model_type"], [390, 2, 1, "", "graph_def_session"], [390, 2, 1, "", "graph_session"], [390, 2, 1, "", "keras_session"], [390, 2, 1, "", "load_saved_model"], [390, 2, 1, "", "saved_model_session"], [390, 2, 1, "", "slim_session"], [390, 2, 1, "", "try_loading_keras"], [390, 2, 1, "", "validate_and_inference_input_output"], [390, 2, 1, "", "validate_graph_node"]], "neural_compressor.tensorflow.utils.utility": [[391, 1, 1, "", "CaptureOutputToFile"], [391, 1, 1, "", "CpuInfo"], [391, 1, 1, "", "TFSlimNetsFactory"], [391, 2, 1, "", "combine_histogram"], [391, 2, 1, "", "deep_get"], [391, 2, 1, "", "disable_random"], [391, 2, 1, "", "dump_elapsed_time"], [391, 2, 1, "", "get_all_fp32_data"], [391, 2, 1, "", "get_tensor_histogram"], [391, 2, 1, "", "itex_installed"], [391, 2, 1, "", "register_algo"], [391, 2, 1, "", "singleton"], [391, 2, 1, "", "valid_keras_format"], [391, 2, 1, "", "version1_eq_version2"], [391, 2, 1, "", "version1_gt_version2"], [391, 2, 1, "", "version1_gte_version2"], [391, 2, 1, "", "version1_lt_version2"], [391, 2, 1, "", "version1_lte_version2"]], "neural_compressor.torch": [[394, 0, 0, "-", "algorithms"], [434, 0, 0, "-", "export"], [440, 0, 0, "-", "quantization"], [446, 0, 0, "-", "utils"]], "neural_compressor.torch.algorithms": [[392, 0, 0, "-", "base_algorithm"], [395, 0, 0, "-", "layer_wise"], [400, 0, 0, "-", "mixed_precision"], [402, 0, 0, "-", "mx_quant"], [407, 0, 0, "-", "pt2e_quant"], [410, 0, 0, "-", "smooth_quant"], [414, 0, 0, "-", "static_quant"], [428, 0, 0, "-", "weight_only"]], "neural_compressor.torch.algorithms.base_algorithm": [[392, 1, 1, "", "Quantizer"]], "neural_compressor.torch.algorithms.fp8_quant.utils": [[393, 0, 0, "-", "logger"]], "neural_compressor.torch.algorithms.layer_wise": [[396, 0, 0, "-", "load"], [397, 0, 0, "-", "modified_pickle"], [398, 0, 0, "-", "utils"]], "neural_compressor.torch.algorithms.layer_wise.load": [[396, 2, 1, "", "load"]], "neural_compressor.torch.algorithms.layer_wise.modified_pickle": [[397, 3, 1, "", "PickleError"], [397, 3, 1, "", "PicklingError"], [397, 3, 1, "", "UnpicklingError"]], "neural_compressor.torch.algorithms.layer_wise.utils": [[398, 1, 1, "", "QDQLayer"], [398, 2, 1, "", "clean_module_weight"], [398, 2, 1, "", "dowload_hf_model"], [398, 2, 1, "", "get_children"], [398, 2, 1, "", "get_module"], [398, 2, 1, "", "get_named_children"], [398, 2, 1, "", "get_super_module_by_name"], [398, 2, 1, "", "load_empty_model"], [398, 2, 1, "", "load_layer_wise_quantized_model"], [398, 2, 1, "", "load_module"], [398, 2, 1, "", "load_tensor"], [398, 2, 1, "", "load_tensor_from_shard"], [398, 2, 1, "", "load_value"], [398, 2, 1, "", "register_weight_hooks"], [398, 2, 1, "", "update_module"]], "neural_compressor.torch.algorithms.mixed_precision": [[399, 0, 0, "-", "half_precision_convert"], [401, 0, 0, "-", "module_wrappers"]], "neural_compressor.torch.algorithms.mixed_precision.half_precision_convert": [[399, 1, 1, "", "HalfPrecisionConverter"]], "neural_compressor.torch.algorithms.mixed_precision.module_wrappers": [[401, 1, 1, "", "HalfPrecisionModuleWrapper"]], "neural_compressor.torch.algorithms.mx_quant": [[403, 0, 0, "-", "mx"], [404, 0, 0, "-", "utils"]], "neural_compressor.torch.algorithms.mx_quant.mx": [[403, 1, 1, "", "MXLinear"], [403, 1, 1, "", "MXQuantizer"]], "neural_compressor.torch.algorithms.mx_quant.utils": [[404, 1, 1, "", "ElemFormat"], [404, 1, 1, "", "RoundingMode"], [404, 2, 1, "", "quantize_elemwise_op"], [404, 2, 1, "", "quantize_mx_op"]], "neural_compressor.torch.algorithms.pt2e_quant": [[405, 0, 0, "-", "core"], [406, 0, 0, "-", "half_precision_rewriter"], [408, 0, 0, "-", "save_load"], [409, 0, 0, "-", "utility"]], "neural_compressor.torch.algorithms.pt2e_quant.core": [[405, 1, 1, "", "W8A8PT2EQuantizer"]], "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter": [[406, 1, 1, "", "PatternPair"], [406, 2, 1, "", "apply_single_pattern_pair"], [406, 2, 1, "", "get_filter_fn"], [406, 2, 1, "", "get_half_precision_node_set"], [406, 2, 1, "", "get_unquantized_node_set"], [406, 2, 1, "", "pattern_factory"], [406, 2, 1, "", "transformation"]], "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.PatternPair": [[406, 4, 1, "", "fn"], [406, 4, 1, "", "replace_pattern"], [406, 4, 1, "", "search_pattern"]], "neural_compressor.torch.algorithms.pt2e_quant.save_load": [[408, 2, 1, "", "load"], [408, 2, 1, "", "save"]], "neural_compressor.torch.algorithms.pt2e_quant.utility": [[409, 2, 1, "", "create_quant_spec_from_config"], [409, 2, 1, "", "create_xiq_quantizer_from_pt2e_config"]], "neural_compressor.torch.algorithms.smooth_quant": [[411, 0, 0, "-", "save_load"], [412, 0, 0, "-", "smooth_quant"], [413, 0, 0, "-", "utility"]], "neural_compressor.torch.algorithms.smooth_quant.save_load": [[411, 2, 1, "", "recover_model_from_json"]], "neural_compressor.torch.algorithms.smooth_quant.smooth_quant": [[412, 1, 1, "", "SmoothQuantQuantizer"], [412, 2, 1, "", "qdq_quantize"]], "neural_compressor.torch.algorithms.smooth_quant.utility": [[413, 1, 1, "", "AutoAlpha"], [413, 1, 1, "", "Calibration"], [413, 1, 1, "", "GraphTrace"], [413, 1, 1, "", "SQLinearWrapper"], [413, 1, 1, "", "TorchSmoothQuant"], [413, 1, 1, "", "WrapperLayer"], [413, 2, 1, "", "build_captured_dataloader"], [413, 2, 1, "", "cal_scale"], [413, 2, 1, "", "cfg_to_qconfig"], [413, 2, 1, "", "check_cfg_and_qconfig"], [413, 2, 1, "", "dump_model_op_stats"], [413, 2, 1, "", "enough_memo_store_scale"], [413, 2, 1, "", "forward_wrapper"], [413, 2, 1, "", "get_module"], [413, 2, 1, "", "get_parent"], [413, 2, 1, "", "get_quantizable_ops_recursively"], [413, 2, 1, "", "model_forward"], [413, 2, 1, "", "model_forward_per_sample"], [413, 2, 1, "", "move_input_to_device"], [413, 2, 1, "", "quant_dequant_w_v1"], [413, 2, 1, "", "quant_dequant_x_v1"], [413, 2, 1, "", "register_autotune"], [413, 2, 1, "", "reshape_in_channel_to_last"], [413, 2, 1, "", "reshape_scale_as_input"], [413, 2, 1, "", "reshape_scale_as_weight"], [413, 2, 1, "", "set_module"], [413, 2, 1, "", "update_sq_scale"]], "neural_compressor.torch.algorithms.static_quant": [[415, 0, 0, "-", "save_load"], [416, 0, 0, "-", "static_quant"], [417, 0, 0, "-", "utility"]], "neural_compressor.torch.algorithms.static_quant.save_load": [[415, 2, 1, "", "load"], [415, 2, 1, "", "save"]], "neural_compressor.torch.algorithms.static_quant.static_quant": [[416, 1, 1, "", "StaticQuantQuantizer"]], "neural_compressor.torch.algorithms.static_quant.utility": [[417, 1, 1, "", "TransformerBasedModelBlockPatternDetector"], [417, 2, 1, "", "cfg_to_qconfig"], [417, 2, 1, "", "check_cfg_and_qconfig"], [417, 2, 1, "", "dump_model_op_stats"], [417, 2, 1, "", "generate_activation_observer"], [417, 2, 1, "", "generate_xpu_qconfig"], [417, 2, 1, "", "get_depth"], [417, 2, 1, "", "get_dict_at_depth"], [417, 2, 1, "", "get_element_under_depth"], [417, 2, 1, "", "get_quantizable_ops_from_cfgs"], [417, 2, 1, "", "get_quantizable_ops_recursively"], [417, 2, 1, "", "parse_cfgs"], [417, 2, 1, "", "simple_inference"]], "neural_compressor.torch.algorithms.weight_only": [[418, 0, 0, "-", "autoround"], [419, 0, 0, "-", "awq"], [420, 0, 0, "-", "gptq"], [424, 0, 0, "-", "hqq"], [429, 0, 0, "-", "modules"], [430, 0, 0, "-", "rtn"], [431, 0, 0, "-", "save_load"], [432, 0, 0, "-", "teq"], [433, 0, 0, "-", "utility"]], "neural_compressor.torch.algorithms.weight_only.autoround": [[418, 1, 1, "", "AutoRoundQuantizer"], [418, 2, 1, "", "get_dataloader"]], "neural_compressor.torch.algorithms.weight_only.awq": [[419, 1, 1, "", "AWQQuantizer"]], "neural_compressor.torch.algorithms.weight_only.gptq": [[420, 1, 1, "", "GPTQ"], [420, 1, 1, "", "GPTQuantizer"], [420, 1, 1, "", "Quantizer"], [420, 1, 1, "", "RAWGPTQuantizer"], [420, 2, 1, "", "find_layers"], [420, 2, 1, "", "find_layers_name"], [420, 2, 1, "", "is_leaf"], [420, 2, 1, "", "log_quantizable_layers_per_transformer"], [420, 2, 1, "", "trace_gptq_target_blocks"]], "neural_compressor.torch.algorithms.weight_only.hqq": [[421, 0, 0, "-", "bitpack"], [422, 0, 0, "-", "config"], [423, 0, 0, "-", "core"], [425, 0, 0, "-", "optimizer"], [426, 0, 0, "-", "qtensor"], [427, 0, 0, "-", "quantizer"]], "neural_compressor.torch.algorithms.weight_only.hqq.bitpack": [[421, 1, 1, "", "Packer"]], "neural_compressor.torch.algorithms.weight_only.hqq.config": [[422, 1, 1, "", "HQQModuleConfig"], [422, 1, 1, "", "QTensorConfig"]], "neural_compressor.torch.algorithms.weight_only.hqq.core": [[423, 1, 1, "", "HQQLinear"], [423, 1, 1, "", "HQQTensorHandle"]], "neural_compressor.torch.algorithms.weight_only.hqq.optimizer": [[425, 2, 1, "", "optimize_weights_proximal_legacy"]], "neural_compressor.torch.algorithms.weight_only.hqq.qtensor": [[426, 1, 1, "", "QTensor"], [426, 1, 1, "", "QTensorMetaInfo"]], "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo": [[426, 4, 1, "", "axis"], [426, 4, 1, "", "group_size"], [426, 4, 1, "", "nbits"], [426, 4, 1, "", "packing"], [426, 4, 1, "", "shape"]], "neural_compressor.torch.algorithms.weight_only.hqq.quantizer": [[427, 1, 1, "", "HQQuantizer"], [427, 2, 1, "", "filter_fn"], [427, 2, 1, "", "patch_hqq_moduile"], [427, 2, 1, "", "replacement_fn"]], "neural_compressor.torch.algorithms.weight_only.modules": [[429, 1, 1, "", "FakeAffineTensorQuantFunction"], [429, 1, 1, "", "HPUWeightOnlyLinear"], [429, 1, 1, "", "INCWeightOnlyLinear"], [429, 1, 1, "", "MulLinear"], [429, 1, 1, "", "QDQLayer"], [429, 1, 1, "", "TEQLinearFakeQuant"], [429, 1, 1, "", "UnpackedWeightOnlyLinearParams"], [429, 1, 1, "", "WeightOnlyLinear"]], "neural_compressor.torch.algorithms.weight_only.rtn": [[430, 1, 1, "", "RTNQuantizer"]], "neural_compressor.torch.algorithms.weight_only.save_load": [[431, 1, 1, "", "WOQModelLoader"], [431, 2, 1, "", "load"], [431, 2, 1, "", "save"]], "neural_compressor.torch.algorithms.weight_only.teq": [[432, 1, 1, "", "TEQuantizer"], [432, 1, 1, "", "TrainableEquivalentTransformation"]], "neural_compressor.torch.algorithms.weight_only.utility": [[433, 1, 1, "", "GraphTrace"], [433, 2, 1, "", "fetch_module"], [433, 2, 1, "", "forward_wrapper"], [433, 2, 1, "", "get_absorb_layers"], [433, 2, 1, "", "get_block_prefix"], [433, 2, 1, "", "get_module"], [433, 2, 1, "", "get_module_input_output"], [433, 2, 1, "", "get_parent"], [433, 2, 1, "", "model_forward"], [433, 2, 1, "", "move_input_to_device"], [433, 2, 1, "", "qdq_weight_actor"], [433, 2, 1, "", "qdq_weight_asym"], [433, 2, 1, "", "qdq_weight_sym"], [433, 2, 1, "", "quant_tensor"], [433, 2, 1, "", "quant_weight_w_scale"], [433, 2, 1, "", "quantize_4bit"], [433, 2, 1, "", "recover_forward"], [433, 2, 1, "", "replace_forward"], [433, 2, 1, "", "search_clip"], [433, 2, 1, "", "set_module"]], "neural_compressor.torch.export": [[435, 0, 0, "-", "pt2e_export"]], "neural_compressor.torch.export.pt2e_export": [[435, 2, 1, "", "export"], [435, 2, 1, "", "export_model_for_pt2e_quant"]], "neural_compressor.torch.quantization": [[437, 0, 0, "-", "algorithm_entry"], [438, 0, 0, "-", "autotune"], [439, 0, 0, "-", "config"], [441, 0, 0, "-", "load_entry"], [442, 0, 0, "-", "quantize"]], "neural_compressor.torch.quantization.algorithm_entry": [[437, 2, 1, "", "autoround_quantize_entry"], [437, 2, 1, "", "awq_quantize_entry"], [437, 2, 1, "", "fp8_entry"], [437, 2, 1, "", "gptq_entry"], [437, 2, 1, "", "hqq_entry"], [437, 2, 1, "", "mixed_precision_entry"], [437, 2, 1, "", "mx_quant_entry"], [437, 2, 1, "", "pt2e_dynamic_quant_entry"], [437, 2, 1, "", "pt2e_static_quant_entry"], [437, 2, 1, "", "rtn_entry"], [437, 2, 1, "", "smooth_quant_entry"], [437, 2, 1, "", "static_quant_entry"], [437, 2, 1, "", "teq_quantize_entry"]], "neural_compressor.torch.quantization.autotune": [[438, 2, 1, "", "autotune"], [438, 2, 1, "", "get_all_config_set"], [438, 2, 1, "", "get_rtn_double_quant_config_set"]], "neural_compressor.torch.quantization.config": [[439, 1, 1, "", "AWQConfig"], [439, 1, 1, "", "AutoRoundConfig"], [439, 1, 1, "", "DynamicQuantConfig"], [439, 1, 1, "", "FP8Config"], [439, 1, 1, "", "GPTQConfig"], [439, 1, 1, "", "HQQConfig"], [439, 1, 1, "", "MXQuantConfig"], [439, 1, 1, "", "MixedPrecisionConfig"], [439, 1, 1, "", "OperatorConfig"], [439, 1, 1, "", "RTNConfig"], [439, 1, 1, "", "SmoothQuantConfig"], [439, 1, 1, "", "StaticQuantConfig"], [439, 1, 1, "", "TEQConfig"], [439, 1, 1, "", "TorchBaseConfig"], [439, 2, 1, "", "get_all_registered_configs"], [439, 2, 1, "", "get_default_AutoRound_config"], [439, 2, 1, "", "get_default_awq_config"], [439, 2, 1, "", "get_default_double_quant_config"], [439, 2, 1, "", "get_default_dynamic_config"], [439, 2, 1, "", "get_default_fp8_config"], [439, 2, 1, "", "get_default_fp8_config_set"], [439, 2, 1, "", "get_default_gptq_config"], [439, 2, 1, "", "get_default_hqq_config"], [439, 2, 1, "", "get_default_mixed_precision_config"], [439, 2, 1, "", "get_default_mixed_precision_config_set"], [439, 2, 1, "", "get_default_mx_config"], [439, 2, 1, "", "get_default_rtn_config"], [439, 2, 1, "", "get_default_sq_config"], [439, 2, 1, "", "get_default_static_config"], [439, 2, 1, "", "get_default_teq_config"], [439, 2, 1, "", "get_woq_tuning_config"]], "neural_compressor.torch.quantization.load_entry": [[441, 2, 1, "", "load"]], "neural_compressor.torch.quantization.quantize": [[442, 2, 1, "", "convert"], [442, 2, 1, "", "finalize_calibration"], [442, 2, 1, "", "need_apply"], [442, 2, 1, "", "prepare"], [442, 2, 1, "", "quantize"]], "neural_compressor.torch.utils": [[443, 0, 0, "-", "auto_accelerator"], [444, 0, 0, "-", "constants"], [445, 0, 0, "-", "environ"], [447, 0, 0, "-", "utility"]], "neural_compressor.torch.utils.auto_accelerator": [[443, 1, 1, "", "AcceleratorRegistry"], [443, 1, 1, "", "Auto_Accelerator"], [443, 1, 1, "", "CPU_Accelerator"], [443, 1, 1, "", "CUDA_Accelerator"], [443, 1, 1, "", "HPU_Accelerator"], [443, 1, 1, "", "XPU_Accelerator"], [443, 2, 1, "", "auto_detect_accelerator"], [443, 2, 1, "", "register_accelerator"]], "neural_compressor.torch.utils.constants": [[444, 1, 1, "", "LoadFormat"]], "neural_compressor.torch.utils.environ": [[445, 2, 1, "", "device_synchronize"], [445, 2, 1, "", "get_accelerator"], [445, 2, 1, "", "get_ipex_version"], [445, 2, 1, "", "get_torch_version"], [445, 2, 1, "", "is_hpex_available"], [445, 2, 1, "", "is_ipex_available"], [445, 2, 1, "", "is_ipex_imported"], [445, 2, 1, "", "is_package_available"], [445, 2, 1, "", "is_transformers_imported"]], "neural_compressor.torch.utils.utility": [[447, 2, 1, "", "dowload_hf_model"], [447, 2, 1, "", "dump_model_op_stats"], [447, 2, 1, "", "fetch_module"], [447, 2, 1, "", "get_double_quant_config_dict"], [447, 2, 1, "", "get_model_device"], [447, 2, 1, "", "get_model_info"], [447, 2, 1, "", "get_processor_type_from_user_config"], [447, 2, 1, "", "get_quantizer"], [447, 2, 1, "", "load_empty_model"], [447, 2, 1, "", "postprocess_model"], [447, 2, 1, "", "register_algo"], [447, 2, 1, "", "set_module"]], "neural_compressor.training": [[448, 1, 1, "", "CallBacks"], [448, 1, 1, "", "CompressionManager"], [448, 2, 1, "", "fit"], [448, 2, 1, "", "prepare_compression"]], "neural_compressor.transformers": [[450, 0, 0, "-", "utils"]], "neural_compressor.transformers.quantization": [[449, 0, 0, "-", "utils"]], "neural_compressor.transformers.utils": [[451, 0, 0, "-", "quantization_config"]], "neural_compressor.transformers.utils.quantization_config": [[451, 1, 1, "", "AutoRoundConfig"], [451, 1, 1, "", "AwqConfig"], [451, 1, 1, "", "GPTQConfig"], [451, 1, 1, "", "INCQuantizationConfigMixin"], [451, 1, 1, "", "QuantizationMethod"], [451, 1, 1, "", "RtnConfig"], [451, 1, 1, "", "TeqConfig"]], "neural_compressor.utils": [[452, 0, 0, "-", "collect_layer_histogram"], [453, 0, 0, "-", "constant"], [454, 0, 0, "-", "create_obj_from_config"], [455, 0, 0, "-", "export"], [460, 0, 0, "-", "kl_divergence"], [461, 0, 0, "-", "load_huggingface"], [462, 0, 0, "-", "logger"], [463, 0, 0, "-", "options"], [464, 0, 0, "-", "pytorch"], [465, 0, 0, "-", "utility"], [466, 0, 0, "-", "weights_details"]], "neural_compressor.utils.collect_layer_histogram": [[452, 1, 1, "", "LayerHistogramCollector"]], "neural_compressor.utils.create_obj_from_config": [[454, 2, 1, "", "create_dataloader"], [454, 2, 1, "", "create_dataset"], [454, 2, 1, "", "create_eval_func"], [454, 2, 1, "", "create_train_func"], [454, 2, 1, "", "get_algorithm"], [454, 2, 1, "", "get_func_from_config"], [454, 2, 1, "", "get_metrics"], [454, 2, 1, "", "get_postprocess"], [454, 2, 1, "", "get_preprocess"]], "neural_compressor.utils.export": [[456, 0, 0, "-", "qlinear2qdq"], [457, 0, 0, "-", "tf2onnx"], [458, 0, 0, "-", "torch2onnx"]], "neural_compressor.utils.export.qlinear2qdq": [[456, 2, 1, "", "check_model"], [456, 2, 1, "", "onnx_qlinear_to_qdq"]], "neural_compressor.utils.export.tf2onnx": [[457, 2, 1, "", "tf_to_fp32_onnx"], [457, 2, 1, "", "tf_to_int8_onnx"]], "neural_compressor.utils.export.torch2onnx": [[458, 2, 1, "", "dynamic_quant_export"], [458, 2, 1, "", "get_node_mapping"], [458, 2, 1, "", "get_quantizable_onnx_ops"], [458, 2, 1, "", "static_quant_export"], [458, 2, 1, "", "torch_to_fp32_onnx"], [458, 2, 1, "", "torch_to_int8_onnx"]], "neural_compressor.utils.kl_divergence": [[460, 1, 1, "", "KL_Divergence"]], "neural_compressor.utils.load_huggingface": [[461, 1, 1, "", "OptimizedModel"], [461, 2, 1, "", "export_compressed_model"], [461, 2, 1, "", "save_for_huggingface_upstream"]], "neural_compressor.utils.logger": [[462, 1, 1, "", "Logger"], [462, 2, 1, "", "debug"], [462, 2, 1, "", "error"], [462, 2, 1, "", "fatal"], [462, 2, 1, "", "info"], [462, 2, 1, "", "log"], [462, 2, 1, "", "warn"], [462, 2, 1, "", "warning"]], "neural_compressor.utils.options": [[463, 1, 1, "", "onnxrt"]], "neural_compressor.utils.pytorch": [[464, 2, 1, "", "is_int8_model"], [464, 2, 1, "", "load"], [464, 2, 1, "", "load_weight_only"], [464, 2, 1, "", "recover_model_from_json"]], "neural_compressor.utils.utility": [[465, 1, 1, "", "CaptureOutputToFile"], [465, 1, 1, "", "CpuInfo"], [465, 2, 1, "", "Dequantize"], [465, 1, 1, "", "DotDict"], [465, 1, 1, "", "GLOBAL_STATE"], [465, 1, 1, "", "LazyImport"], [465, 1, 1, "", "MODE"], [465, 1, 1, "", "OpEntry"], [465, 1, 1, "", "Statistics"], [465, 2, 1, "", "alias_param"], [465, 2, 1, "", "calculate_mse"], [465, 2, 1, "", "check_key_exist"], [465, 2, 1, "", "combine_histogram"], [465, 2, 1, "", "compare_objects"], [465, 2, 1, "", "compute_sparsity"], [465, 2, 1, "", "deep_get"], [465, 2, 1, "", "deep_set"], [465, 2, 1, "", "dequantize_weight"], [465, 2, 1, "", "dump_class_attrs"], [465, 2, 1, "", "dump_data_to_local"], [465, 2, 1, "", "dump_elapsed_time"], [465, 2, 1, "", "dump_table"], [465, 2, 1, "", "dump_table_to_csv"], [465, 2, 1, "", "equal_dicts"], [465, 2, 1, "", "fault_tolerant_file"], [465, 2, 1, "", "get_all_fp32_data"], [465, 2, 1, "", "get_number_of_sockets"], [465, 2, 1, "", "get_op_list"], [465, 2, 1, "", "get_size"], [465, 2, 1, "", "get_tensor_histogram"], [465, 2, 1, "", "get_tensors_info"], [465, 2, 1, "", "get_tuning_history"], [465, 2, 1, "", "get_weights_details"], [465, 2, 1, "", "load_data_from_pkl"], [465, 2, 1, "", "mse_metric_gap"], [465, 2, 1, "", "print_op_list"], [465, 2, 1, "", "print_table"], [465, 2, 1, "", "recover"], [465, 2, 1, "", "set_random_seed"], [465, 2, 1, "", "set_resume_from"], [465, 2, 1, "", "set_tensorboard"], [465, 2, 1, "", "set_workspace"], [465, 2, 1, "", "show_memory_info"], [465, 2, 1, "", "singleton"], [465, 2, 1, "", "str2array"], [465, 2, 1, "", "time_limit"], [465, 2, 1, "", "version1_eq_version2"], [465, 2, 1, "", "version1_gt_version2"], [465, 2, 1, "", "version1_gte_version2"], [465, 2, 1, "", "version1_lt_version2"], [465, 2, 1, "", "version1_lte_version2"]], "neural_compressor.utils.weights_details": [[466, 1, 1, "", "WeightsDetails"], [466, 1, 1, "", "WeightsStatistics"]]}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "function", "Python function"], "3": ["py", "exception", "Python exception"], "4": ["py", "attribute", "Python attribute"], "5": ["py", "data", "Python data"]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:function", "3": "py:exception", "4": "py:attribute", "5": "py:data"}, "terms": {"": [30, 31, 90, 128, 133, 140, 150, 152, 173, 174, 175, 179, 180, 181, 182, 185, 187, 192, 194, 195, 208, 211, 224, 225, 232, 234, 235, 239, 262, 380, 385, 391, 396, 413, 431, 433, 441, 465, 469, 470, 471, 473, 474, 475, 476, 478, 480, 482, 487, 488, 489, 494, 495, 520, 524, 526, 527, 528, 529, 531, 536, 537, 541, 542, 543, 544, 547, 548, 549, 550, 552, 553], "0": [3, 30, 31, 39, 75, 90, 133, 139, 140, 145, 147, 149, 152, 153, 154, 163, 169, 171, 192, 195, 200, 202, 205, 206, 208, 209, 212, 213, 216, 221, 225, 234, 245, 262, 267, 281, 303, 311, 385, 387, 396, 413, 417, 425, 433, 439, 443, 451, 458, 461, 472, 473, 474, 476, 479, 481, 482, 485, 487, 490, 492, 502, 520, 521, 524, 526, 527, 528, 529, 532, 533, 534, 535, 536, 537, 539, 542, 544, 545, 547, 548, 549, 550, 551, 552], "00": [534, 553], "000": [211, 492], "0000": 538, "00000": 211, "00001": 211, "00003": 211, "00004": 211, "0001": [3, 195, 536], "0003": [534, 553], "0004": 536, "0005": 534, "0006": [534, 553], "0007": 553, "0008": [534, 553], "001": [211, 487, 524, 550], "0016": 534, "002": 524, "0021": 534, "0025": 534, "0029": [487, 550, 553], "00296431384049356": [487, 550], "0030": 553, "0036": [487, 550], "0040": 534, "0043": 534, "0046": [534, 553], "0048": 553, "005": 547, "0051": 534, "0058": 553, "0059755356051027775": [487, 550], "0061": 534, "006533813662827015": [487, 550], "00774": 542, "0086": [487, 550], "0097": 534, "00978": [439, 476, 487, 547], "01": [31, 153, 195, 425, 439, 476, 534, 536, 547, 552, 553], "0106": 553, "0115": 553, "0119": 553, "0130": 553, "0141": 553, "0142": 534, "017": 551, "01x": 553, "02": [195, 553], "0201": 534, "0213": 553, "02340": 169, "027": 553, "02x": 553, "03": [534, 553], "0352": 534, "03x": 553, "04": [492, 532, 553], "04191": 519, "0438": 553, "04x": 553, "05": [150, 195, 234, 413, 534, 535, 550, 553], "0500": [487, 550], "05516": [439, 476, 487], "0559": 534, "05754": 542, "05x": 553, "06": 553, "0626": 553, "0698": [487, 550], "06x": 553, "07": [487, 492, 550, 553], "0734": 553, "0737": [487, 550], "07x": 553, "08": [225, 534, 551, 553], "0806": [487, 550], "083": 553, "0837": 549, "08x": 553, "09": [534, 553], "0927": 553, "09656": 187, "099": 211, "0999": 553, "0f": 524, "0x": [140, 396], "0x2b0001b0": 553, "1": [3, 29, 30, 31, 40, 59, 74, 90, 94, 98, 131, 133, 140, 142, 145, 147, 149, 150, 151, 153, 154, 163, 169, 181, 182, 184, 195, 200, 202, 205, 206, 208, 209, 210, 212, 213, 216, 217, 221, 225, 230, 231, 232, 234, 245, 262, 280, 281, 284, 292, 294, 298, 312, 331, 346, 359, 383, 385, 387, 391, 396, 413, 417, 418, 420, 425, 429, 433, 439, 441, 451, 454, 461, 465, 469, 471, 472, 473, 474, 475, 476, 478, 479, 480, 481, 482, 487, 488, 490, 492, 493, 495, 519, 521, 526, 528, 532, 534, 535, 537, 539, 540, 541, 542, 544, 545, 547, 548, 549, 550, 551, 552], "10": [195, 211, 266, 425, 481, 482, 492, 518, 526, 532, 536, 542, 551, 552, 553], "100": [3, 151, 152, 153, 195, 211, 281, 301, 302, 305, 443, 480, 487, 518, 524, 530, 532, 536, 544, 551, 552, 553], "1000": 536, "10000": [266, 542], "10004": [473, 476, 477, 482, 490, 493, 521, 523, 524, 528, 531, 537, 539, 541, 545, 547], "10005": [539, 545], "10006": 523, "10016": [487, 550], "100x": [476, 487, 547], "101": [209, 234, 487, 535, 550, 553], "10163": 553, "1024": [131, 211, 383], "10271": [472, 539], "10281": [472, 539], "103": [551, 553], "10339": 553, "104": 553, "10438": [476, 487, 547, 550], "1052": 553, "10537": [472, 539], "1058": 553, "1077": 553, "10833": 225, "1095": 553, "10k": [418, 451, 525], "11": [473, 487, 532, 535, 537, 550, 552, 553], "1120": 553, "1129": 553, "1137": 553, "1139": 553, "1142": 553, "116": 551, "1161": 553, "1165": 553, "117": 553, "118": 553, "1186": 553, "119": [487, 550], "12": [534, 553], "120": [487, 550], "1209": 553, "123": [211, 551], "1244": 553, "124m": [474, 550], "1253": 553, "125m": [474, 529, 550], "126": 553, "1262": 553, "1268": 553, "127": [212, 213, 387, 487, 544, 550], "1276": 553, "128": [3, 31, 145, 209, 212, 213, 225, 387, 418, 420, 439, 451, 476, 481, 487, 536, 544, 547, 551, 553], "1280": 553, "1284": 553, "12b": 534, "12x": 553, "13": [487, 527, 532, 550, 553], "1324": 553, "13325": [476, 487, 547, 550], "135": 553, "136": 553, "1365": [225, 551], "1367": 553, "137": 553, "1374": 553, "1381": [487, 550], "1383": 553, "139": [487, 550, 553], "13b": [474, 534, 550, 553], "13x": 553, "14": [195, 457, 458, 526, 532, 553], "1406": 553, "142": 553, "14314": [476, 487, 547], "1451": 553, "1495": 553, "1498": 553, "14x": 553, "15": [133, 385, 528, 532, 534], "1510": [487, 550], "1512": 553, "1514": 553, "1515": 553, "1517": 553, "152": 553, "155": 553, "1556": 553, "1583": [487, 550], "1587": 553, "15x": 553, "16": [473, 532, 547, 553], "1601": [487, 550], "161": 553, "162": [487, 550, 553], "1658": 553, "16599": [487, 550], "1661": 553, "1666": 553, "16x": 553, "16x16gb": 553, "17": [485, 492, 532, 534], "170": 553, "1713": 553, "172": [487, 550, 553], "1720": 553, "173": 553, "17323": [420, 439, 476, 487, 547], "174": 553, "1742": [487, 550], "1747": 553, "1749": [487, 550], "175": 553, "17509": [487, 550], "1751": [487, 550], "176": 553, "177": [232, 553], "178": 553, "179": 553, "17x": 553, "18": [532, 534, 543, 553], "1809": 519, "1810": 169, "1838": 553, "184": 553, "18518": 135, "18529": 135, "186": 553, "1862": 553, "1889": 553, "1890": [487, 550], "18x": 553, "19": 553, "192": [487, 550], "1920": 553, "192795": 520, "195": 553, "1951": 553, "1956": 553, "1971": 553, "1978": 195, "1981": 553, "1983354538679123": [487, 550], "1989": 553, "19x": 553, "1_11_capabl": 495, "1b7": [474, 534, 550], "1e": [150, 413, 487, 550], "1e1": 425, "1s4c14ins1bsthroughput": 553, "1x": 553, "1x1": [536, 542], "1x2": [487, 550], "1xchannel": [195, 542], "2": [29, 30, 31, 39, 59, 90, 94, 140, 147, 149, 151, 153, 154, 175, 181, 182, 195, 210, 230, 232, 234, 245, 266, 281, 297, 311, 331, 359, 396, 413, 433, 441, 465, 470, 471, 472, 474, 475, 476, 478, 479, 480, 481, 482, 483, 487, 490, 492, 493, 502, 519, 521, 528, 529, 531, 532, 533, 534, 535, 537, 539, 540, 542, 543, 544, 545, 547, 548, 549, 550, 551, 552], "20": [225, 425, 542, 551, 553], "200": [224, 418, 439, 451, 476, 490, 552], "2000": 536, "2001": 209, "201": 553, "2011": 519, "2012": 211, "2017": 519, "2018": 519, "2019": 542, "2020": [135, 472, 539], "2021": 542, "20210514": 553, "2022": [195, 476, 487, 533, 542, 547, 550], "2023": [472, 476, 487, 492, 539, 542, 547, 550], "2024": [492, 553], "2043": 209, "2048": [3, 391, 418, 420, 439, 451, 465, 476, 547], "206": 553, "207": [487, 550, 553], "2080": 553, "2083": 553, "20b": [534, 553], "21": [234, 487, 534, 543, 550, 553], "21020": [487, 550], "2111": 542, "212": 553, "213": 553, "2132": 549, "214": 553, "215": 553, "2169": 553, "217": 553, "2198": 553, "21x": 553, "22": [532, 534, 553], "2204": 187, "2209": [476, 487, 547, 550, 553], "2210": [420, 439, 476, 487, 547], "2211": [476, 487, 547, 550], "2213": 553, "222": 553, "2220": [487, 550], "223": 553, "2232": 553, "224": [195, 221, 524, 526, 536, 551], "22444": [487, 550], "225": [221, 536, 553], "2287": 553, "229": [221, 536], "23": [154, 534, 553], "230": 553, "2301": 542, "2305": [476, 487, 547], "2306": [439, 476, 487, 547], "2309": [439, 476, 487], "2310": [472, 539], "234": 553, "235": 553, "2365": 553, "2384": 553, "23f1": 553, "23x": 553, "24": [154, 482, 542, 552, 553], "24101": 542, "24116": 542, "2420": [487, 550], "244": 553, "249": 553, "25": [542, 553], "250": 542, "2504": 553, "2538": 553, "255": [487, 544, 550], "256": [216, 221, 439, 524, 536, 551], "256gb": 553, "2570": [487, 550], "2584": 553, "25x": 553, "26": [534, 553], "2630": 553, "26f1": 553, "26x": 553, "27": [527, 534, 553], "2788": 553, "2793": 553, "2799": 553, "27x": 553, "28": [209, 210, 214, 553], "2805": 553, "281": 553, "282": 553, "2862": 553, "2897": 553, "28x": 553, "29": [534, 553], "2970": [487, 550], "298": 553, "2991": [487, 550], "29x": 553, "2d": [55, 327, 487, 550], "2e5m2": 471, "2gb": [243, 390], "2x": [525, 531], "2x1": [542, 553], "2x2": [487, 550], "2xlarg": 553, "3": [29, 31, 133, 140, 153, 154, 182, 195, 211, 225, 230, 281, 385, 396, 413, 441, 465, 472, 473, 475, 476, 478, 480, 481, 482, 487, 490, 492, 502, 519, 520, 521, 524, 526, 528, 529, 532, 535, 536, 537, 539, 540, 542, 543, 544, 547, 548, 549, 550, 551, 552, 553], "30": [225, 525, 531, 551, 553], "300": 542, "302": 553, "303": 553, "3067": 553, "30b": [474, 534, 550, 553], "30x": 553, "31": [30, 534, 553], "312": 553, "3121": 553, "31x": 553, "32": [31, 171, 280, 413, 418, 429, 433, 439, 451, 472, 473, 480, 481, 524, 530, 539, 547, 553], "320": 553, "3242": 553, "3253": [487, 550], "329": 553, "32accuraci": 553, "32x": 553, "33": [135, 472, 534, 539, 553], "3377": 553, "3388": 553, "339": 553, "33x": 553, "34": [492, 534, 553], "3429": 553, "344": 553, "3445": 553, "3463": 553, "349": 553, "34f1": 553, "34x": 553, "35": [534, 542, 553], "350m": [474, 550], "354": [474, 550], "3542": [474, 550], "358": 553, "35x": 553, "36": 553, "365": 553, "3686": 553, "36x": 553, "37": [534, 553], "373": 553, "374": 553, "3740": [487, 550], "375": 553, "3757": [474, 550], "377": 553, "379": [474, 550], "38": 553, "3804": [474, 550], "381": 542, "3815": [487, 550], "382": 553, "384": [225, 551], "3845": [487, 550], "3850": [487, 550], "385297635664756e": [487, 550], "3852e": [487, 550], "3887": [474, 550], "39": 553, "390": 553, "391": 553, "3911": [487, 550], "3924": [487, 550], "393": 553, "3930": [474, 550], "3947": [474, 550], "395": 553, "3950": 553, "396": 553, "399": 553, "3a14": 553, "3b": [474, 534, 550], "3d": [55, 327, 487, 543, 550], "3dgan": 543, "3f": 482, "3rd": [473, 487, 537, 543, 544, 546], "3x": 527, "4": [31, 39, 142, 145, 151, 154, 175, 184, 195, 218, 221, 225, 227, 228, 230, 280, 281, 311, 418, 429, 433, 439, 451, 470, 472, 474, 475, 476, 477, 482, 487, 488, 492, 493, 495, 518, 524, 525, 528, 531, 532, 535, 536, 539, 542, 544, 547, 550, 551, 552, 553], "40": [534, 553], "4019": 553, "404": [542, 553], "405": 553, "4055": [487, 550], "406": [536, 553], "4096": 553, "40b": 534, "41": 553, "4124": 553, "4149": [474, 550], "4172": [474, 550], "4193": 553, "42": [195, 418, 439, 476, 553], "420": 531, "4202": 553, "4208": 553, "4227": 553, "4237": 553, "4259": 553, "4271": 553, "42x": 553, "43": [534, 553], "4312": 553, "4319": 553, "434": 553, "4351": 553, "43x": 553, "44": 553, "440": 553, "4413": 553, "4430": 553, "4469": 549, "448": 553, "449": 553, "45": [490, 534, 553], "4516": [474, 550], "4533": [474, 550], "4542": 553, "456": 536, "46": [534, 553], "4607": 553, "4628": 553, "4634": [474, 550], "4697": 553, "46x": 553, "47": [154, 482, 534, 553], "471": 553, "4728": 553, "4731": 553, "4734": [487, 550], "4741": [487, 550], "4743": [487, 550], "4789": 553, "47x": 553, "48": [154, 487, 550, 553], "4800": 553, "4828": [474, 550], "484": [281, 553], "485": 536, "4895": 553, "4899": 553, "48x": 553, "49": [534, 553], "4906": [474, 550], "4907": 553, "4916": 553, "4923": 553, "4936": [474, 550], "494": 553, "4954": 553, "497": 553, "4973": 553, "4980": [474, 550], "4984": 553, "4f": 520, "4th": [473, 487, 534, 543, 544], "4x": [184, 487, 544], "4x1": [175, 195, 536, 542, 553], "5": [139, 149, 153, 163, 195, 213, 221, 234, 262, 303, 413, 417, 439, 474, 476, 479, 487, 493, 526, 528, 532, 535, 536, 542, 544, 547, 550, 551, 552, 553], "50": [232, 487, 494, 542, 550, 553], "5018": [474, 550], "504": 553, "5040": [487, 550], "5045": 553, "5048": [474, 550], "5049": 553, "5053": 553, "5057": [474, 550], "5058": 553, "5084": 553, "5098": 553, "50x": 553, "51": [534, 553], "511": 553, "512": [473, 476], "5142": 553, "517": 553, "5177": 553, "518": [474, 550], "5185": [474, 550], "52": 553, "5228": 553, "525": 553, "5282": 553, "52f1": 553, "53": [534, 553], "530": 553, "5328": 553, "533": 553, "534": 553, "535": 553, "5359": 553, "5369": 553, "5398": 553, "54": 553, "5419": 553, "5436": [474, 550], "5443": [474, 550, 553], "5444": [487, 550], "5477": 553, "548": 553, "549": 553, "5494": 553, "54accuraci": 553, "55": [534, 553], "5514": 553, "5523": 553, "5525": 553, "5540": 553, "5552": [474, 550], "5555": [487, 550], "5593": [474, 550, 553], "55x": 553, "56": 553, "5603": 553, "5604": 553, "560m": [474, 550], "5617": 553, "5637": 553, "5642": 553, "5655": 553, "566": 553, "567": 553, "5682": 553, "56be4db0acb8001400a502ec": 232, "57": [487, 534, 550, 553], "570": 553, "5711": 553, "5714": 553, "5716": 553, "5718": 553, "5732": 553, "5738": 553, "5742": [474, 550], "5752": 553, "5764": [474, 550, 553], "5765": 553, "577": 553, "5771": 553, "5777": 553, "5789": [474, 550], "5799": 553, "57x": 553, "58": [534, 553], "5814": 553, "5819": 553, "582": 553, "5823": 553, "5826": [487, 550], "5834": 553, "584": 553, "5841": 553, "5843": 553, "5871": 553, "588": 553, "5881": 553, "5898": 553, "5899": 553, "58x": 553, "59": [487, 534, 550, 553], "5911": 553, "5933": 553, "5934": 553, "5951": 553, "5972": [487, 550, 553], "5977": [474, 550], "598": 553, "5991": 553, "5997": 553, "59f1": 553, "59x": 553, "5b": [474, 550], "5x": 543, "6": [195, 472, 474, 476, 479, 487, 528, 539, 544, 550, 552, 553], "60": 553, "600": [536, 553], "6002": 553, "6004": 553, "6018": 553, "6029": 553, "6038": [487, 550], "6053": 553, "6057": 553, "6059": 553, "6094": 553, "60x": 553, "61": [534, 553], "611": 553, "6123": 553, "613": 553, "6134": 553, "6136": 553, "614": 553, "615": 553, "6154": 553, "6181": 553, "6187": 553, "619": 553, "6195": 553, "61accuraci": 553, "61x": 553, "62": [534, 553], "6224": 553, "623": 553, "6239": 553, "624": 553, "6247": [474, 550], "6261": 553, "6266": 553, "6297": [474, 550], "62x": 553, "63": [534, 542, 553], "6301": 553, "6312": 553, "635": 553, "636": 553, "6360": 553, "6361": 553, "6365": [474, 550], "637690492221736e": [487, 550], "6376e": [487, 550], "6377": 553, "6379": 553, "6390": 553, "6392": [474, 550], "6393": 553, "6396": 553, "6399": 553, "63x": 553, "64": [225, 439, 473, 481, 487, 534, 547, 550, 551, 553], "6401": 553, "6404": [474, 550], "6409": 553, "6410": 553, "6433": 553, "6434": 553, "6437": [474, 550, 553], "6438": 553, "6439": 553, "6448": 553, "6455": 553, "6456": 553, "6472": 553, "6473": 553, "6474": 553, "648": 553, "6481": [487, 550], "6483": 553, "6484": 553, "6488": 553, "6491": 553, "6496": 553, "6497": 553, "6499": [474, 550], "64x": 553, "65": 553, "6504": 553, "6505": 553, "6506": [487, 550], "6509": 553, "6519": 553, "652": 553, "6527": 553, "6532": 553, "6535": 553, "6542": [474, 550], "65421": 520, "6543": 553, "655": [474, 550, 553], "6559": 553, "6569": [474, 550], "6571": 553, "6575": 553, "6579": 553, "6582": 553, "659": 553, "6594": 553, "6598": 553, "65b": [474, 550], "65x": 553, "66": 553, "6604": 553, "6612": 553, "6614": 553, "6621": [474, 550], "6622": 553, "663": 553, "6654": 553, "6661": 553, "6669": 553, "6678": 553, "6685": 553, "6687": 553, "6693": 553, "66b": [474, 550], "66x": 553, "67": [534, 553], "6709": 553, "6713": 553, "6718": [474, 550], "6719": 553, "6724": 553, "6726": 553, "6735": [474, 550], "6739": 553, "6740": [474, 550, 553], "6742": 553, "6746": 553, "6748": 553, "6756": 553, "6769": [474, 550, 553], "678": 553, "679": 553, "67x": 553, "68": [534, 551, 553], "6803": 553, "6804": [474, 550, 553], "6814": [474, 550], "6820": 553, "6821": [474, 487, 550], "6824": 553, "6827": 553, "6829": 553, "6831": [474, 550, 553], "6832": 553, "6835": [487, 550], "6836": [487, 550], "6837": [487, 550], "6839": [487, 550], "684": 553, "6845": 553, "6848": [487, 550], "685": 553, "6854": 553, "6857": 553, "6859": 553, "6861": 553, "6862": 553, "6864": 553, "6866": [474, 550, 553], "6872": [474, 550], "6876": 553, "6878": 553, "6883": [487, 550], "6885": 553, "6887": 553, "689": 553, "6890": 553, "6895": [474, 550], "69": 553, "6902": 553, "6911": 553, "6918": 553, "693": 553, "6953": [474, 550, 553], "6961": 553, "6977": 553, "6982": 553, "6994": 550, "6ap0": 553, "6b": [474, 534, 550, 553], "6f": 524, "7": [29, 151, 154, 195, 245, 413, 425, 433, 474, 476, 479, 487, 495, 518, 527, 528, 536, 542, 544, 548, 550, 552, 553], "70": [534, 553], "7002": 553, "7006": 553, "7009": 553, "7018": 553, "7022": 553, "7024": 553, "7025": 553, "7030": 553, "7031": 553, "7032": 553, "7034": 553, "7056": 553, "7058": [550, 553], "707": 553, "7075": 553, "7077": 553, "7080": 553, "7088": 553, "70b": [534, 553], "70x": 553, "71": [154, 534, 553], "7103": 553, "7105": 553, "7106": 553, "7107": 553, "7111": 553, "712": 553, "7122": 553, "7128": [474, 550], "714": 553, "7143": [474, 550], "7149": [474, 550], "715": 553, "7153": 553, "7174": [487, 550], "718": 553, "7186": 553, "7190": 553, "7198": 553, "71x": 553, "72": [154, 487, 534, 550, 553], "7203": 553, "722": 553, "7221": [474, 550], "7233": 553, "7240": 553, "7243": 553, "7244": 553, "7246": 553, "7247": 553, "7268": 553, "7269": 553, "727": 553, "7273": 553, "7277": 553, "728": 553, "7283": 553, "7285": 553, "72x": 553, "73": [534, 553], "7312": 553, "732": 553, "7322": 553, "7323": 553, "7326": [474, 550], "733": 553, "7332": 550, "7334": 553, "7335": 550, "7337": 553, "734": 553, "7350": 553, "7353": 553, "7357": [474, 550], "7361": [474, 550, 553], "7392": [550, 553], "7398": [474, 550], "7399": 553, "73x": 553, "74": [534, 553], "7415": 553, "7432": 553, "7440": [487, 550], "7442": 553, "7443": 553, "7448": 553, "7451": [487, 550], "7476": 553, "7486": 553, "7495": 549, "7497": 553, "74x": 553, "75": [534, 542, 553], "7518": 553, "7519": 553, "753": 553, "754": 473, "7541": 553, "7543": 553, "756": 553, "7566": 553, "7568": 553, "7572": 553, "7589": [487, 550], "7590": [474, 550], "7596": 553, "75x": 553, "76": [534, 553], "7608": [487, 550], "7615": [550, 553], "7616": 553, "7617": 553, "7622": 553, "7627": [474, 550, 553], "7628": 553, "7632": 550, "7633": 553, "7634": 553, "767": 553, "7675": 553, "7677": [550, 553], "7682": 553, "7699": 553, "76x": 553, "77": [534, 553], "770": 553, "7704": 553, "7706": 553, "7715": 553, "7742": 553, "774m": [474, 550], "7753": 553, "7758": 553, "7759": [474, 550, 553], "7764": 553, "7772": [487, 550], "778": 553, "7797": 553, "77x": 553, "78": [551, 553], "780": 553, "7807": 553, "7813": 553, "7824": 553, "7828": 553, "7829": 553, "783": 553, "7835": 553, "7836": 553, "784": 553, "7840": [474, 550], "7845": 553, "7851": 553, "7856": 553, "7873": 553, "7878": 553, "7894": 553, "7895": 542, "79": [534, 553], "790": 553, "7905": 553, "7908": [474, 550], "7911": 553, "7927": 553, "7941": 553, "7957": [474, 550], "7964": 553, "7965": 553, "79x": 553, "7b": [474, 483, 492, 534, 550, 553], "7b1": [474, 550, 553], "8": [98, 140, 154, 195, 224, 396, 404, 413, 418, 433, 439, 451, 470, 471, 472, 474, 476, 477, 487, 490, 494, 519, 520, 528, 532, 539, 542, 543, 547, 550, 552, 553], "80": [527, 534, 545, 553], "800": [225, 551], "8001": [1, 452], "801": 542, "8018": 553, "8025": 553, "8044": 553, "8047": 553, "805": 547, "8058": 553, "8074": 553, "8084": 553, "8096": 553, "81": 553, "8146": 553, "8178": 553, "82": [534, 553], "8207": [487, 550], "8213": 553, "822": 553, "8235": 553, "8246": [487, 550], "8256": 553, "8259": 553, "8266": 549, "8291": 549, "8294": 549, "8298": [487, 550], "8299": 549, "82x": 553, "83": [487, 549, 550, 553], "8314": 553, "8363": 553, "8371": 553, "8372": 549, "8382": 553, "83x": 553, "84": [487, 550, 553], "841": 553, "8411": 553, "8480": 553, "84x": 553, "85": [487, 549, 550, 553], "8539": 553, "85x": 553, "86": [534, 553], "8626": 553, "863": 553, "8684": 553, "86x": 553, "87": [221, 534, 553], "875": [221, 551], "8763": [487, 550], "8768": [487, 550], "8780": 553, "8782": 553, "87f1": 553, "88": [527, 549, 553], "8809": 553, "8814": 553, "8816": 553, "8863": 553, "88x": 553, "89": [487, 534, 550, 553], "893": 553, "8984": 553, "89x": 553, "8ghz": 553, "8x1": 195, "9": [169, 195, 474, 482, 490, 532, 536, 542, 550, 552, 553], "90": [195, 534, 545, 553], "9048": 553, "9091": 553, "90f1": 553, "91": [487, 547, 550, 553], "9125": 553, "9163": 553, "91x": 553, "92": [534, 553], "921": 553, "925": 553, "927": 553, "93": [487, 550, 553], "9301": [487, 550], "9308": [487, 550], "9317": 553, "9324": 553, "9359": 553, "93x": 553, "94": [551, 553], "9403": 553, "9411": 553, "94x": 553, "95": [75, 154, 234, 535, 553], "951": 553, "9522": 553, "9527": [266, 536], "953": 553, "95top1": 553, "95x": 553, "96": [534, 553], "9635": 553, "97": [534, 536, 553], "9702": 553, "98": [195, 536, 542, 553], "9860": [487, 550], "9867": 534, "9892": 553, "99": [3, 153, 303, 553], "9902": 553, "9906": 553, "9907": 534, "9909": 553, "9911": 534, "9915": 534, "9916": 553, "9917": 553, "9919": 553, "9921": 553, "9922": 553, "9928": 534, "9930": 534, "9931": 553, "9932": 553, "9933": [534, 553], "9934": 553, "9935": 553, "9937": 553, "9941": 553, "9942": 553, "9944": 553, "9945": [534, 553], "9947": 553, "9950": 553, "9951": 553, "9952": 553, "9953": 553, "9955": 534, "9957": [534, 553], "9958": 553, "9961": 553, "9962": 553, "9963": 553, "9967": 553, "9971": 553, "9972": 534, "9975": 534, "9976": 534, "9978": 553, "9979": 553, "9983": 553, "9984": [534, 553], "9986": 534, "9987": 534, "9988": 534, "9989": 534, "999": [3, 303], "9990": 534, "9991": 534, "9992": 534, "9994": [534, 553], "9995": 534, "9997": 534, "9998": 553, "99ccff": 552, "99x": 553, "A": [3, 40, 59, 60, 88, 101, 125, 126, 133, 138, 145, 152, 153, 159, 161, 162, 169, 170, 173, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 195, 211, 225, 227, 230, 231, 232, 234, 235, 239, 243, 266, 283, 286, 312, 331, 332, 385, 389, 390, 391, 397, 404, 406, 409, 412, 413, 415, 425, 427, 433, 443, 448, 465, 474, 476, 477, 487, 489, 494, 520, 521, 525, 528, 534, 535, 536, 538, 542, 543, 544, 547, 550, 551, 552], "And": [55, 327, 480, 487, 489, 490, 518, 520, 536, 550], "As": [471, 476, 487, 490, 494, 521, 535, 536, 542, 547, 552], "At": [472, 489, 494, 539, 552], "Being": 488, "By": [140, 173, 195, 227, 396, 476, 483, 494, 495, 535, 538, 542, 543, 547, 552], "For": [29, 31, 145, 149, 153, 156, 160, 173, 174, 177, 178, 188, 195, 211, 225, 231, 232, 234, 235, 262, 413, 433, 439, 465, 471, 474, 476, 477, 478, 479, 483, 487, 488, 490, 491, 493, 495, 523, 524, 526, 528, 529, 531, 542, 546, 547, 550, 552, 553], "IT": [211, 218, 543], "If": [52, 53, 55, 59, 140, 151, 153, 156, 195, 198, 199, 211, 225, 235, 262, 281, 324, 325, 327, 331, 396, 413, 431, 433, 435, 441, 447, 448, 451, 471, 477, 480, 487, 489, 490, 494, 518, 520, 521, 524, 527, 532, 533, 535, 536, 540, 542, 544, 547, 549, 550, 551, 552], "In": [162, 177, 178, 179, 184, 185, 186, 189, 195, 208, 230, 245, 447, 469, 476, 477, 480, 487, 488, 490, 492, 493, 494, 521, 523, 524, 535, 536, 540, 541, 542, 544, 546, 547, 549, 550, 551, 552], "It": [39, 140, 159, 162, 166, 175, 198, 199, 232, 234, 235, 262, 267, 271, 311, 396, 433, 442, 448, 472, 475, 476, 477, 478, 480, 481, 487, 493, 494, 495, 519, 527, 529, 536, 539, 542, 544, 547, 549, 552], "Its": [494, 519, 542], "NOT": [209, 528], "No": [413, 489, 520, 527, 536, 543], "Not": [277, 278, 391, 465, 471, 520], "ON": 546, "Of": 521, "On": [487, 544, 553], "One": [477, 495, 520, 524, 531, 542, 543, 552], "TO": 524, "The": [3, 21, 39, 59, 98, 104, 106, 125, 133, 140, 145, 146, 151, 152, 153, 155, 156, 158, 160, 161, 162, 163, 165, 169, 173, 175, 177, 178, 180, 181, 182, 187, 188, 189, 190, 191, 192, 195, 198, 199, 200, 209, 210, 211, 212, 213, 217, 218, 225, 227, 228, 229, 231, 232, 234, 235, 243, 245, 262, 263, 264, 265, 266, 267, 268, 269, 271, 272, 273, 274, 278, 280, 281, 283, 284, 288, 292, 293, 294, 297, 298, 299, 301, 302, 305, 311, 331, 344, 361, 385, 386, 387, 388, 389, 390, 391, 392, 396, 405, 406, 407, 408, 409, 410, 412, 413, 414, 416, 417, 418, 422, 423, 425, 426, 427, 433, 435, 437, 438, 439, 441, 442, 443, 447, 448, 452, 454, 460, 461, 464, 465, 466, 469, 470, 471, 472, 473, 475, 476, 477, 479, 480, 481, 487, 488, 490, 493, 494, 495, 496, 498, 504, 507, 510, 518, 519, 520, 521, 524, 526, 528, 529, 530, 531, 532, 534, 535, 536, 537, 538, 539, 540, 541, 542, 544, 545, 546, 547, 548, 549, 550, 551, 552, 553], "Their": 454, "Then": [230, 487, 494, 550, 552], "There": [100, 263, 265, 470, 475, 479, 487, 492, 520, 528, 531, 536, 547, 550, 552], "These": [494, 531], "To": [30, 230, 245, 392, 472, 473, 474, 475, 476, 479, 481, 482, 487, 489, 492, 494, 495, 520, 524, 537, 539, 542, 546, 547, 548, 550, 552], "Will": [128, 380, 441, 531], "With": [81, 245, 352, 480, 487, 490, 493, 495, 521, 532, 536, 540, 542, 543, 544, 549, 550, 552, 553], "_": [198, 199, 262, 473, 474, 476, 477, 480, 482, 487, 490, 492, 493, 494, 519, 524, 526, 528, 532, 536, 537, 538, 540, 542, 544, 547, 548, 549, 550, 552], "__all__": 520, "__call__": 218, "__class__": 245, "__getitem__": [207, 211, 225, 521, 536], "__init__": [431, 441, 493, 520, 521, 535, 552], "__iter__": [207, 211, 521, 536], "__len__": [207, 211], "__name__": 245, "__str__": 451, "__version__": [1, 138, 397, 520], "_configset": 153, "_description_": [438, 477], "_epoch_ran": 162, "_generate_dataload": [200, 387], "_inductor": [470, 475], "_lossandgradi": 520, "_propagate_qconfig_help": 145, "_quantiz": 458, "_quantizedconv": [76, 347], "_quantizeddeconv": [76, 347], "_quantizedfusedbatchnorm": [108, 363], "_quantizedmatmul": [78, 79, 349, 350], "_saved_model": [133, 385], "_type_": [145, 461], "_use_new_zipfile_seri": 170, "a100cuda": 553, "aarch64": 518, "ab": [30, 169, 187, 420, 433, 439, 480, 487, 542, 544, 550], "abbrevi": 195, "abc": [98, 232, 493, 552], "abcadaptor": 493, "abctunestrategi": 552, "abil": [472, 493, 494, 528, 539, 550], "abl": [198, 199, 235, 262, 448, 480, 487, 544], "abound": 543, "about": [169, 191, 465, 469, 471, 488, 520, 521, 536, 542, 546, 552, 553], "abov": [39, 311, 474, 475, 476, 478, 487, 493, 494, 495, 542, 544, 550, 552], "absolut": [169, 195, 234, 413, 472, 487, 535, 536, 539, 542, 544, 552], "absorb": [145, 149, 413, 433, 476, 547], "absorb_layer_dict": [419, 439, 451], "absorb_pair": 31, "absorb_to_lay": [145, 413, 432, 433, 439], "absorbed_1": [145, 433], "absorpt": [145, 433], "abstract": [71, 162, 225, 343, 493, 495, 530], "abus": 488, "ac": 266, "acc": [473, 478, 534, 542, 553], "acceler": [171, 439, 443, 445, 471, 473, 474, 476, 477, 479, 487, 492, 532, 536, 542, 543, 546, 547, 550, 552], "accelerator_execution_tim": 251, "acceleratorregistri": 443, "accept": [195, 281, 481, 488, 518, 520, 521, 547], "access": [52, 53, 55, 195, 324, 325, 327, 461, 465], "accommod": [494, 495], "accompani": [533, 552], "accord": [1, 107, 145, 151, 195, 209, 210, 211, 225, 269, 271, 392, 442, 447, 454, 471, 480, 481, 487, 493, 524, 542, 546, 550, 551, 552], "accordingli": 550, "account": [488, 549, 552], "accumul": [277, 472, 476, 539, 552], "accur": [29, 149, 413, 420, 439, 475, 476, 487, 542, 547, 550], "accuraci": [31, 151, 153, 192, 195, 198, 199, 234, 235, 245, 262, 267, 281, 448, 472, 474, 475, 476, 480, 481, 483, 490, 492, 494, 495, 519, 521, 523, 524, 525, 526, 529, 535, 536, 539, 540, 541, 542, 543, 547, 548, 549, 550, 553], "accuracy_criterion": [195, 245, 536, 540, 552], "accuracy_level": 31, "accuracycriterion": [195, 536, 552], "accuracyspars": 553, "achiev": [474, 475, 476, 477, 478, 481, 483, 487, 526, 534, 536, 541, 542, 543, 544, 550, 552], "acq": 266, "acq_max": 266, "acquisit": 266, "across": [235, 392, 472, 481, 522, 529, 536, 539, 542, 545, 550, 552], "act": [192, 207, 387, 488], "act_algo": [413, 439, 475], "act_algorithm": 303, "act_bit": [418, 439], "act_dtyp": [299, 303, 439, 472, 474, 475, 478, 539], "act_dynam": [418, 439], "act_fn": 174, "act_granular": [299, 303, 439, 478], "act_group_s": [418, 439], "act_max_valu": [292, 293, 294, 297, 298], "act_maxabs_hw_weights_pcs_maxabs_pow2": 471, "act_maxabs_pow2_weights_pcs_opt_pow2": 471, "act_min_valu": [292, 293, 294, 297, 298], "act_ord": [439, 476], "act_sym": [299, 303, 418, 439, 475, 478, 480, 481], "action": 488, "activ": [16, 31, 126, 145, 166, 195, 278, 280, 286, 292, 293, 294, 298, 413, 417, 439, 470, 471, 474, 475, 476, 479, 480, 487, 493, 494, 495, 519, 523, 528, 536, 544, 547, 550], "activation_max": 465, "activation_min": 465, "activation_min_max": 465, "activationoper": 5, "activity_regular": [292, 293, 294, 298], "actord": [31, 476, 547], "actual": [234, 475, 524, 527], "ad": [186, 209, 227, 266, 470, 473, 476, 494, 495, 537, 542, 547], "adadelta": 524, "adam": 165, "adamw": 165, "adapt": [472, 488, 494, 539, 543], "adaptor": [162, 195, 280, 288, 289, 454, 469, 495, 531, 545, 546, 548, 550], "adaptor_registri": 493, "add": [30, 38, 49, 94, 104, 133, 165, 192, 195, 209, 211, 278, 310, 321, 359, 385, 465, 469, 474, 489, 490, 492, 495, 521, 524, 526, 528, 535, 536, 549, 550, 552], "add_origin_loss": [163, 195], "add_port_to_nam": 90, "add_qdq_pair_to_weight": [28, 195, 544], "add_relu": 526, "addit": [145, 195, 448, 476, 494, 495, 547, 548, 552], "addition": [476, 495, 524, 542, 552], "addn": 528, "address": [211, 473, 476, 481, 488, 520, 537, 543], "addv2": [38, 54, 310, 326, 528], "adher": 489, "adjust": [487, 544, 550], "adopt": [487, 489, 542, 543, 550], "advanc": [135, 195, 472, 473, 476, 478, 480, 487, 488, 494, 499, 534, 539, 542, 544, 547], "advantag": [473, 542, 552], "afc": 232, "affect": [487, 550], "affin": [142, 429, 544], "aforement": 536, "after": [1, 63, 133, 145, 171, 175, 180, 182, 187, 195, 209, 221, 225, 267, 281, 335, 385, 406, 413, 445, 461, 465, 470, 471, 475, 476, 479, 487, 492, 494, 523, 526, 531, 535, 536, 540, 541, 542, 544, 546, 547, 549, 550, 551, 552], "ag": 488, "again": [211, 546], "against": [228, 406], "aggress": 552, "agnost": [157, 477], "agnostic_mod": 230, "agre": 489, "ai": [469, 472, 473, 477, 492, 539, 543, 546], "aid": 522, "aim": [469, 481, 492, 529, 534, 542, 550, 552], "ajanthan": 542, "al": [135, 472, 476, 487, 492, 519, 532, 539, 547, 550], "albert": 553, "alemb": 527, "alexnet": 553, "algo": [156, 288, 289, 409, 442, 454], "algo_nam": [152, 305, 442, 520], "algorithm": [1, 31, 145, 152, 156, 195, 226, 227, 234, 290, 299, 301, 305, 391, 436, 437, 439, 441, 442, 447, 454, 460, 476, 477, 480, 481, 483, 487, 492, 493, 494, 495, 520, 523, 528, 529, 531, 534, 542, 544], "algorithm_entri": [304, 440, 520], "algorithm_registri": 146, "algorithm_typ": 146, "algorithmschedul": 146, "algos_map": [391, 447], "alia": [462, 465], "alias": [465, 520], "alias_param": 465, "alibaba": [492, 543], "align": [225, 471, 488, 547, 551], "alignimagechannel": 551, "alignimagechanneltransform": 225, "alistarh": 542, "all": [1, 3, 21, 31, 48, 82, 140, 141, 145, 146, 148, 151, 152, 154, 157, 162, 165, 170, 175, 183, 192, 195, 200, 201, 207, 211, 218, 225, 227, 230, 232, 234, 236, 245, 274, 280, 282, 299, 302, 320, 353, 387, 389, 390, 391, 392, 396, 398, 413, 417, 420, 429, 438, 439, 441, 454, 458, 465, 471, 474, 477, 480, 481, 483, 487, 488, 489, 492, 493, 494, 495, 520, 521, 524, 528, 532, 536, 541, 542, 543, 544, 546, 547, 550, 551, 552], "all_par": [413, 433], "allbalanc": 553, "allenai": [231, 232], "allevi": 550, "alloc": 482, "allow": [145, 152, 266, 433, 473, 475, 476, 481, 524, 535, 536, 537, 542, 547, 550, 552], "allowlist": [439, 471], "along": [425, 426, 476, 532, 542, 547], "alpha": [126, 139, 142, 149, 169, 189, 286, 303, 413, 417, 429, 439, 487, 520, 544, 552], "alpha_list": 277, "alpha_max": [413, 439, 550], "alpha_min": [413, 439, 550], "alpha_step": [413, 439, 550], "alreadi": [140, 151, 211, 224, 396, 473, 477, 493, 527, 531, 552], "also": [138, 174, 208, 211, 225, 227, 234, 245, 262, 397, 471, 473, 476, 477, 478, 479, 487, 489, 493, 494, 495, 521, 525, 529, 531, 535, 536, 540, 542, 543, 544, 546, 547, 550, 552], "altern": [140, 195, 262, 396], "although": [208, 549], "alwai": [153, 230, 234, 262, 471, 481, 535, 536, 547], "amax": [433, 472, 539], "amazon": 492, "amd": [492, 532, 553], "among": [234, 472, 487, 539, 550], "amount": [3, 413, 479, 550], "amp": [1, 418, 547], "amp_cfg": 1, "amp_convert": 1, "amx": [473, 543], "an": [1, 52, 53, 55, 90, 126, 128, 133, 135, 138, 140, 145, 150, 166, 180, 195, 203, 207, 211, 225, 226, 227, 231, 232, 235, 257, 261, 262, 281, 286, 324, 325, 327, 380, 385, 396, 397, 409, 417, 433, 447, 448, 465, 467, 471, 472, 473, 474, 475, 476, 477, 479, 480, 481, 487, 488, 490, 492, 493, 495, 519, 521, 522, 526, 534, 535, 536, 537, 539, 540, 542, 543, 544, 547, 549, 550, 551, 552], "anaconda": 532, "analysi": [472, 539, 542, 549], "analyt": [469, 532, 543], "analyz": [95, 173, 243, 360, 390, 549, 550], "andrew": 519, "ani": [135, 140, 156, 230, 232, 257, 261, 277, 281, 302, 392, 396, 422, 435, 442, 443, 451, 465, 477, 480, 488, 492, 495, 520, 524, 542, 549, 552], "anneal": 168, "anno_dir": 210, "anno_path": [234, 535], "annot": [210, 230, 281, 494, 495, 535, 542, 552], "anoth": [225, 227, 465, 551, 552], "answer": [225, 231, 232, 488, 542, 551, 553], "answer_start": 232, "answeringsquad": 553, "ao": 409, "ap": 535, "ap0": 553, "apach": [3, 533], "api": [55, 60, 95, 154, 230, 234, 262, 277, 278, 281, 290, 302, 303, 304, 305, 327, 332, 360, 389, 391, 392, 420, 436, 438, 439, 440, 442, 444, 465, 471, 474, 476, 481, 487, 490, 492, 496, 498, 504, 507, 510, 526, 527, 529, 531, 532, 536, 548, 549, 552, 554], "appear": [140, 396, 488], "append": [145, 266, 490, 523, 536, 541], "append_attr": 145, "appl": 552, "appli": [31, 98, 111, 112, 113, 116, 118, 122, 133, 142, 162, 184, 186, 228, 301, 305, 366, 367, 368, 371, 373, 377, 385, 392, 406, 413, 429, 437, 442, 447, 469, 472, 475, 479, 480, 481, 487, 488, 494, 495, 536, 539, 541, 542, 544, 546, 549, 550, 552], "applianc": 543, "applic": [221, 476, 478, 487, 495, 526, 543, 547, 550, 551], "apply_awq_clip": 31, "apply_awq_scal": 31, "apply_inlin": [133, 385], "apply_single_pattern_pair": 406, "appoint": 488, "approach": [195, 475, 476, 487, 490, 519, 531, 536, 542, 543, 545, 547, 552], "appropri": [443, 475, 481, 483, 487, 488, 519, 550], "approv": 489, "approx": [476, 487, 547], "approxim": [227, 228, 476, 494, 535, 547], "appu": 476, "apr": [492, 543], "apt": [527, 532], "ar": [52, 53, 90, 140, 145, 154, 175, 180, 181, 182, 187, 195, 209, 225, 230, 234, 263, 265, 266, 280, 281, 324, 325, 392, 396, 406, 409, 413, 417, 454, 464, 465, 470, 471, 472, 473, 475, 476, 477, 479, 480, 483, 487, 488, 489, 490, 493, 494, 520, 521, 523, 524, 525, 526, 528, 530, 531, 533, 534, 535, 536, 537, 539, 540, 541, 542, 543, 544, 546, 547, 548, 549, 550, 551, 552], "arang": 550, "arbitrari": [140, 396, 477, 536, 541], "arcfac": 553, "architectur": [151, 469, 473, 476, 483, 487, 492, 518, 529, 536, 542, 543, 547], "arctic": 532, "are_shapes_equ": 90, "area": [225, 230, 472, 535, 539, 551], "arg": [1, 39, 90, 145, 154, 209, 210, 211, 266, 281, 311, 399, 420, 433, 437, 447, 461, 462, 472, 477, 524, 536, 539, 542, 544, 547, 550, 551], "argmax": 16, "argmaxoper": 6, "argpars": 154, "argu": 520, "argument": [140, 154, 195, 281, 396, 406, 413, 431, 438, 441, 442, 477, 480, 481, 547], "ariel": 542, "arithmet": 528, "arm": [492, 531, 532, 553], "around": 90, "arr": [30, 391, 465], "arrai": [3, 30, 31, 133, 140, 225, 230, 396, 465, 551], "arrang": [181, 182, 187, 210, 211, 214, 542], "art": 542, "articl": [231, 232], "arxiv": [169, 187, 420, 439, 472, 476, 487, 492, 519, 539, 542, 543, 547, 550], "as_text": 90, "ascii": [140, 396], "asd932_": 211, "ask": [492, 532], "aspect": [221, 225, 551], "asplo": 543, "assert_error": 90, "assertionerror": [170, 176, 183, 192, 235, 435, 447], "assign": [230, 465, 524, 552], "assist": [159, 548], "associ": [133, 140, 230, 396, 406], "assum": [224, 230, 493, 528], "asterisk": [474, 550], "asym": [29, 30, 31, 142, 145, 413, 429, 433, 495, 528, 547], "asymmetr": [413, 480, 495, 544, 547, 552], "atenc": 482, "atom": 533, "att": [231, 232], "attach": [487, 536, 550], "attack": 488, "attempt": 552, "attent": [16, 143, 171, 173, 184, 195, 209, 417, 488, 542], "attention_ffn_nam": 184, "attention_mask": [209, 536], "attentionoper": 7, "attr": [90, 133, 173, 385], "attr1": 281, "attr2": 281, "attr5": 281, "attribut": [30, 68, 89, 90, 133, 145, 173, 184, 195, 340, 447, 465, 471, 493, 521, 528, 530, 536], "attribute1": 281, "attribute_to_kwarg": 30, "attributeerror": [138, 281, 397], "aug": [492, 543], "augment": 2, "author": 533, "auto": [145, 152, 153, 171, 173, 195, 264, 270, 302, 413, 438, 439, 443, 445, 465, 471, 474, 477, 484, 490, 492, 519, 529, 542, 544, 547], "auto_acceler": 446, "auto_alpha_arg": [303, 439, 550], "auto_clip": 451, "auto_config": 542, "auto_copi": 145, "auto_detect_acceler": 443, "auto_input_output": [133, 385], "auto_merg": 30, "auto_mixed_precis": 270, "auto_scal": 451, "auto_slim": 172, "autoalpha": 413, "autom": [543, 550], "automat": [171, 173, 174, 195, 211, 214, 221, 443, 447, 471, 477, 480, 482, 483, 490, 492, 518, 531, 536, 537, 541, 542, 544, 550, 551, 552], "automixedprecisiontunestrategi": 264, "automodelforcausallm": [141, 398, 529], "automodelforsequenceclassif": 536, "autonumb": [494, 495], "autoround": [428, 437, 439, 477, 487, 492, 534], "autoround_arg": 476, "autoround_quantize_entri": 437, "autoroundconfig": [437, 439, 451, 476], "autoroundquant": 418, "autotoken": 536, "autotrack": [125, 133, 283, 385], "autotun": [478, 479, 480, 487, 500, 520], "autotunestrategi": 263, "aux": 1, "auxiliari": 459, "avail": [154, 188, 195, 239, 413, 445, 473, 476, 477, 483, 492, 496, 498, 504, 507, 510, 520, 525, 527, 529, 531, 542, 552, 553], "averag": [31, 231, 232, 234, 476, 535, 536, 547, 552, 553], "averagepool": 23, "averagepooling2d": 297, "avg": 544, "avgpool": [114, 123, 297, 369, 378, 528], "avoid": [90, 140, 145, 209, 396, 413, 433, 447, 482, 490, 520], "avx": 473, "avx512": [473, 487, 537, 544], "avx512_bf16": [473, 537], "avx512_core_amx_fp16": 473, "avx512_fp16": 473, "aw": [543, 553], "awai": 521, "awar": [31, 135, 162, 195, 269, 439, 448, 476, 477, 481, 493, 494, 495, 519, 523, 524, 526, 531, 541, 543, 547, 552], "awq": [31, 428, 433, 437, 439, 477, 487, 545, 547], "awq_arg": [476, 547], "awq_g32asym": 547, "awq_quant": 31, "awq_quantize_entri": 437, "awqconfig": [437, 439, 451, 476], "awqquant": 419, "ax": [195, 404, 458], "axi": [30, 195, 425, 426], "azur": [489, 492, 543], "b": [30, 59, 154, 209, 331, 418, 465, 476, 487, 489, 519, 535, 542, 547, 550, 552], "b1": [59, 331], "b16": [36, 308], "b_dataload": [151, 195, 518, 536], "b_filter": 1, "b_func": [151, 518], "back": [140, 145, 154, 225, 396], "backbon": 549, "backend": [2, 28, 29, 149, 165, 195, 196, 197, 201, 202, 205, 209, 210, 212, 213, 214, 215, 216, 220, 222, 225, 235, 236, 237, 239, 272, 439, 473, 476, 477, 490, 495, 524, 530, 531, 536, 537, 547, 551, 552], "backward": [448, 487, 523, 524, 536, 541, 542, 544, 548], "badri": 476, "baichuan": 534, "baichuan2": 534, "balanc": [217, 413, 472, 474, 476, 480, 487, 539, 547, 550], "ban": 488, "bandit": 489, "bandwidth": [473, 476, 487, 536, 537, 547], "bar": [30, 211, 543], "bare": [492, 527, 532], "bart": 553, "base": [1, 3, 21, 32, 71, 90, 101, 105, 107, 117, 129, 135, 138, 143, 145, 146, 152, 153, 154, 161, 162, 169, 176, 183, 189, 191, 195, 200, 203, 207, 209, 211, 218, 225, 234, 236, 243, 244, 245, 271, 274, 278, 289, 305, 343, 372, 381, 387, 390, 392, 397, 409, 413, 417, 429, 439, 442, 443, 445, 447, 470, 471, 473, 474, 476, 477, 481, 483, 487, 493, 494, 495, 500, 520, 523, 524, 528, 536, 537, 542, 543, 544, 547, 549, 550, 552, 553], "base_algorithm": 394, "base_config": [153, 155, 299, 301, 302, 303, 305, 438, 439, 442], "base_dir": 30, "base_model": 237, "base_tun": [155, 302, 438, 478, 480], "basecallback": 162, "baseconfig": [152, 153, 156, 299, 301, 302, 305, 438, 439, 442, 477, 480, 520], "basedataload": [200, 204, 206, 387], "basedatalod": [200, 387], "baselin": [454, 481, 549, 550], "baseline_model": [480, 481], "basemetr": [234, 262], "basemodel": [236, 301, 302, 305, 390, 480], "basepattern": [175, 177, 179], "baseprun": [180, 185, 187, 188], "basereg": 189, "basetransform": 225, "basi": 542, "basic": [173, 175, 183, 195, 224, 270, 274, 277, 448, 472, 531, 536, 539, 549], "basicprun": [186, 188], "basictoken": 224, "basictunestrategi": 265, "batch": [1, 145, 200, 202, 203, 207, 208, 387, 418, 448, 476, 521, 523, 536, 541, 542, 544, 550, 551, 552, 553], "batch_idx": 524, "batch_sampl": [200, 202, 205, 206, 208, 387, 521], "batch_siz": [195, 200, 202, 205, 206, 207, 208, 209, 210, 387, 418, 439, 451, 458, 476, 521, 524, 526, 530, 536, 544], "batchmatmul": [113, 368], "batchmatmulv2": [113, 368], "batchnorm": [20, 47, 52, 106, 319, 324, 490, 550], "batchnormalizationoper": 20, "batchsampl": [207, 387], "batchtospacend": [43, 315], "bayesian": [195, 270, 542], "bayesianoptim": 266, "bayesiantunestrategi": 266, "bbox": [230, 490, 535], "bboxes_labels_scor": 490, "beam": [227, 535], "becaus": [140, 179, 184, 225, 396, 479, 487, 490, 544, 550, 551, 552], "becom": [476, 487, 493, 526, 542, 547], "been": [3, 140, 170, 176, 183, 227, 391, 396, 404, 412, 413, 417, 473, 476, 480, 487, 495, 520, 536, 537, 547, 550], "befor": [92, 94, 149, 175, 180, 182, 187, 188, 190, 195, 209, 288, 357, 359, 420, 431, 441, 445, 471, 476, 487, 489, 495, 521, 523, 524, 527, 528, 536, 544, 547, 549, 552], "begin": [101, 181, 182, 187, 475, 520, 521, 523, 536, 542, 552], "behavior": [140, 396, 488, 493, 494, 495, 528, 538, 547, 552], "being": [135, 230, 495], "beit": 553, "belong": [211, 239, 544], "below": [40, 51, 59, 154, 195, 234, 262, 312, 323, 331, 469, 471, 472, 474, 476, 477, 480, 481, 487, 489, 490, 492, 493, 494, 495, 521, 524, 529, 530, 535, 539, 540, 541, 542, 544, 547, 549, 550, 552], "benchmark": [155, 195, 226, 245, 465, 469, 492, 499, 500, 529, 538, 552, 553], "benchmark_with_raw_cmd": 151, "benchmarkconf": 536, "benchmarkconfig": [151, 195, 518, 536], "benefici": 519, "benefit": [529, 541], "bert": [173, 195, 205, 208, 209, 225, 492, 535, 537, 542, 551, 553], "bert_dataset": 215, "bertattent": 173, "besid": [476, 487, 493, 547], "best": [162, 225, 271, 433, 476, 477, 478, 479, 481, 488, 520, 532, 540, 544, 547, 550, 551, 552], "best_clip_ratio": 433, "best_configur": 464, "best_model": [162, 464, 473, 478, 479, 480, 481, 547], "best_model_weight": 464, "best_scor": 162, "beta": [169, 425], "better": [81, 195, 198, 199, 235, 262, 352, 448, 473, 476, 487, 520, 523, 535, 537, 542, 543, 544, 547, 549, 550, 552], "between": [3, 29, 128, 150, 186, 195, 225, 231, 234, 257, 261, 380, 406, 413, 465, 471, 472, 476, 477, 480, 487, 490, 492, 493, 494, 495, 519, 531, 535, 536, 539, 544, 547, 548, 549, 550, 551, 552], "bf16": [31, 72, 134, 195, 278, 344, 399, 401, 406, 439, 471, 480, 493, 494, 528, 536, 546, 552, 553], "bf16_convert": [37, 136, 309], "bf16_op": [33, 35, 92, 306, 307, 357, 494, 546], "bf16convert": [35, 307, 546], "bf16modul": 134, "bf16modulewrapp": 134, "bf16wrapper": 546, "bfloat16": [30, 429, 439, 473, 492, 537, 546], "bfloat16fp16": 471, "bi": [231, 232], "bia": [128, 195, 380, 403, 423, 429, 547], "bias_constraint": [292, 293, 294, 298], "bias_correct": [130, 382], "bias_initi": [292, 293, 294, 298], "bias_regular": [292, 293, 294, 298], "biasadd": [38, 44, 49, 51, 94, 310, 316, 321, 323, 359, 528], "biascorrect": [128, 380], "bibtex": 533, "bicub": [225, 551], "big": [135, 476, 547], "bigscienc": [474, 534, 550, 553], "bilibili": 543, "bilinear": [221, 225, 551], "bilinearimagenet": 551, "bilinearimagenettransform": 221, "bilingu": 227, "billion": 542, "bilstm": 553, "bin": [3, 140, 141, 391, 396, 398, 465, 527], "binari": [8, 133, 234, 385, 527, 535, 548], "binary_op": 16, "binarydirect8bitoper": 8, "binaryoper": 8, "bind": [151, 483], "bio": 553, "bit": [29, 31, 145, 195, 280, 413, 421, 426, 429, 433, 439, 451, 470, 471, 472, 473, 476, 477, 487, 495, 519, 523, 537, 539, 543, 544, 547, 550], "bita": [472, 539], "bitnami": 543, "bitpack": 424, "bitwidth": 470, "bk3": 3, "black": 552, "black_nod": 2, "blendcnn": 553, "bleu": [228, 233, 535, 542], "bleu_hook": 228, "bleu_scor": 228, "bleu_token": 227, "bleu_util": 233, "blob": [3, 135, 177, 178, 227, 228, 231, 232, 234, 262, 536], "blob_siz": 31, "block": [31, 143, 145, 169, 179, 182, 187, 192, 245, 281, 417, 433, 472, 476, 531, 539, 540, 542, 547, 552], "block_list": [145, 433], "block_mask": [169, 183], "block_num": [145, 433], "block_pattern": [143, 417], "block_prefix": [145, 433], "block_siz": [179, 404, 439, 476, 547], "blockfallbacktuningsampl": 277, "blocklist": [439, 471], "blockmaskcriterion": 169, "blocksiz": [31, 439, 451, 472, 539], "blockwis": 550, "blockwise_over_matmul_gemm_conv": 192, "blog": [439, 492, 543], "bloom": [474, 487, 492, 534, 542, 550, 553], "bloomz": [474, 550, 553], "blue": [476, 545], "bmm": [471, 476, 487, 547], "bn": 553, "bnb": [476, 547], "bnb_nf4": [439, 447], "bo": 195, "bodi": 488, "bool": [1, 29, 30, 31, 126, 133, 140, 144, 145, 153, 161, 175, 195, 209, 211, 221, 225, 228, 234, 277, 281, 286, 299, 303, 385, 396, 398, 406, 409, 412, 413, 418, 420, 423, 425, 426, 427, 433, 439, 442, 445, 451, 458, 461, 464, 465, 476, 477, 521, 535, 551], "bool_val": 90, "boolean": [1, 409], "boost": [473, 492, 537, 542, 543], "booster": 523, "border": 551, "both": [133, 195, 385, 443, 475, 476, 478, 483, 487, 488, 493, 523, 536, 542, 544, 547, 550, 552], "bottleneck": [476, 487, 547], "boudoukh": 542, "bound": [59, 151, 225, 230, 266, 331, 413, 535, 551], "boundari": [225, 551], "bowl": 232, "box": [225, 230, 234, 490, 535, 551, 552], "branch": [133, 385, 489], "brand": 533, "break": [94, 359, 524, 536], "breakthrough": [472, 539], "breviti": [227, 228, 535], "bridg": [493, 494, 531], "briefli": [487, 536, 550], "bright": 551, "bring": [487, 550], "broad": [469, 492, 531], "broadcast": [225, 524, 551], "broadcast_optimizer_st": 524, "broadcast_paramet": 524, "bronco": 232, "brought": [487, 538, 544], "buffer": [140, 396, 451], "bug": [489, 492], "build": [1, 29, 31, 100, 146, 147, 149, 150, 154, 238, 240, 242, 243, 244, 390, 413, 480, 493, 494, 495, 532, 538, 543, 552], "build_captured_dataload": 413, "build_slave_faker_model": 280, "build_torch_model": 473, "built": [60, 165, 184, 196, 197, 201, 205, 209, 210, 215, 217, 219, 220, 221, 222, 225, 234, 237, 245, 262, 301, 305, 332, 448, 480, 481, 493, 524, 536, 540, 544, 549, 551, 552], "builtin": [140, 396, 524], "busi": 543, "button": [489, 531], "bypass_reshap": [52, 53, 324, 325], "byte": [140, 396, 413], "byte_arrai": [140, 396], "bytes_or_buff": 451, "bytesio": [140, 396], "c": [3, 59, 154, 211, 331, 465, 476, 482, 487, 527, 547, 552], "c1": [59, 331], "c1c2": [59, 331], "c2": [59, 331], "c6a": 553, "c6g": 553, "c6i": 553, "c_": [476, 547], "c_out": 476, "cach": [209, 476, 487, 492, 527, 544, 547], "cache_dir": [141, 398, 447], "cache_kl": 1, "cache_minmax": 1, "caffenet": 553, "cal_scal": 413, "calcul": [30, 45, 145, 153, 169, 177, 192, 195, 212, 213, 231, 232, 271, 317, 387, 413, 425, 452, 465, 471, 474, 476, 480, 487, 519, 535, 536, 540, 542, 544, 547, 549, 550, 552], "calculate_md5": 211, "calculate_ms": 465, "calculate_quant_min_max": 145, "calculate_scale_zp": 30, "calib": [145, 292, 293, 294, 297, 298, 494], "calib_cfg": 1, "calib_data": [1, 139], "calib_dataload": [262, 284, 301, 302, 305, 478, 479, 480, 481, 490, 521, 530, 535, 536, 544, 545, 546, 547], "calib_func": [33, 145, 262, 284, 301, 302, 305, 306, 433, 471, 480, 492, 546], "calib_iter": [284, 288, 301, 302, 305, 480, 494], "calib_method": 3, "calib_model": 1, "calib_num": 413, "calib_registri": 3, "calib_tensor": 1, "calibcollector": 1, "calibdata": 1, "calibr": [1, 4, 31, 34, 74, 75, 125, 145, 151, 195, 198, 199, 262, 285, 301, 305, 346, 412, 413, 418, 438, 442, 460, 469, 471, 475, 476, 477, 480, 487, 492, 493, 495, 530, 531, 542, 544, 547, 552], "calibration_data": [84, 92, 357], "calibration_sampling_s": [195, 536], "calibratorbas": 3, "call": [1, 29, 140, 146, 161, 173, 181, 182, 187, 230, 396, 413, 445, 480, 483, 487, 490, 493, 521, 530, 542, 544, 550, 551], "call_count": 161, "call_on": 151, "callabl": [140, 153, 195, 232, 284, 301, 302, 305, 396, 412, 437, 438, 439, 442, 443, 447, 448, 477, 480, 520, 521], "callback": [448, 454, 490, 536, 541, 542, 544], "callbacks_list": 448, "camembert": 553, "can": [29, 30, 31, 128, 135, 140, 150, 173, 174, 175, 180, 188, 190, 195, 198, 199, 208, 211, 225, 230, 232, 234, 235, 245, 262, 380, 396, 413, 442, 448, 465, 471, 472, 473, 474, 475, 476, 477, 478, 479, 480, 481, 483, 487, 490, 492, 493, 494, 495, 518, 520, 521, 523, 524, 526, 528, 531, 532, 534, 535, 536, 537, 538, 539, 540, 541, 542, 544, 545, 546, 547, 549, 550, 551, 552, 553], "candid": 406, "cannot": [230, 476, 490, 520, 527, 547], "cap": 492, "cap_s8_1_11": 495, "cap_s8_1_11_conv1d": 495, "capabl": [1, 32, 278, 289, 471, 473, 476, 487, 494, 495, 518, 528, 536, 537, 542, 544, 552], "capac": [476, 487, 547, 549], "captur": [391, 413, 465, 475, 476], "captureddataload": 413, "captureoutputtofil": [391, 465], "card": [476, 542], "carri": [412, 413, 542], "cascad": 532, "case": [30, 55, 59, 140, 151, 154, 195, 208, 224, 225, 245, 327, 331, 396, 441, 443, 469, 476, 477, 480, 487, 495, 520, 521, 523, 524, 528, 530, 535, 540, 542, 543, 544, 547, 548, 550, 551, 553], "cast": [30, 36, 308, 546, 551], "cast_tensor": 30, "castonnxtransform": 225, "castpytorchtransform": 225, "casttftransform": 225, "cat": [490, 526], "categor": 535, "categori": [211, 229, 518], "category_id_set": 230, "caus": [192, 476, 487, 494, 521, 542, 547], "causal": [431, 441, 542], "cce5ff": 552, "cd": [524, 532], "cdot": [487, 550], "ce": [163, 195, 536], "center": [225, 491, 492, 532, 551, 552], "centercrop": 551, "centercroptftransform": 225, "centercroptransform": 225, "cento": [532, 553], "central_fract": [221, 551], "cern": 543, "certain": [140, 194, 396, 481, 549], "certif": 489, "cfg": [56, 57, 145, 278, 328, 329, 412, 413, 417, 454, 494, 495], "cfg_filter": 454, "cfg_from_fil": 465, "cfg_preprocess": 454, "cfg_to_qconfig": [413, 417], "challeng": [472, 476, 539, 545], "chang": [29, 81, 128, 150, 181, 182, 184, 185, 187, 190, 195, 269, 352, 380, 413, 442, 465, 477, 489, 494, 521, 524, 527, 533, 536, 542, 551, 552], "channel": [29, 30, 31, 128, 149, 150, 171, 174, 179, 195, 221, 225, 380, 413, 433, 461, 471, 472, 474, 476, 492, 493, 495, 531, 532, 539, 542, 547, 551, 553], "channel_axi": [98, 147, 150], "channels_last": 221, "channelx1": [195, 542], "chapter": 494, "characterist": 488, "chart": [487, 544, 549], "chat": [474, 483, 534, 550, 553], "chatbot": [472, 539, 543], "chatglm2": 534, "chatglm3": 534, "check": [1, 31, 52, 53, 90, 133, 145, 192, 201, 211, 324, 325, 385, 391, 406, 413, 417, 427, 442, 445, 456, 464, 465, 480, 482, 492, 524, 532, 548], "check_cfg_and_qconfig": [145, 413, 417], "check_config": 192, "check_dataload": 201, "check_integr": 211, "check_key_exist": 465, "check_key_valid": 192, "check_model": 456, "check_mx_vers": 1, "checknumer": [65, 337], "checkout": 489, "checkpoint": [140, 243, 390, 396, 431, 441, 464, 538], "checkpoint_dir": [431, 441, 464], "checkpoint_sess": [243, 390], "checksum": 211, "chees": 520, "cheeseshopaddress": 520, "chen": 533, "cheng": [476, 487], "child": [59, 141, 331, 398, 420], "children": [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 19, 21, 22, 23, 25, 26, 141, 398], "chines": 543, "choic": [209, 476, 480, 487, 493, 535, 550], "choos": [211, 433, 461, 477, 487, 531, 543, 548, 550, 552], "chosen": [471, 494, 519], "chunk": [225, 551], "chunk_siz": 211, "ci": 489, "cifar": [211, 553], "cifar10": 211, "cifar100": 211, "circumst": 488, "ckpt": [133, 235, 243, 262, 385, 390, 553], "cl": [141, 146, 161, 163, 165, 175, 180, 188, 189, 190, 211, 218, 225, 234, 245, 274, 391, 398, 447, 465, 520], "claim": 533, "clamp_": [487, 550], "clarifi": 488, "class": [101, 138, 145, 170, 176, 183, 215, 235, 262, 285, 287, 291, 305, 397, 400, 447, 476, 477, 478, 480, 481, 490, 494, 520, 521, 535, 536, 540, 541, 544, 548, 552], "class_1": 211, "class_n": 211, "classdef": 552, "classic": [477, 552], "classif": [188, 209, 225, 234, 526, 535, 542, 543], "classifi": [173, 192, 209, 234], "classificationmnli": 553, "classificationmrpc": 553, "classificationqnli": 553, "classificationqqp": 553, "classificationsst": 553, "classifierheadsearch": 173, "classifierheadsearchertf": 173, "classregist": 280, "clean": [224, 398, 536], "clean_module_weight": 398, "clean_weight": 398, "clear": [207, 493, 528, 535, 536], "click": [492, 531, 532, 543], "client": [161, 492], "clip": [31, 413, 433, 476, 487, 547, 550], "clip_grad_norm_": 536, "clm": 542, "clone": [489, 532], "close": [128, 150, 380, 519], "cloud": [472, 489, 492, 539, 543], "cluster": 552, "cmd": [151, 532], "cnn": 553, "cnt": 536, "co": 542, "coarsest": [487, 550], "coco": [210, 217, 230, 234, 535, 542], "coco_dataset": 215, "coco_filt": 219, "coco_label_map": 233, "coco_tool": 233, "cocoev": 230, "cocoevalwrapp": 230, "cocomap": 535, "cocomapv2": [234, 535], "coconpi": 210, "cocoraw": 210, "cocorecorddataset": 210, "cocowrapp": 230, "code": [140, 173, 198, 199, 262, 396, 439, 448, 469, 473, 476, 478, 490, 492, 493, 494, 495, 523, 524, 530, 531, 533, 535, 540, 541, 542, 543, 544, 549, 550, 551], "codec": [140, 396], "codenam": [473, 534, 537], "coder": [531, 543], "coeff": 189, "coeffici": [40, 189, 312, 542], "cola": [209, 535, 553], "collabor": [489, 492], "collat": [133, 145, 385], "collate_fn": [200, 202, 203, 205, 206, 208, 387, 521], "collate_pr": 30, "collate_result": 145, "collate_tf_pr": [133, 385], "collate_torch_pr": 145, "collctor": 3, "collect": [1, 3, 30, 145, 153, 154, 223, 225, 232, 234, 391, 403, 412, 413, 416, 419, 421, 430, 452, 465, 480, 487, 494, 544, 552], "collect_layer_histogram": 459, "collect_layer_input": 192, "collect_weight_info": 145, "collector": [1, 135, 452], "collectorbas": 1, "collecttransform": 225, "color": [476, 542, 545], "colorjitt": 551, "column": [465, 476, 487, 547, 550], "column_map": 465, "columnwis": [50, 322], "com": [3, 135, 177, 178, 188, 209, 227, 228, 231, 232, 234, 262, 439, 488, 520, 532, 533, 536, 548, 549, 553], "comb": 523, "combin": [1, 145, 195, 198, 199, 221, 235, 262, 391, 417, 448, 465, 476, 479, 490, 492, 493, 531, 536, 541, 543, 544, 546, 547, 551, 552], "combine_cap": 1, "combine_histogram": [391, 465], "come": [140, 396, 472, 534, 539, 552], "comma": 418, "command": [151, 154, 448, 482, 483, 524], "command_prefix": 154, "comment": [138, 397, 476, 482, 488, 494, 535, 536, 547, 551], "commentsbalancedor": 553, "commit": [477, 480, 488, 489], "common": [124, 138, 140, 195, 223, 226, 299, 301, 302, 303, 305, 379, 396, 397, 437, 438, 439, 442, 447, 454, 474, 478, 479, 480, 488, 520, 523, 524, 526, 529, 530, 532, 536, 544, 550], "commonli": 542, "commun": 488, "comoress": 461, "compact": [536, 542], "compar": [135, 234, 465, 472, 475, 476, 481, 487, 523, 535, 539, 542, 544, 547, 549, 552], "compare_kei": 465, "compare_label": [234, 262, 535], "compare_object": 465, "compare_weight": 135, "comparison": [465, 547, 548], "compat": [133, 243, 385, 390, 489, 524, 538, 542, 548], "compatible_format": [138, 397], "compil": [227, 470, 475, 536], "complaint": 488, "complement": [473, 542], "complet": [278, 471, 493, 494, 542, 544, 552, 553], "complex": [156, 473, 520, 536, 537, 542], "complex_attr": 156, "complextfmap": 520, "compli": 552, "compon": [162, 284, 481, 490, 520, 524, 532, 533, 541, 542], "compos": [152, 225, 454, 551], "composableconfig": [152, 520], "composetransform": 225, "comprehens": [469, 477, 480, 536], "compress": [226, 245, 420, 439, 448, 461, 467, 469, 471, 474, 476, 477, 479, 481, 487, 492, 499, 529, 531, 536, 540, 541, 542, 543, 544, 550, 553], "compressed_model": 547, "compression_dim": [429, 461, 547], "compression_dtyp": [429, 461, 547], "compression_manag": [195, 448, 490, 523, 536, 541, 542, 544], "compressionmanag": 448, "compressor": [1, 151, 154, 162, 165, 177, 178, 188, 195, 221, 222, 225, 226, 233, 234, 235, 239, 246, 262, 270, 276, 290, 302, 303, 304, 305, 389, 392, 394, 436, 437, 438, 439, 440, 441, 442, 444, 445, 446, 447, 449, 451, 455, 467, 469, 471, 472, 473, 474, 475, 476, 477, 478, 480, 481, 482, 484, 487, 489, 493, 494, 495, 518, 519, 520, 522, 523, 524, 525, 526, 527, 528, 529, 530, 533, 534, 537, 538, 539, 540, 541, 542, 543, 544, 547, 548, 550, 551, 552, 553], "comput": [30, 31, 90, 135, 145, 227, 228, 231, 232, 234, 413, 417, 425, 448, 465, 471, 472, 473, 475, 476, 487, 519, 521, 523, 526, 535, 536, 537, 539, 542, 543, 544, 547, 550, 552], "compute_bleu": 228, "compute_const_folding_using_tf": 90, "compute_dtyp": 451, "compute_error": 135, "compute_spars": 465, "computemetr": 230, "concat": [16, 132, 384], "concat_gener": 225, "concaten": 413, "concatoper": 9, "concatv2": [109, 119, 132, 364, 374, 384, 528], "concept": [469, 530, 549], "concret": [133, 385, 390, 552], "conda": [527, 548], "condit": [70, 153, 209, 210, 211, 225, 263, 265, 342, 481, 533, 551, 552], "conduct": [469, 490, 536, 552], "conf": [146, 151, 162, 195, 198, 199, 235, 245, 262, 263, 264, 266, 267, 271, 273, 274, 278, 281, 448, 490, 495, 518, 530, 536, 537, 538, 541, 544, 545, 546, 547, 549, 550, 552], "confer": [135, 487, 542, 550], "confid": 145, "confidence_batch": [145, 552], "confidenti": 488, "config": [1, 31, 100, 101, 103, 107, 145, 151, 152, 153, 156, 160, 161, 169, 170, 171, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 198, 199, 209, 226, 235, 257, 261, 278, 279, 280, 281, 284, 288, 289, 300, 301, 302, 304, 305, 389, 406, 409, 412, 413, 417, 424, 427, 431, 438, 440, 442, 447, 448, 451, 454, 464, 465, 470, 471, 473, 475, 476, 477, 478, 494, 495, 499, 500, 518, 520, 521, 523, 524, 526, 531, 535, 536, 537, 538, 541, 542, 544, 546, 547, 549, 552], "config1": 153, "config2": 153, "config_file_path": 188, "config_inst": 151, "config_list": [152, 153], "config_map": [160, 427], "config_name_map": 160, "config_quantizable_lay": 103, "config_set": [153, 473, 478, 479, 480, 481], "config_sourc": 153, "configload": 153, "configmappingtyp": 427, "configproto": 261, "configregistri": [152, 160], "configs_map": [305, 399, 437, 442], "configset": 153, "configur": [1, 103, 134, 145, 151, 152, 153, 154, 161, 192, 195, 198, 199, 201, 211, 214, 234, 235, 245, 262, 271, 280, 301, 305, 406, 408, 409, 411, 413, 417, 422, 427, 437, 439, 442, 447, 448, 453, 454, 458, 463, 464, 477, 481, 483, 490, 493, 494, 536, 540, 542, 544, 547, 548, 550, 551, 552, 553], "confirm": 494, "conflict": [90, 520, 527], "connect": [169, 542, 549], "consecut": [171, 173, 174, 542], "conserv": [195, 270], "conservativetunestrategi": 267, "consid": [31, 133, 234, 385, 488, 519, 520, 552], "consider": [479, 550], "consist": [41, 48, 313, 320, 476, 489, 490, 520, 550, 552], "consolid": 532, "const": [41, 42, 48, 49, 52, 53, 55, 67, 83, 313, 314, 320, 321, 324, 325, 327, 339, 354], "const_node_valu": 90, "constant": [90, 158, 266, 276, 388, 446, 458, 459, 520, 521, 528, 551], "constant_valu": 225, "constfold": 528, "constrain": 545, "constraint": [195, 536, 542, 549, 552], "construct": [140, 209, 212, 213, 216, 223, 234, 239, 243, 280, 387, 389, 390, 396, 454, 481, 488, 494, 495, 524, 542, 552], "construct_function_from_graph_def": [133, 385], "consum": [481, 521], "consumpt": [472, 476, 487, 539, 550], "contact": [488, 548, 549], "contain": [1, 52, 53, 55, 59, 124, 133, 135, 140, 145, 151, 162, 170, 173, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 190, 192, 195, 198, 199, 209, 210, 211, 230, 231, 232, 235, 262, 324, 325, 327, 331, 379, 385, 396, 406, 409, 412, 413, 417, 425, 429, 448, 454, 458, 464, 469, 476, 480, 492, 519, 527, 531, 535, 542, 547, 552], "content_fold": 216, "context": [1, 465, 476, 487, 547], "contextu": 542, "contigu": 145, "continu": [178, 230, 476, 534, 536, 542], "contract": [43, 315], "contrast": [175, 551], "contrib": [3, 226], "contribut": [488, 492, 542], "control": [146, 195, 490, 536, 542, 552], "conv": [16, 43, 47, 51, 56, 57, 58, 77, 94, 149, 195, 315, 319, 323, 328, 329, 330, 348, 359, 490, 494, 495, 536, 542, 544, 552], "conv1": [195, 478, 544], "conv1d": [194, 477, 495], "conv1d_relu": 526, "conv2d": [38, 44, 45, 46, 50, 51, 56, 110, 120, 128, 294, 295, 298, 303, 310, 316, 317, 318, 322, 323, 328, 365, 375, 380, 413, 471, 494, 495, 526, 528, 550, 552], "conv2d_config": 478, "conv2d_relu": 526, "conv2dbackpropinput": [111, 366], "conv3d": [56, 110, 328, 365], "conv3dbackpropinputv2": [111, 366], "conveni": [477, 536], "convent": [211, 230, 472, 489, 539], "convers": [39, 40, 195, 311, 312, 406, 473, 474, 487, 489, 493, 494, 536, 537, 544, 546, 550], "convert": [1, 30, 33, 34, 35, 38, 39, 40, 41, 42, 51, 59, 71, 84, 85, 87, 88, 89, 90, 116, 121, 125, 127, 134, 145, 173, 195, 209, 221, 224, 225, 230, 278, 281, 283, 288, 289, 306, 307, 310, 311, 312, 313, 314, 323, 331, 343, 355, 371, 376, 392, 399, 406, 437, 442, 447, 449, 457, 470, 471, 472, 473, 474, 475, 476, 477, 479, 480, 483, 487, 490, 492, 494, 529, 536, 537, 544, 546, 547, 550, 551, 552], "convert_add_to_biasadd": [61, 333], "convert_bf16": 494, "convert_by_vocab": 224, "convert_examples_to_featur": [209, 225], "convert_layout": [61, 333], "convert_leakyrelu": [61, 333], "convert_nan_to_random": [61, 333], "convert_placeholder_to_const": [61, 333], "convert_tensorflow_tensor_to_onnx": 90, "convert_to_unicod": 224, "convertaddtobiasaddoptim": [38, 310], "converted_model": [195, 235, 536, 537], "convertlayoutoptim": [39, 311], "convertleakyreluoptim": [40, 312], "convertnantorandom": [41, 313], "convertplaceholdertoconst": [42, 314], "convolut": 543, "convoper": 10, "cooper": [473, 532, 537, 543], "coordin": [225, 266, 551, 552], "copi": [195, 465, 521], "copyreg": [138, 397], "copyright": [489, 533], "core": [151, 154, 195, 285, 407, 424, 476, 482, 483, 489, 492, 518, 532, 533, 553], "core_id": 151, "core_list": [151, 154], "core_list_per_inst": 154, "cores_per_inst": [151, 195, 518, 536], "corner": [225, 489, 493, 495, 551], "corpor": 533, "correct": [128, 150, 192, 195, 230, 231, 232, 234, 380, 488], "correspond": [3, 135, 173, 184, 195, 209, 227, 230, 234, 412, 413, 417, 427, 454, 465, 471, 477, 487, 493, 528, 536, 542, 544, 549, 552], "cost": [471, 472, 476, 487, 539, 544, 547], "could": [140, 149, 175, 198, 199, 211, 235, 262, 396, 413, 448, 469, 473, 475, 476, 478, 480, 487, 488, 490, 523, 527, 536, 541, 542, 544, 547, 550], "count": [1, 476, 487, 547], "counter": 90, "coupl": 208, "cover": [489, 526, 530, 543], "coverag": 489, "cowork": [431, 441], "cpu": [76, 77, 78, 79, 139, 140, 145, 154, 161, 195, 347, 348, 349, 350, 391, 396, 398, 401, 413, 420, 429, 431, 433, 441, 443, 461, 465, 473, 475, 477, 480, 482, 494, 518, 519, 531, 536, 537, 543, 544, 545, 546, 547], "cpu_acceler": 443, "cpu_execution_tim": 251, "cpu_index": 154, "cpu_rang": 154, "cpuexecutionprovid": [2, 28, 29, 31, 537, 544], "cpufreq": 520, "cpuinfo": [161, 391, 465], "craft": [472, 539], "crbug": 520, "creat": [1, 3, 90, 138, 156, 195, 200, 209, 211, 230, 257, 261, 278, 280, 281, 387, 397, 406, 409, 451, 454, 469, 471, 487, 488, 493, 538, 542, 544, 549, 552], "create_data_exampl": 1, "create_dataload": 454, "create_dataset": 454, "create_eval_func": 454, "create_obj_from_config": 459, "create_onnx_config": 257, "create_quant_spec_from_config": 409, "create_tf_config": 261, "create_train_func": 454, "create_xiq_quantizer_from_pt2e_config": 409, "criteria": [170, 195, 481, 490, 550], "criterion": [135, 162, 164, 165, 169, 175, 180, 181, 182, 184, 187, 191, 195, 523, 536, 542, 544, 550, 552], "criterion_class": [169, 191], "criterion_conf": 195, "criterion_registri": 163, "criterion_typ": 163, "critet": 163, "critic": [184, 420, 480, 488], "crop": [221, 225, 551], "crop_pad": 225, "crop_ratio": 216, "cropres": 551, "cropresizetftransform": 225, "cropresizetransform": 225, "croptoboundingbox": [225, 551], "cross": [165, 234, 482, 530, 552], "cross_memori": 482, "crossentropyloss": [163, 195, 536], "crowd": 230, "crucial": [475, 542], "cs412": 3, "cse": [59, 83, 331, 354], "csv": 465, "ctx": 1, "cube": [195, 542], "cuda": [140, 192, 396, 413, 425, 443, 477, 537, 542, 544], "cuda_acceler": 443, "cudaexecutionprovid": [537, 544], "current": [1, 55, 89, 154, 169, 170, 173, 176, 180, 183, 195, 266, 272, 327, 413, 433, 441, 447, 465, 475, 476, 477, 481, 490, 492, 493, 495, 519, 520, 524, 528, 529, 536, 540, 542, 544, 547, 550, 552], "current_pattern": 173, "current_sparsity_ratio": 180, "curv": 535, "custom": [100, 138, 145, 151, 234, 245, 292, 293, 294, 295, 297, 298, 397, 433, 464, 471, 477, 481, 487, 492, 518, 523, 542, 543, 547, 549], "custom_metr": 530, "custom_tune_config": [473, 478, 479, 480, 481], "customis": [521, 535], "customized_msg": [161, 391, 465], "cv": [195, 471, 475, 477, 480, 542], "cv2": 221, "cvf": [487, 550], "d": [59, 145, 331, 417, 530, 542], "d1": [59, 331, 465], "d2": 465, "d_": 195, "d_conf": [195, 523, 536, 541], "dai": 552, "damp_perc": 451, "dampen": 31, "darvish": [472, 539], "data": [1, 29, 30, 31, 41, 90, 125, 133, 135, 140, 145, 149, 161, 173, 195, 198, 199, 226, 235, 256, 260, 262, 266, 278, 280, 283, 301, 305, 313, 385, 388, 391, 396, 403, 404, 409, 413, 418, 433, 448, 451, 454, 458, 465, 469, 470, 471, 472, 473, 475, 476, 477, 480, 487, 492, 493, 519, 521, 524, 528, 532, 535, 536, 537, 539, 544, 546, 547, 548, 549, 550, 551, 552], "data_dir": 209, "data_format": [211, 221, 292, 294, 297, 298], "data_it": [1, 173], "data_load": [33, 34, 306, 493], "data_path": 214, "data_sourc": [207, 454], "data_typ": [280, 418], "data_x": 1, "databas": 211, "databrick": [474, 534, 550, 553], "datafunc": 211, "dataiterload": 1, "dataload": [1, 2, 29, 31, 125, 126, 135, 145, 151, 170, 171, 173, 188, 192, 198, 199, 209, 220, 256, 260, 262, 283, 286, 387, 413, 418, 420, 433, 448, 454, 469, 480, 490, 493, 494, 523, 524, 530, 536, 537, 541, 542, 544, 545, 546, 547, 550, 551], "dataloader_cfg": 454, "dataloaderwrap": 1, "datalod": 413, "dataset": [125, 126, 145, 188, 198, 199, 200, 202, 203, 205, 206, 207, 208, 220, 230, 231, 232, 234, 235, 262, 283, 286, 387, 418, 448, 451, 454, 474, 476, 478, 479, 480, 487, 493, 494, 521, 524, 535, 536, 542, 544, 547, 548, 550, 552, 553], "dataset_format": 211, "dataset_nam": 418, "dataset_registri": 211, "dataset_typ": 211, "datatyp": [90, 145, 546, 552, 553], "date": [476, 547], "datetim": 195, "dbox": 490, "dco": 489, "ddr5": 553, "deal": 448, "debug": [281, 462, 552], "debug_stripp": 528, "dec": 543, "decapoda": 553, "decid": [101, 195, 228, 480, 482, 493, 494, 536, 544, 548, 552], "decim": 465, "decis": [520, 535], "declar": 520, "decod": [140, 221, 227, 396, 451, 535, 551], "decode_singl": 490, "decodeimag": 551, "decompos": [52, 53, 324, 325], "decor": [3, 21, 52, 53, 55, 133, 146, 152, 161, 165, 175, 180, 188, 190, 225, 234, 245, 274, 324, 325, 327, 391, 413, 445, 447, 465, 490, 493, 552], "decorator_metr": 234, "decreas": [83, 354, 542], "dedic": 195, "dedicated_qdq_pair": [28, 195, 544], "deem": 488, "deep": [391, 465, 469, 472, 473, 477, 480, 487, 492, 493, 494, 521, 531, 532, 536, 537, 539, 543, 544, 552], "deep_get": [245, 391, 465], "deep_set": [245, 465], "deepcopi": 195, "deepen": 543, "deepst": 195, "def": [52, 53, 55, 153, 198, 199, 262, 281, 324, 325, 327, 391, 447, 448, 473, 474, 477, 478, 480, 481, 487, 490, 493, 520, 521, 523, 524, 535, 536, 544, 550, 552], "default": [3, 31, 82, 133, 140, 145, 152, 156, 161, 192, 195, 198, 199, 202, 209, 210, 211, 221, 225, 227, 234, 243, 280, 299, 303, 353, 385, 390, 391, 396, 398, 408, 409, 412, 413, 418, 425, 431, 433, 435, 437, 438, 439, 441, 442, 447, 451, 454, 457, 458, 461, 465, 471, 472, 473, 474, 476, 477, 480, 481, 482, 483, 490, 493, 520, 521, 528, 531, 535, 536, 537, 539, 540, 542, 544, 546, 547, 549, 550, 551, 552], "default_alpha": 550, "default_col": [202, 387], "default_config": 192, "default_dtyp": 278, "default_opset_vers": 127, "default_sampl": [153, 481], "default_sq_alpha_arg": 303, "default_v": 156, "default_white_list": [152, 299, 303, 439], "default_workspac": 195, "defaultdataload": [202, 208], "defin": [71, 135, 156, 173, 175, 180, 181, 182, 187, 188, 189, 190, 195, 198, 199, 235, 262, 343, 448, 451, 464, 471, 478, 480, 481, 487, 488, 492, 493, 494, 521, 523, 528, 531, 535, 536, 541, 542, 544, 547, 549, 550, 552], "definit": [133, 142, 203, 207, 385, 429], "defult": [431, 441], "degrad": [523, 542, 552], "delet": 542, "delete_assign": 261, "deliv": [473, 476, 536, 543, 548], "demand": [476, 487, 547], "demo": [154, 477, 536], "democrat": 543, "demonstr": [472, 476, 481, 483, 492, 525, 539], "denot": [487, 550], "dens": [173, 190, 195, 295, 542, 553], "dense_shap": 213, "densenet": 553, "densiti": 552, "denver": 232, "depend": [1, 198, 199, 235, 262, 448, 489, 492, 527, 528, 532, 544, 552], "deploi": [476, 481, 487, 489, 536, 547, 552], "deploy": [477, 522, 543, 545, 550], "deprec": [153, 520, 548, 551], "depth": [145, 417, 546], "depth_multipli": [294, 298], "depthwis": [294, 413], "depthwise_constraint": [294, 298], "depthwise_conv2d": 295, "depthwise_initi": [294, 298], "depthwise_regular": [294, 298], "depthwiseconv2d": 294, "depthwiseconv2dn": [50, 56, 110, 120, 322, 328, 365, 375, 528], "dequant": [29, 30, 31, 36, 73, 76, 77, 78, 79, 81, 135, 145, 308, 345, 347, 348, 349, 350, 352, 398, 413, 423, 429, 433, 465, 487, 490, 494, 550], "dequantize_cast_optim": [37, 309], "dequantize_data": 30, "dequantize_data_with_scale_zero": 30, "dequantize_per_channel": [487, 550], "dequantize_tensor": 465, "dequantize_weight": 465, "dequantizecastoptim": [36, 308], "dequantizelinear": 30, "deriv": [162, 169, 177, 178, 179, 185, 186, 187, 188, 189, 190, 191], "derogatori": 488, "desc": 536, "desc_act": 451, "descent": [173, 439, 476, 487, 492, 543], "describ": [493, 495, 520, 528], "descript": [1, 117, 281, 372, 471, 474, 490, 494, 495, 521, 550], "deseri": [140, 396], "design": [162, 208, 234, 267, 469, 475, 477, 480, 492, 536, 542, 544], "desir": [195, 221, 225, 409, 474, 494, 495, 542, 550, 551], "despit": 481, "dest": 90, "destin": [133, 385, 456], "detach": [487, 550], "detail": [29, 149, 152, 173, 225, 413, 439, 465, 466, 469, 473, 474, 476, 477, 478, 479, 480, 487, 488, 492, 494, 495, 519, 520, 528, 530, 534, 535, 536, 537, 542, 547, 548, 549, 550, 552], "detect": [143, 145, 161, 173, 195, 230, 234, 239, 417, 443, 447, 477, 489, 490, 542, 552], "detect_processor_type_based_on_hw": 161, "detection_box": [230, 536], "detection_boxes_list": 230, "detection_class": [230, 536], "detection_classes_list": 230, "detection_mask": 230, "detection_scor": [230, 536], "detection_scores_list": 230, "detection_typ": 230, "detectionboxes_precis": 234, "detectioncoco": 553, "detections_list": 230, "detector": 143, "determin": [169, 175, 180, 191, 195, 427, 460, 470, 475, 481, 483, 488, 490, 519, 542, 544], "determinist": 536, "dettmer": [476, 487, 547], "dev": 527, "develop": [135, 156, 245, 472, 473, 489, 490, 520, 532, 536, 537, 539, 542, 543, 546, 549], "deviat": [225, 551], "devic": [1, 64, 74, 75, 76, 77, 78, 79, 82, 92, 116, 121, 132, 139, 140, 145, 170, 173, 174, 188, 192, 195, 336, 346, 347, 348, 349, 350, 353, 357, 371, 376, 384, 396, 398, 401, 413, 417, 418, 420, 423, 425, 429, 431, 433, 441, 445, 447, 461, 473, 476, 477, 483, 487, 492, 494, 521, 536, 537, 542, 545, 547], "device_id": [140, 396], "device_nam": [443, 445], "device_synchron": 445, "devop": 489, "df": 90, "diag": 31, "diagnosi": 543, "diagon": [31, 476, 547], "diagram": [476, 494, 495, 552], "dict": [1, 31, 101, 133, 134, 135, 140, 145, 146, 151, 154, 160, 165, 169, 170, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 194, 195, 198, 199, 208, 229, 230, 231, 232, 234, 235, 243, 262, 277, 280, 281, 289, 299, 303, 305, 385, 390, 391, 396, 399, 404, 406, 411, 412, 413, 417, 418, 419, 420, 425, 427, 433, 435, 437, 438, 439, 442, 447, 448, 451, 452, 454, 456, 458, 464, 465, 476, 477, 478, 483, 490, 494, 520, 526, 535, 542, 544, 550, 552], "dictionari": [52, 53, 55, 133, 134, 135, 140, 145, 194, 195, 224, 230, 324, 325, 327, 391, 396, 404, 413, 417, 431, 441, 447, 465], "differ": [128, 146, 150, 152, 154, 156, 157, 163, 184, 195, 203, 211, 225, 234, 243, 245, 380, 390, 444, 460, 471, 476, 477, 480, 483, 487, 488, 490, 494, 521, 524, 525, 529, 530, 531, 535, 536, 538, 540, 542, 544, 547, 550, 551, 552], "difficult": [474, 479, 481, 487, 493, 550], "difficulti": [474, 479, 487, 550], "diffus": [492, 543], "digit": [227, 465, 543], "dilat": [43, 315], "dilated_contract": [61, 333], "dilatedcontract": [43, 315], "dilation_r": [292, 294, 298], "dim": [225, 487, 550, 551], "dimens": [52, 53, 90, 202, 225, 324, 325, 387, 413, 476, 547, 551], "dir": [145, 209, 461, 464, 527, 530], "direct": [85, 179, 355, 477, 542], "direct8bit": 11, "direct8bitoper": 11, "direct_q8": 16, "directli": [171, 195, 208, 230, 234, 478, 535, 536, 542, 544], "directori": [195, 210, 211, 243, 390, 408, 431, 441, 461, 464, 465, 492, 524, 527], "disabl": [133, 195, 391, 488, 546, 547, 550], "disable_al": 195, "disable_quanted_input": 451, "disable_random": [133, 391], "discard": 521, "discord": 492, "discourag": 542, "discov": 519, "discret": [3, 552], "discrimin": 553, "discuss": [477, 492], "dispatch": [494, 531], "displai": [195, 277, 278, 391, 465], "distanc": 465, "distil": [162, 195, 469, 492, 525, 529, 531, 541], "distil_loss": [195, 536], "distilbert": [209, 537, 543, 553], "distillation_conf": 162, "distillation_criterion": [523, 536, 541], "distillationcallback": 162, "distillationconfig": [195, 448, 523, 536, 541], "distilroberta": 553, "distinct": [472, 539], "distort": 494, "distribut": [1, 3, 128, 150, 195, 200, 202, 203, 205, 206, 207, 208, 380, 387, 460, 469, 471, 476, 480, 487, 494, 521, 532, 543, 544, 547, 548, 550, 553], "distribute_calib_tensor": 1, "distributedoptim": 524, "distributedsampl": 524, "distutil": 527, "div_": [487, 550], "dive": [469, 528], "diverg": [3, 452, 460, 495, 519, 552], "divid": [487, 521, 550, 552], "divis": [31, 413], "dl": [235, 473, 530, 543, 553], "dlabel": 490, "dlrm": 234, "dmlexecutionprovid": 544, "dnnlexecutionprovid": [537, 544], "do": [162, 188, 195, 208, 209, 227, 230, 411, 458, 464, 471, 477, 488, 494, 520, 524, 528, 531, 535, 536, 542, 546, 548, 550, 552], "do_blockwis": [413, 439, 550], "do_constant_fold": 458, "do_lower_cas": [209, 224, 225, 551], "doc": [177, 178, 195, 234, 262, 277, 278, 281, 391, 443, 465, 492, 532, 535, 536], "doc_span_index": 225, "doc_strid": [225, 551], "doc_token": 225, "docker": 527, "docstr": [195, 281], "docstyl": 489, "document": [225, 281, 469, 473, 478, 479, 487, 494, 495, 499, 524, 534, 537, 542, 548, 551], "doe": [227, 280, 301, 305, 475, 476, 480, 520, 521, 535, 536, 547, 548, 551], "doesn": [140, 225, 396, 473, 480, 493, 524, 536, 537], "dolli": [474, 534, 542, 550, 553], "domain": [89, 90, 195, 542, 552], "don": [128, 150, 175, 195, 380, 474, 475, 490, 542, 552], "done": [487, 490, 523, 542, 544], "dong": 135, "dot": [391, 465, 473, 487, 537, 544], "dotdict": [195, 245, 465], "doubl": [438, 439, 476, 543], "double_qu": 447, "double_quant_bit": [439, 476], "double_quant_dtyp": [439, 476], "double_quant_group_s": [439, 476], "double_quant_typ": 447, "double_quant_use_sym": [439, 476], "dowload_hf_model": [141, 398, 447], "download": [141, 211, 398, 447, 492, 532, 548], "download_url": 211, "downstream": 542, "dq": [92, 94, 116, 357, 359, 371, 470, 475, 477, 487, 550], "draw": [521, 549, 552], "drive": 495, "driven": [245, 492, 529, 536, 540], "drop": [192, 230, 418, 473, 474, 476, 487, 489, 536, 537, 542, 547, 550, 553], "drop_last": [203, 207, 387], "dry_run": 524, "dscore": 490, "dtype": [30, 31, 87, 90, 195, 212, 213, 221, 225, 387, 401, 406, 409, 413, 423, 429, 433, 439, 461, 473, 476, 477, 487, 494, 495, 526, 528, 544, 547, 550, 551], "dtype_map": 30, "dtype_to_nam": 30, "duc": 553, "due": [154, 487, 495, 526, 542, 544, 550], "dummi": [44, 173, 212, 213, 234, 316, 387, 480, 535, 536], "dummy_biasadd": [61, 333], "dummy_dataset": 215, "dummy_dataset_v2": 215, "dummy_v2": [213, 387], "dummydataset": [212, 213, 387, 480], "dummydatasetv2": 387, "dump": [2, 138, 145, 151, 154, 397, 413, 417, 447, 458, 465, 480, 487, 489, 544], "dump_class_attr": 465, "dump_data_to_loc": 465, "dump_elapsed_tim": [161, 391, 465, 493], "dump_fp32": [131, 383], "dump_model_op_stat": [413, 417, 447], "dump_numa_info": 154, "dump_op_typ": 2, "dump_stats_path": [439, 471], "dump_tabl": 465, "dump_table_to_csv": 465, "duplic": [83, 93, 266, 354, 358], "durat": 549, "dure": [1, 138, 140, 175, 179, 190, 195, 245, 396, 397, 413, 442, 447, 465, 474, 475, 477, 480, 487, 492, 494, 529, 536, 538, 540, 541, 542, 544, 550], "dyna": 195, "dynam": [140, 195, 200, 278, 387, 396, 409, 435, 437, 439, 458, 476, 477, 492, 493, 521, 526, 529, 531, 536, 543, 552, 553], "dynamic_ax": [195, 458, 526], "dynamic_length": 209, "dynamic_max_gap": [418, 439, 476], "dynamic_quant_export": 458, "dynamic_shap": 435, "dynamicquantconfig": [439, 470], "dynamo": [475, 477], "e": [140, 154, 175, 195, 396, 476, 483, 487, 488, 489, 492, 525, 542, 547, 550, 552], "e16": 489, "e2m1": [472, 476, 539, 547], "e2m3": [472, 539], "e3m2": [472, 539], "e4m3": [439, 471, 472, 492, 539], "e5m2": [471, 472, 539], "e8m0": [472, 539], "each": [126, 133, 135, 140, 145, 154, 192, 195, 207, 211, 214, 221, 225, 228, 230, 231, 232, 271, 286, 387, 396, 412, 413, 417, 433, 465, 469, 476, 479, 482, 487, 489, 493, 494, 495, 520, 523, 528, 536, 540, 542, 545, 547, 549, 551, 552], "eager": [188, 261, 435, 470, 475, 476, 477, 524, 531, 544, 546], "earli": [195, 487, 536, 544, 552], "eas": [477, 480, 532, 543], "easi": [209, 475, 477, 480, 526, 536, 543, 544, 547, 549], "easier": 543, "easili": [245, 481, 487, 493, 540, 550], "econom": 488, "ecosystem": [492, 543], "edg": 551, "edit": 488, "edouard": [487, 550], "edu": [3, 211], "educ": 488, "effect": [187, 475, 476, 493, 542, 543], "effici": [29, 149, 413, 475, 483, 487, 492, 519, 521, 541, 542, 543, 547, 550, 552], "efficientnet": 553, "efficientnet_b0": 553, "efficientnet_b3": 553, "effort": 536, "eg": [145, 211, 433], "either": [140, 153, 195, 230, 396, 475, 480, 481, 483, 487, 541, 544], "elaps": [161, 391, 465], "electra": 553, "electron": 488, "elem_format": 404, "elem_typ": 90, "element": [31, 153, 177, 178, 192, 207, 230, 387, 404, 433, 465, 472, 476, 487, 531, 535, 539, 542, 547, 550], "elementwise_over_al": 192, "elementwise_over_matmul_gemm_conv": 192, "elemformat": 404, "eleutherai": [474, 529, 534, 550, 553], "elia": [476, 487, 547], "elimin": [51, 323], "ellipsi": [406, 443], "els": [1, 133, 195, 207, 245, 385, 433, 547], "em": 553, "email": 492, "emb": 476, "embed": [145, 420, 519, 542], "embed_layernorm": 16, "embed_out": 542, "embedlayernorm": 12, "embedlayernormalizationoper": 12, "emerg": [472, 539, 550], "emit": 471, "emnlp": [492, 543], "emot": 553, "empathi": 488, "empir": [128, 150, 380], "empow": [472, 539], "empti": [141, 195, 398, 447, 471, 476, 477, 545], "emsp": 542, "emul": [477, 487, 536, 544], "en": [492, 532], "enabl": [31, 94, 135, 180, 195, 359, 409, 473, 475, 476, 480, 494, 495, 524, 537, 542, 543, 550, 552], "enable_act": 135, "enable_al": 195, "enable_auto_scal": [31, 547], "enable_bas": 195, "enable_eager_execut": 524, "enable_extend": 195, "enable_full_rang": [418, 433, 439, 461, 476, 545, 547], "enable_minmax_tun": [418, 439, 476], "enable_mse_search": [31, 547], "enable_quanted_input": [418, 439, 476], "encapsul": [95, 198, 199, 235, 262, 360, 448, 538], "encod": [140, 230, 396, 451, 551], "encodejp": 551, "encount": [521, 527], "end": [133, 180, 181, 182, 187, 195, 209, 224, 225, 263, 265, 385, 493, 494, 495, 523, 528, 532, 536, 540, 542, 547, 551, 552], "end_epoch": 536, "end_posit": 225, "end_step": [180, 195, 536, 542], "endlessli": 552, "energi": [472, 539], "engin": 473, "english": 542, "enhanc": [483, 519, 542, 543, 546], "enough": [156, 413, 480, 487, 544], "enough_memo_store_scal": 413, "ensp": 551, "ensur": [1, 225, 266, 475, 478, 524, 544, 551], "ensure_list": 1, "entir": [262, 448, 474, 476, 479, 490, 494, 495, 519, 542], "entranc": [64, 201, 336], "entri": [52, 53, 55, 135, 165, 301, 302, 305, 324, 325, 327, 437, 438, 441, 442, 465, 477, 520, 533], "entropi": [195, 519, 552], "enum": 1, "enumer": [156, 157, 448, 472, 493, 523, 524, 536, 539, 541, 542], "env": [151, 527], "env_var": 151, "environ": [30, 151, 443, 446, 473, 477, 483, 488, 492, 518, 552], "eoferror": [138, 397], "ep": [3, 150, 537], "epoch": [162, 181, 182, 187, 448, 521, 523, 524, 536, 541, 542], "equal": [90, 128, 133, 150, 281, 380, 391, 465, 472, 539, 542, 547], "equal_dict": 465, "equat": [30, 232, 234, 487, 544, 550], "equival": [68, 340, 432, 472, 474, 476, 479, 487, 492, 539, 543, 547, 550], "erf": [54, 326], "error": [31, 90, 135, 140, 234, 271, 396, 413, 451, 462, 471, 476, 487, 527, 535, 547, 550, 552], "error_msg": 90, "especi": 529, "essenti": [519, 527], "estim": [133, 234, 243, 390, 552], "estimator_sess": [243, 390], "et": [135, 472, 476, 487, 519, 539, 547, 550], "etc": [151, 162, 224, 232, 235, 262, 392, 464, 492, 531, 542, 549, 552], "ethnic": 488, "euclidean": 465, "eural_compressor": 245, "eval": [490, 520, 521, 544], "eval_acc": 153, "eval_acc_fn": [473, 478, 480], "eval_arg": [153, 302, 438, 473, 477, 478, 480], "eval_dataload": [151, 195, 198, 199, 235, 262, 263, 264, 266, 267, 271, 273, 274, 448, 518, 530, 535, 536, 544, 545, 552], "eval_fn": [153, 302, 438, 473, 477, 478, 479, 480, 481], "eval_fn_wrapp": 479, "eval_frequ": 162, "eval_func": [125, 198, 199, 235, 262, 263, 264, 266, 267, 271, 273, 274, 281, 283, 448, 490, 521, 523, 524, 536, 544, 545, 546, 547, 552], "eval_metr": [198, 199, 235, 262, 263, 264, 266, 267, 271, 273, 274, 448, 535, 544], "eval_perf": 153, "eval_result": 520, "eval_result_of_q_model": 153, "evalu": [151, 153, 162, 175, 198, 199, 209, 227, 230, 231, 232, 234, 235, 245, 262, 438, 448, 454, 477, 479, 480, 481, 487, 493, 494, 520, 523, 530, 531, 534, 535, 536, 537, 540, 542, 544, 549, 550, 552], "evaluate_squad": 233, "evaluation_result": 524, "evaluation_time_cost": 524, "evaluationfuncwrapp": 153, "even": [487, 545, 547, 550], "evenli": 521, "event": 488, "everi": [52, 53, 55, 175, 178, 180, 195, 324, 325, 327, 476, 493, 521, 545, 547, 552], "everyon": 488, "everyth": 192, "exact": [231, 418], "exact_match_scor": 231, "exactli": 524, "exampl": [1, 31, 135, 140, 145, 151, 152, 153, 156, 160, 173, 174, 188, 195, 209, 210, 211, 221, 225, 230, 231, 232, 234, 235, 245, 262, 280, 281, 391, 396, 408, 411, 426, 433, 435, 443, 447, 448, 464, 465, 469, 474, 480, 481, 483, 488, 492, 494, 495, 499, 529, 530, 531, 546, 548, 551, 552, 554], "example_algo": [391, 447], "example_gener": 281, "example_index": 225, "example_inp": 145, "example_input": [145, 195, 408, 411, 412, 413, 417, 432, 433, 435, 438, 442, 458, 464, 470, 474, 475, 476, 477, 526], "examplealgorithm": 152, "examplealgorithmconfig": 152, "exampleclass": 281, "exce": [225, 547, 551], "exceed": [243, 390], "excel": [487, 547], "except": [140, 281, 396, 413, 465, 476, 520, 544, 545], "exchang": 526, "exclud": [195, 471, 493, 519, 546], "excluded_op_nam": [56, 57, 195, 328, 329, 536, 542], "excluded_precis": [195, 439, 546], "execut": [29, 30, 39, 140, 151, 157, 180, 181, 182, 195, 261, 262, 263, 265, 311, 392, 396, 412, 420, 448, 454, 464, 465, 475, 476, 487, 523, 536, 537, 541, 542, 544, 547, 549, 552, 553], "executionprovid": 553, "exemplifi": 542, "exhaust": [195, 270, 413], "exhaustivetunestrategi": 268, "exist": [39, 151, 243, 311, 390, 391, 445, 465, 473, 477, 526, 535, 552], "exit": [195, 263, 265, 481, 536], "exit_polici": 536, "exp": [195, 472, 536, 539, 542], "expand_and_reshap": 404, "expanddim": [45, 317], "expanddims_optim": [61, 333], "expanddimsoptim": [45, 317], "expect": [211, 476, 478, 487, 488, 489, 527, 534, 544, 547, 552], "expens": [536, 552], "experi": [480, 488, 549, 550, 552], "experiment": [523, 524, 526, 536, 542, 544, 548, 551], "explain": [156, 487, 495, 550], "explicit": 488, "explicitli": [156, 195, 475, 483, 530, 542], "explor": [472, 493, 539], "explos": [472, 539], "expon": [472, 539], "exporsingleimagedetectionboxestococo": 230, "export": [86, 195, 230, 436, 459, 469, 470, 473, 475, 477, 527], "export_compressed_model": [461, 547], "export_model_for_pt2e_qu": 435, "exportconfig": 195, "exportdetectionstococo": 230, "exported_model": [470, 475], "exportgroundtruthtococo": 230, "exportsingleimagedetectionboxestococo": 230, "exportsingleimagedetectionmaskstococo": 230, "exportsingleimagedetectionstococo": 230, "exportsingleimagegroundtruthtococo": 230, "expos": 451, "express": [227, 488], "extend": [477, 494, 495, 529], "extend_engin": [95, 360], "extens": [138, 140, 391, 396, 397, 465, 473, 474, 475, 477, 487, 492, 493, 500, 520, 527, 528, 529, 531, 532, 534, 536, 537, 538, 542, 543, 544, 547, 550, 552], "extra": [140, 232, 396, 476, 536, 547], "extra_opset": 87, "extract": [52, 53, 55, 133, 173, 211, 280, 324, 325, 327], "extract_data_typ": 280, "extran": 520, "extrem": 519, "f": [140, 170, 396, 476, 487, 520, 524, 544, 547, 550], "f1": [231, 233, 234, 524, 535, 536, 549, 553], "f1_score": [231, 232], "face": [141, 398, 447, 488, 492, 499, 543, 548, 553], "facebook": [474, 534, 550, 553], "facil": [140, 396], "facilit": 520, "fact": [487, 544], "factor": [3, 126, 286, 413, 425, 470, 474, 476, 480, 487, 547, 550, 553], "factori": [241, 391], "fail": [140, 396, 490, 521, 526], "failur": [489, 490], "fair": 488, "faith": 488, "fake": [29, 31, 98, 142, 149, 156, 280, 413, 429, 433, 476, 487, 536, 544, 547, 550], "fake_qu": [33, 73, 92, 116, 121, 306, 345, 357, 371, 376], "fake_quant": 99, "fakeaffinetensorquantfunct": [142, 429], "fakealgoconfig": 156, "fakequ": [73, 288, 345], "fakequant": 98, "fakequantizebas": 98, "falcon": [474, 492, 534, 542, 550, 553], "fall": [140, 145, 396, 472, 539], "fallback": [145, 195, 269, 271, 272, 473, 474, 475, 526, 537, 546, 552], "fallback_list": 28, "fallback_ord": 145, "fallbacktuningsampl": 277, "fals": [1, 2, 28, 29, 30, 31, 32, 33, 34, 56, 57, 74, 77, 84, 87, 88, 90, 98, 116, 121, 128, 131, 132, 133, 139, 140, 144, 145, 151, 163, 166, 195, 200, 202, 205, 206, 208, 209, 211, 221, 225, 230, 234, 245, 262, 281, 289, 292, 293, 294, 297, 298, 303, 306, 328, 329, 346, 348, 371, 376, 380, 383, 384, 385, 387, 396, 403, 404, 406, 409, 413, 417, 418, 420, 425, 427, 429, 433, 439, 442, 451, 454, 461, 464, 465, 474, 476, 478, 480, 481, 482, 493, 494, 521, 528, 535, 536, 544, 547, 550, 551, 552], "familiar": 469, "famou": [476, 487, 547], "faq": [488, 492], "far": 477, "fashionmnist": 211, "fast": [187, 195, 476, 480, 542, 543, 547], "fast_bias_correct": [148, 195, 544], "fastbiascorrect": [147, 150], "faster": [521, 522, 526, 543, 552, 553], "fatal": 462, "father": [141, 173, 398], "fault": 489, "fault_tolerant_fil": 465, "fbgemm": [473, 537, 544], "fc": [145, 195, 542], "fc1": [145, 433, 475], "fc2": [31, 145, 433], "feasibl": 195, "featur": [195, 209, 210, 221, 225, 413, 473, 478, 487, 489, 492, 518, 521, 522, 536, 537, 538, 542, 543, 548, 551], "feb": 543, "fed": [413, 552], "feed": [133, 208, 385, 542], "feed_dict": [133, 208, 385], "feedward": 184, "fefin": 199, "feng": 533, "ferplu": 553, "fetch": [46, 145, 148, 154, 203, 318, 387, 494], "fetch_modul": [145, 433, 447], "fetch_weight_from_reshap": [61, 333], "fetchweightfromreshapeoptim": [46, 318], "few": [542, 543, 550, 552], "ffffff": 552, "ffn": [143, 184, 417], "ffn2_sparsiti": [171, 542], "ffn_modul": 184, "ffn_name": 184, "field": [195, 211, 230, 472, 490, 493, 495, 524, 536, 539, 549, 552], "field_nam": [161, 465], "fig": 471, "figur": [476, 545], "file": [90, 133, 138, 140, 141, 145, 148, 160, 166, 188, 192, 195, 198, 199, 209, 210, 211, 214, 224, 225, 230, 235, 245, 249, 250, 253, 262, 385, 391, 396, 397, 398, 411, 413, 417, 464, 465, 471, 476, 482, 489, 493, 494, 495, 524, 527, 530, 533, 535, 536, 538, 540, 544, 547, 551], "file_lik": [140, 396], "file_typ": 465, "filenam": [211, 465], "filepath": [140, 396, 465, 520], "fill": [549, 551, 552], "filter": [1, 209, 210, 211, 212, 213, 214, 216, 220, 292, 298, 387, 406, 427, 465, 495, 531, 542], "filter_fn": 427, "filter_registri": 218, "filter_typ": 218, "final": [140, 173, 180, 192, 396, 475, 487, 494, 536, 540, 542, 544, 548, 552], "finalize_calibr": 442, "find": [30, 52, 53, 55, 90, 133, 194, 234, 266, 324, 325, 327, 385, 465, 481, 493, 534, 542, 547, 549, 550, 552], "find_by_nam": 30, "find_lay": [194, 420], "find_layers_nam": 420, "find_opset": 90, "fine": [186, 209, 477, 520, 542, 543, 544], "finer": [487, 550, 552], "finest": [487, 550], "finetun": [476, 487, 542, 547], "finish": 483, "first": [128, 140, 145, 150, 152, 174, 195, 209, 230, 267, 278, 380, 391, 396, 413, 433, 465, 472, 473, 476, 482, 487, 490, 492, 493, 494, 495, 532, 537, 539, 544, 546, 547, 549, 550, 552], "first_conv_or_matmul_quant": [195, 544], "first_n": [131, 383], "fit": [151, 175, 195, 235, 262, 266, 281, 448, 490, 518, 521, 524, 530, 535, 536, 537, 538, 542, 544, 545, 546, 547], "fit_with_raw_cmd": 151, "fix": [133, 185, 187, 209, 385, 476, 521, 542, 544, 547, 552], "fix_ref_type_of_graph_def": [133, 385], "flag": [195, 228], "flan": 542, "flatten_static_graph": 173, "flex": [492, 532], "flexibl": [473, 476, 480, 492, 542, 547], "flip": [221, 225, 551], "float": [3, 30, 31, 125, 126, 135, 152, 175, 180, 189, 192, 195, 209, 221, 228, 230, 231, 232, 277, 281, 283, 286, 303, 392, 413, 418, 433, 439, 442, 443, 451, 465, 470, 471, 472, 473, 474, 475, 476, 478, 479, 481, 487, 520, 535, 539, 544, 550, 551], "float16": [5, 8, 30, 401, 406, 461, 471, 476, 547], "float16activationoper": 5, "float16binaryoper": 8, "float32": [212, 213, 225, 230, 387, 429, 461, 471, 476, 487, 493, 518, 536, 544, 547, 550, 551], "float_dict": 135, "float_model": [135, 476, 483], "float_to_bfloat16": 30, "float_to_float16": 30, "floatfunct": 490, "floor": [472, 539], "flop": [476, 487, 547], "flow": [231, 232, 487, 490, 536], "flowchart": 552, "fn": 406, "fn_arg": 406, "focu": [519, 552], "focus": [472, 476, 480, 488, 493, 529, 539], "fold": [47, 48, 145, 303, 319, 320, 413, 432, 433, 439, 458, 474, 476, 528, 547, 550], "fold_batch_norm": [61, 333], "fold_const": [61, 333], "foldbatchnormnodesoptim": [47, 319], "folder": [133, 211, 216, 235, 262, 385, 464, 476, 477, 547], "follow": [73, 95, 153, 174, 211, 227, 230, 345, 360, 392, 420, 472, 473, 474, 479, 482, 483, 487, 488, 489, 490, 492, 493, 494, 495, 520, 521, 523, 524, 527, 528, 532, 533, 535, 536, 537, 538, 539, 541, 542, 544, 547, 550, 552], "footprint": [195, 245, 523, 536, 540, 542, 545], "forc": [443, 546], "forg": 527, "fork": 489, "form": 232, "format": [5, 30, 39, 133, 145, 154, 195, 209, 210, 211, 230, 278, 281, 288, 289, 311, 385, 389, 390, 404, 431, 441, 444, 458, 461, 472, 473, 475, 477, 480, 482, 487, 492, 494, 495, 520, 524, 526, 535, 536, 537, 538, 539, 543, 544, 547], "format_list2str": 154, "format_vers": [138, 397], "formul": 536, "formula": [487, 542, 550], "forpytorch": 532, "fortensorflow": 532, "fortieth": 542, "forward": [1, 145, 192, 413, 433, 476, 487, 494, 536, 542, 544, 547, 550], "forward_wrapp": [145, 413, 433], "foster": 488, "found": [162, 406, 413, 473, 492, 520, 534, 537, 550, 552, 553], "foundat": 543, "four": [470, 475, 481, 553], "fp1": [487, 550], "fp16": [31, 195, 278, 399, 401, 406, 418, 439, 487, 544], "fp2": [487, 550], "fp32": [28, 29, 31, 64, 116, 121, 128, 145, 150, 195, 198, 199, 234, 267, 271, 278, 301, 305, 336, 371, 376, 380, 391, 406, 411, 412, 415, 431, 433, 437, 454, 457, 458, 461, 464, 465, 471, 473, 474, 475, 476, 477, 478, 480, 487, 489, 493, 495, 528, 534, 535, 536, 537, 544, 546, 547, 548, 549, 550, 552, 553], "fp32_baselin": [153, 454, 493], "fp32_graph": [128, 380], "fp32_layer": [292, 293, 294, 297, 298], "fp32_model": [135, 145, 431, 441, 458, 465, 474, 475, 479, 480, 545, 547], "fp32_model_path": 545, "fp32_onnx_config": 526, "fp32_onnx_path": 458, "fp32_op": [33, 35, 92, 306, 307, 357], "fp32_tensor": 465, "fp4": [433, 472, 476, 539, 547], "fp6": [472, 539], "fp8": [437, 439, 441, 472, 477, 539, 543], "fp8_config": [439, 471, 492], "fp8_entri": 437, "fp8_white_list": [439, 471], "fp8config": [437, 439, 471, 492], "fpath": 211, "frac": [472, 487, 539, 550], "fraction": [221, 551], "fragment": 493, "framework": [1, 151, 152, 157, 163, 165, 170, 176, 180, 183, 187, 188, 196, 197, 201, 202, 205, 208, 209, 210, 211, 212, 213, 214, 215, 216, 218, 220, 222, 225, 234, 235, 236, 237, 239, 272, 278, 288, 299, 389, 454, 469, 473, 475, 480, 481, 487, 493, 495, 519, 520, 524, 525, 529, 530, 531, 535, 536, 537, 542, 543, 544, 551, 552, 553], "framework_dataset": 211, "framework_nam": [152, 520], "framework_specific_info": [32, 288, 289, 493], "frantar": [476, 487, 542, 547], "free": [29, 149, 187, 198, 199, 262, 413, 474, 479, 487, 488, 540, 549, 550], "freez": [73, 74, 75, 133, 345, 346, 385, 470, 475, 542], "freeze_fake_qu": [80, 351], "freeze_valu": [80, 351], "freeze_value_without_calib": 80, "freezefakequantopoptim": [73, 345], "freezevaluetransform": [74, 346], "freezevaluewithoutcalibtransform": 75, "frequenc": [162, 180, 195, 536, 542], "frequent": 532, "fresh": [492, 532], "friendli": [472, 487, 528, 536, 539, 543, 550], "from": [1, 30, 46, 52, 53, 55, 90, 133, 140, 141, 145, 151, 152, 153, 160, 162, 163, 169, 170, 176, 177, 178, 179, 183, 185, 186, 187, 188, 189, 190, 191, 192, 195, 198, 199, 200, 203, 206, 209, 210, 211, 212, 213, 214, 216, 221, 227, 230, 231, 232, 235, 243, 245, 262, 278, 280, 281, 288, 318, 324, 325, 327, 385, 387, 390, 392, 396, 398, 406, 408, 411, 412, 413, 415, 417, 431, 433, 437, 441, 447, 448, 451, 454, 456, 457, 458, 461, 464, 465, 469, 470, 471, 472, 473, 474, 475, 476, 478, 479, 480, 481, 482, 483, 487, 488, 489, 490, 493, 495, 518, 520, 521, 523, 524, 525, 526, 527, 529, 531, 534, 535, 537, 538, 539, 540, 541, 542, 543, 544, 545, 546, 547, 548, 549, 550, 551, 552], "from_dict": 478, "from_pretrain": [461, 529, 536], "frozen": [235, 243, 262, 390, 538], "frozen_func": [133, 385], "frozen_pb_sess": [243, 390], "fuel": [472, 539], "full": [30, 209, 210, 211, 461, 465, 471, 476, 492, 519, 527, 533, 542, 547, 548], "full_rang": 433, "fulli": [478, 536, 544, 550], "fulltoken": 224, "fun": 281, "func": [133, 145, 161, 385, 465, 544], "func_dict": 454, "function": [124, 125, 138, 159, 181, 182, 187, 195, 198, 199, 210, 283, 296, 379, 393, 397, 421, 459, 469, 473, 475, 476, 477, 480, 487, 489, 490, 493, 494, 495, 518, 521, 523, 526, 530, 531, 534, 535, 536, 537, 542, 544, 547, 549, 550, 552], "function1": 281, "function2": 281, "function3": 281, "fundament": [478, 479, 519, 536], "funnel": 553, "funsd": 553, "further": [55, 195, 327, 473, 487, 488, 492, 537, 538, 544], "fuse": [1, 43, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 76, 77, 78, 79, 81, 116, 121, 144, 145, 149, 315, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 347, 348, 349, 350, 352, 371, 376, 417, 490, 550], "fuse_biasadd_add": [61, 333], "fuse_column_wise_mul": [61, 333], "fuse_conv_redundant_dequant": [80, 351], "fuse_conv_requant": [80, 351], "fuse_conv_with_math": [61, 333], "fuse_decomposed_bn": [61, 333], "fuse_decomposed_in": [61, 333], "fuse_gelu": [61, 333], "fuse_layer_norm": [61, 333], "fuse_matmul_redundant_dequant": [80, 351], "fuse_matmul_requant": [80, 351], "fuse_pad_with_conv": [61, 333], "fuse_pad_with_fp32_conv": [61, 333], "fuse_qdq_bn": [115, 370], "fuse_qdq_concatv2": [115, 370], "fuse_qdq_conv": [115, 370], "fuse_qdq_deconv": [115, 370], "fuse_qdq_in": [115, 370], "fuse_qdq_matmul": [115, 370], "fuse_qdq_pool": [115, 370], "fuse_reshape_transpos": [61, 333], "fusebiasaddandaddoptim": [49, 321], "fusecolumnwisemuloptim": [50, 322], "fuseconvredundantdequantizetransform": [76, 347], "fuseconvrequantizetransform": [77, 348], "fuseconvwithmathoptim": [51, 323], "fusedbatchnorm": [66, 338], "fusedbatchnormv2": [66, 338], "fusedbatchnormv3": [108, 118, 363, 373], "fusedbatcnormv3": [55, 327], "fusedecomposedbnoptim": [52, 324], "fusedecomposedinoptim": [53, 325], "fusedinstancenorm": [112, 367], "fusedmatmul": 18, "fusedmatmuloper": 18, "fusegeluoptim": [54, 326], "fuselayernormoptim": [55, 327], "fusematmulredundantdequantizetransform": [78, 349], "fusematmulrequantizedequantizenewapitransform": [79, 350], "fusematmulrequantizedequantizetransform": [79, 350], "fusematmulrequantizenewapitransform": [79, 350], "fusematmulrequantizetransform": [79, 350], "fusenodestartwithconcatv2": [109, 119, 364, 374], "fusenodestartwithconv2d": [110, 120, 365, 375], "fusenodestartwithdeconv2d": [111, 366], "fusenodestartwithfusedbatchnormv3": [108, 118, 363, 373], "fusenodestartwithfusedinstancenorm": [112, 367], "fusenodestartwithmatmul": [113, 122, 368, 377], "fusenodestartwithpool": [114, 123, 369, 378], "fusepadwithconv2doptim": [56, 328], "fusepadwithfp32conv2doptim": [57, 329], "fusetransposereshapeoptim": [58, 330], "fusion": [44, 46, 55, 63, 94, 111, 112, 113, 116, 117, 118, 122, 316, 318, 327, 335, 359, 366, 367, 368, 371, 372, 373, 377, 479, 490, 493, 528], "futur": [149, 153, 198, 199, 469, 477, 531, 534, 536], "fw": 494, "fwk": 239, "fwk_name": [152, 520], "fx": [145, 272, 406, 435, 441, 470, 473, 475, 531, 537, 543, 544, 546], "fx_model": 145, "fx_white_list": 145, "g": [90, 140, 154, 175, 195, 396, 476, 483, 487, 489, 525, 542, 547, 548, 550, 552], "g_idx": 429, "gain": [541, 543], "gan": 543, "gap": [476, 538], "gather": [1, 16, 195], "gatheroper": 13, "gaudi": [477, 492, 532, 543], "gaudi2": [471, 492, 532], "gaussian": [266, 552], "gavgpool": 16, "gb": 483, "gcc": 553, "gcp": 543, "gelu": [54, 326], "gemm": [16, 195], "gemm_to_matmul": [195, 544], "gemmoper": 15, "gen": [473, 487, 534, 537, 543, 544, 546], "gen_bar_updat": 211, "gender": 488, "gener": [1, 33, 34, 72, 107, 133, 145, 151, 153, 154, 173, 198, 199, 200, 208, 211, 212, 213, 214, 225, 227, 235, 258, 262, 266, 281, 299, 303, 306, 344, 385, 387, 413, 417, 418, 420, 438, 439, 442, 448, 471, 472, 473, 474, 476, 477, 478, 483, 487, 489, 490, 493, 495, 521, 535, 536, 537, 539, 540, 542, 543, 544, 546, 547, 550, 551, 552], "generaltopk": 234, "generate_activation_observ": [145, 417], "generate_feed_dict": [133, 385], "generate_ffn2_pruning_config": 171, "generate_mha_pruning_config": 171, "generate_prefix": [151, 154], "generate_xpu_qconfig": 417, "generategraphwithqdqpattern": [92, 357], "generator1": 281, "geomean": 531, "gestalt": 543, "get": [1, 29, 30, 31, 52, 53, 55, 89, 90, 133, 141, 145, 151, 154, 161, 165, 166, 169, 170, 171, 173, 176, 183, 189, 190, 191, 192, 195, 203, 225, 234, 243, 262, 271, 278, 280, 299, 302, 324, 325, 327, 385, 387, 390, 391, 398, 413, 417, 420, 433, 439, 447, 454, 458, 461, 465, 469, 474, 477, 482, 487, 494, 519, 527, 531, 532, 534, 536, 543, 547, 550, 552, 554], "get_absorb_lay": [145, 433], "get_acceler": 445, "get_activ": 166, "get_adaptor_nam": 280, "get_algorithm": 454, "get_all_config": 160, "get_all_config_set": [302, 438], "get_all_config_set_from_config_registri": [152, 520], "get_all_fp32_data": [391, 465], "get_all_registered_config": [299, 439], "get_architectur": 151, "get_attribut": 173, "get_blob_s": 31, "get_block_prefix": [145, 433], "get_bounded_thread": 151, "get_children": [141, 398], "get_common_modul": 173, "get_const_dim_count": [52, 53, 324, 325], "get_core_id": 151, "get_criterion": 169, "get_dataload": 418, "get_default_autoround_config": 439, "get_default_awq_config": 439, "get_default_double_quant_config": 439, "get_default_dynamic_config": 439, "get_default_fp8_config": 439, "get_default_fp8_config_set": 439, "get_default_gptq_config": 439, "get_default_hqq_config": 439, "get_default_mixed_precision_config": 439, "get_default_mixed_precision_config_set": 439, "get_default_mx_config": 439, "get_default_rtn_config": [439, 483], "get_default_sq_config": [303, 439], "get_default_static_config": 439, "get_default_static_quant_config": [299, 303], "get_default_teq_config": 439, "get_depth": [145, 417], "get_dict_at_depth": [145, 417], "get_double_quant_config_dict": 447, "get_element_under_depth": [145, 417], "get_embedding_contigu": 145, "get_estimator_graph": 133, "get_example_input": 145, "get_fallback_ord": 145, "get_filter_fn": 406, "get_final_text": 225, "get_framework_nam": 1, "get_func_from_config": 454, "get_graph_def": [133, 385], "get_half_precision_node_set": 406, "get_hidden_st": 145, "get_index_from_strided_slice_of_shap": 90, "get_input_output_node_nam": [133, 385], "get_ipex_vers": 445, "get_lay": 192, "get_linux_numa_info": 154, "get_max_supported_opset_vers": 89, "get_metr": 454, "get_model_devic": 447, "get_model_fwk_nam": 239, "get_model_info": 447, "get_model_input_shap": [133, 385], "get_model_typ": [243, 390], "get_modul": [141, 398, 413, 433], "get_module_input_output": [145, 433], "get_mse_order_per_fp32": 145, "get_mse_order_per_int8": 145, "get_named_children": [141, 398], "get_node_map": 458, "get_node_original_nam": 30, "get_numa_nod": 154, "get_number_of_socket": 465, "get_op_list": 465, "get_op_type_by_nam": 145, "get_par": [413, 433], "get_pattern": 176, "get_physical_id": 151, "get_postprocess": 454, "get_preprocess": 454, "get_processor_type_from_user_config": 447, "get_prun": 183, "get_quant": 447, "get_quant_dequant_output": 29, "get_quantizable_onnx_op": 458, "get_quantizable_ops_from_cfg": [145, 417], "get_quantizable_ops_recurs": [413, 417], "get_reg": 189, "get_reg_typ": 189, "get_reversed_numa_info": 154, "get_rtn_double_quant_config_set": 438, "get_schedul": 190, "get_schema": 89, "get_siz": 465, "get_sparsity_ratio": 192, "get_sparsity_ratio_tf": 192, "get_subgraphs_from_onnx": 90, "get_super_module_by_nam": [141, 398], "get_tensor_by_nam": [133, 385], "get_tensor_histogram": [391, 465], "get_tensor_val_from_graph_nod": 133, "get_tensorflow_node_attr": 90, "get_tensorflow_node_shape_attr": 90, "get_tensorflow_tensor_data": 90, "get_tensorflow_tensor_shap": 90, "get_tensors_info": 465, "get_tf_criterion": 191, "get_tf_model_typ": 390, "get_thread": 151, "get_threads_per_cor": 151, "get_torch_vers": [145, 445], "get_torchvision_map": 225, "get_tuning_histori": 465, "get_unquantized_node_set": 406, "get_weight_from_input_tensor": 133, "get_weight_scal": 31, "get_weights_detail": 465, "get_windows_numa_info": 154, "get_woq_tuning_config": [439, 481], "get_workspac": 161, "getdefaultencod": 451, "getenv": 520, "gholami": 542, "gigant": [474, 479, 550], "git": [489, 527, 532], "github": [3, 135, 177, 178, 188, 209, 227, 228, 231, 232, 234, 262, 439, 476, 489, 492, 525, 532, 533, 536, 548], "give": [156, 494, 552], "given": [1, 3, 30, 52, 53, 55, 89, 90, 101, 133, 141, 145, 152, 194, 225, 230, 262, 324, 325, 327, 392, 398, 406, 409, 413, 427, 433, 442, 447, 451, 477, 481, 495, 542, 550, 551], "global": [100, 175, 195, 280, 389, 465, 476, 477, 478, 490, 536, 542, 552], "global_config": 192, "global_st": 465, "global_step": 180, "globalaveragepool": 14, "globalaveragepooloper": 14, "glorot_uniform": [292, 293, 294, 298], "glue": [227, 234, 535, 536], "gluon": [1, 235, 262, 538], "glx": 527, "gm": 406, "go": [528, 547, 551], "goal": [151, 235, 262, 481, 487, 494, 521, 541, 544, 552], "goe": 471, "good": [478, 488, 544, 552], "googl": [473, 492, 520, 537, 543], "googlenet": 553, "got": [133, 385, 494, 527], "gp": 266, "gpt": [474, 492, 529, 534, 542, 550, 553], "gptq": [31, 392, 428, 431, 437, 439, 441, 477, 483, 487, 492, 520, 534, 545, 547], "gptq_arg": [476, 547], "gptq_config": 547, "gptq_config_path": 547, "gptq_entri": 437, "gptq_g128asym": 547, "gptq_g32asym": 547, "gptq_g32asym_disable_last_matmul": 547, "gptq_quantiz": 31, "gptq_related_block": 420, "gptqconfig": [437, 439, 451, 476, 481], "gptquantiz": 420, "gptqw4g128asym": 553, "gptqw4g128sym": 553, "gptqw4g32asym": 553, "gptqw4g32sym": 553, "gpu": [74, 75, 82, 140, 195, 346, 353, 396, 413, 443, 476, 480, 518, 531, 536, 537, 544, 545], "gracefulli": 488, "grad": [182, 187], "gradient": [169, 439, 476, 487, 492, 531, 536, 542, 543, 553], "gradient_accumulate_step": [418, 439, 476], "gradient_accumulation_step": 536, "gradientcriterion": 169, "gradual": [190, 542], "grain": [186, 477, 542, 543, 552], "gram": 228, "granular": [292, 293, 294, 297, 298, 409, 472, 487, 493, 494, 495, 528, 531, 539, 544, 550], "graph": [33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 90, 91, 92, 93, 94, 95, 97, 98, 99, 102, 115, 117, 121, 124, 127, 128, 130, 131, 132, 133, 173, 208, 236, 243, 261, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 360, 362, 370, 372, 376, 379, 380, 382, 383, 384, 385, 390, 406, 441, 470, 475, 487, 490, 493, 524, 530, 538, 544, 545, 546], "graph_bas": [72, 344], "graph_convert": [96, 361], "graph_converter_without_calib": 96, "graph_cse_optim": [61, 333], "graph_def": [39, 125, 126, 133, 235, 243, 261, 262, 283, 286, 311, 385, 390, 457], "graph_def_sess": [243, 390], "graph_modul": 435, "graph_nam": 87, "graph_node_name_map": 133, "graph_optimization_level": [195, 544], "graph_output": 90, "graph_rewrit": [96, 361], "graph_sess": [243, 390], "graph_transform_bas": [130, 382], "graph_util": [96, 361], "graphanalyz": [95, 360], "graphconvert": [33, 306], "graphconverterwithoutcalib": 34, "graphcseoptim": [59, 331], "graphdef": [59, 133, 243, 261, 331, 385, 390, 538], "graphfoldconstantoptim": [48, 320], "graphmodel": 406, "graphmodul": [145, 406, 435, 490, 546], "graphrewriterbas": [71, 343], "graphrewriterhelp": [95, 360], "graphtrac": [413, 433], "graphtransform": [129, 381], "graphtransformbas": [129, 381], "grappler": [60, 332, 528], "grappler_optim": 528, "grappler_pass": [61, 333], "grappleroptim": [60, 332], "greater": [133, 391, 465, 480, 542, 552], "greatest": 552, "greatli": [476, 545, 547], "grei": [476, 545], "grid": [195, 542], "ground": [231, 232], "ground_truth": [231, 232], "groundtruth": [195, 230], "groundtruth_box": 230, "groundtruth_boxes_list": 230, "groundtruth_class": 230, "groundtruth_classes_list": 230, "groundtruth_dict": 230, "groundtruth_is_crowd": 230, "groundtruth_mask": 230, "group": [31, 189, 292, 426, 433, 476, 487, 492, 531, 542, 547, 551, 552, 553], "group_dim": [439, 476, 547], "group_norm": 526, "group_siz": [31, 142, 145, 280, 426, 429, 433, 439, 451, 476, 481, 547], "grouplasso": 189, "groupnorm": 550, "grow": [476, 487, 547], "grown": 542, "growth": [472, 473, 536, 537, 539, 542], "gt": [474, 476, 550, 551], "guangxuan": [476, 487, 547, 550], "guarante": [195, 536], "guess_output_rank": 30, "gui": [531, 542], "guid": [209, 473, 480, 490, 492, 520, 532], "guidelin": [491, 492], "gz": 211, "h": [31, 195, 225, 524, 551], "h384": 553, "h5": 538, "ha": [52, 53, 55, 59, 140, 179, 180, 227, 281, 324, 325, 327, 331, 391, 396, 404, 420, 443, 473, 478, 480, 487, 489, 493, 494, 495, 521, 526, 531, 536, 537, 542, 544, 546, 549, 550, 552], "habana": [471, 492, 532], "habana_visible_devic": 492, "habanalab": 492, "hack": 227, "haihao": [533, 542], "half": [399, 401, 406, 439, 473, 476, 537], "half_away_from_zero": [292, 293, 294, 297, 298], "half_precision_convert": 400, "half_precision_rewrit": 407, "halfprecisionconvert": 399, "halfprecisionmodulewrapp": 401, "hand": [477, 480], "handl": [46, 133, 149, 159, 318, 385, 393, 413, 423, 462, 490, 491, 520, 521, 550], "handler": [398, 451, 465, 552], "hanj": 3, "hanwen": 533, "harass": 488, "hard": [195, 521], "hardswish": 526, "hardtanh": 550, "hardwar": [161, 447, 472, 475, 483, 492, 493, 531, 536, 539, 542, 543], "harm": 488, "harmon": [232, 234], "has_zp": 31, "hassoun": 542, "hat": 553, "have": [3, 59, 68, 126, 133, 140, 170, 174, 176, 183, 207, 227, 230, 234, 262, 280, 281, 286, 331, 340, 385, 396, 412, 413, 417, 472, 473, 474, 476, 481, 487, 488, 489, 494, 495, 520, 521, 524, 528, 533, 535, 536, 537, 539, 540, 542, 544, 545, 547, 550, 552], "haven": 542, "hawq": [135, 269, 552], "hawq_metr": 136, "hawq_top": 135, "hawq_v2": [195, 270], "hawq_v2_loss": 552, "hawq_v2tunestrategi": 269, "hbm": 532, "he": 493, "head": [171, 173, 177, 184, 192, 476, 542], "head_mask": 184, "header": [161, 465, 527], "heavi": [476, 523], "height": [179, 221, 225, 524, 551], "hellaswag": 553, "helloworld": [537, 551], "help": [145, 166, 433, 469, 481, 487, 520, 534, 538, 547, 552], "helper": [30, 95, 101, 133, 145, 209, 210, 211, 224, 243, 360, 385, 390, 417, 456, 457, 458, 463], "here": [230, 281, 471, 474, 475, 476, 479, 480, 483, 487, 494, 524, 525, 526, 528, 534, 535, 544, 548, 549, 550, 553], "herebi": 550, "herlper": [124, 379], "hesit": 542, "hessian": [31, 135, 269, 476, 547, 552], "hessian_trac": 135, "hessiantrac": 135, "heterogen": 543, "hf": [141, 398, 431, 441, 447, 483, 534, 550, 553], "hicham": 476, "hidden": [174, 179, 493], "high": [30, 212, 213, 387, 471, 480, 532, 543, 552], "higher": [152, 195, 198, 199, 235, 262, 443, 448, 471, 476, 483, 487, 490, 526, 535, 542, 544, 547, 549], "higher_is_bett": [195, 234, 262, 552], "highest": 552, "highli": [476, 543, 547], "highlight": 490, "hint": [465, 527], "histogram": [3, 391, 452, 465], "histogramcollector": 3, "histori": [195, 464, 465, 552], "history_cfg": 464, "hoc": 227, "hold": [230, 266], "holder": 216, "hook": [135, 162, 166, 184, 398, 454, 523, 536, 542, 550], "hope": 526, "horizont": [225, 551], "horovod": 524, "host": [492, 524], "hostconst": [82, 353], "hour": 552, "how": [31, 140, 162, 169, 175, 181, 182, 187, 195, 225, 396, 433, 447, 469, 473, 475, 476, 477, 478, 479, 480, 487, 489, 490, 491, 493, 521, 523, 524, 530, 535, 536, 542, 543, 544, 550, 551, 552], "howev": [140, 396, 476, 483, 487, 542, 547, 550], "howpublish": 533, "hp_dtype": [439, 471], "hpex": 445, "hpo": [198, 542], "hpoconfig": 195, "hpu": [429, 441, 443, 471, 477], "hpu_acceler": 443, "hpuweightonlylinear": 429, "hqq": [428, 439, 477, 492], "hqq_arg": 476, "hqq_blog": [439, 476], "hqq_entri": 437, "hqqconfig": [437, 439, 476], "hqqlinear": [423, 427], "hqqmodul": 422, "hqqmoduleconfig": 422, "hqqtensorhandl": 423, "hqquantiz": 427, "hqt": 471, "hqt_output": [439, 471], "hroughput": 482, "ht": 553, "html": [490, 492, 494, 519, 524, 531, 532, 544], "htmllabel": 552, "http": [3, 135, 169, 177, 178, 187, 188, 209, 211, 227, 228, 230, 231, 232, 234, 262, 420, 439, 476, 490, 492, 532, 533, 536, 542, 548], "hub": [141, 398, 431, 441, 447, 492, 525], "hue": 551, "hug": [141, 398, 447, 492, 543], "huge": [523, 542, 545], "hugginfac": [431, 441], "huggingfac": [173, 184, 209, 431, 441, 461, 472, 492, 525, 539, 550, 553], "huggingface_model": 188, "human": [154, 552], "hvd": [234, 524], "hw": 471, "hybirdblock": [235, 262], "hybrid": 483, "hybridblock": 538, "hyper": [167, 476], "hyperparamet": [195, 487, 549, 550, 552], "i": [1, 30, 31, 33, 34, 36, 39, 40, 45, 49, 55, 67, 70, 90, 117, 128, 133, 135, 138, 140, 144, 145, 150, 151, 153, 156, 161, 162, 165, 166, 169, 173, 174, 180, 185, 186, 187, 188, 189, 191, 192, 195, 198, 199, 200, 207, 208, 209, 210, 211, 212, 213, 216, 218, 221, 225, 227, 230, 232, 234, 235, 245, 249, 250, 253, 262, 267, 272, 280, 281, 306, 308, 311, 312, 317, 321, 327, 339, 342, 372, 380, 385, 387, 391, 396, 397, 406, 408, 409, 413, 417, 420, 426, 427, 431, 433, 435, 439, 441, 443, 445, 447, 448, 451, 461, 464, 465, 470, 471, 472, 473, 474, 475, 476, 477, 479, 480, 481, 482, 483, 487, 488, 489, 490, 492, 493, 494, 495, 496, 498, 504, 507, 510, 518, 519, 520, 521, 523, 524, 526, 527, 528, 531, 532, 533, 535, 536, 537, 538, 539, 540, 541, 542, 543, 544, 545, 546, 547, 548, 549, 550, 551, 552, 553], "ic": [532, 543], "id": [151, 224, 227, 229, 230, 231, 232, 535, 549, 552], "idea": [487, 492, 542, 550, 552], "ideal": 473, "ident": [59, 65, 174, 331, 337, 488], "identifi": [52, 53, 55, 140, 230, 243, 324, 325, 327, 390, 396, 481, 542, 547], "idx1": 211, "idx3": 211, "ieee": [135, 473, 487, 537, 550], "ignor": [465, 476, 487, 519, 547, 550, 552], "ignore_attr": 465, "ignore_kei": 465, "ii": 552, "illinoi": 3, "illustr": [476, 494, 495, 523, 552], "imag": [210, 211, 214, 216, 221, 225, 230, 473, 487, 524, 526, 542, 550, 551, 553], "image_format": 216, "image_height": 230, "image_id": [230, 535], "image_list": 214, "image_tensor": 536, "image_width": 230, "imageclassifi": 211, "imagefold": [211, 524, 536], "imagenet": [211, 214, 221, 478, 536, 542, 551, 553], "imagenet_dataset": 215, "imagenet_transform": 222, "imagenetraw": 214, "imagerecord": 524, "imageri": 488, "img": 492, "img1": 214, "img2": 214, "img_dir": 210, "imgx": 214, "iml": 543, "immedi": 542, "impact": [269, 542, 548, 552], "imper": 490, "implement": [95, 128, 132, 140, 198, 199, 204, 207, 208, 209, 211, 227, 235, 245, 262, 269, 360, 380, 384, 392, 396, 448, 476, 495, 521, 535, 536, 542, 544, 547, 548, 552], "implicitli": [140, 156, 396], "import": [133, 151, 153, 161, 195, 235, 245, 262, 281, 385, 431, 441, 445, 448, 465, 469, 470, 471, 472, 473, 474, 475, 476, 477, 478, 479, 480, 481, 483, 487, 490, 492, 495, 518, 521, 523, 524, 526, 529, 535, 536, 537, 538, 539, 540, 541, 542, 544, 545, 546, 548, 549, 550, 551, 552], "importerror": [138, 397, 527], "impract": 476, "improv": [186, 473, 475, 476, 487, 489, 492, 519, 520, 536, 542, 543, 544, 546, 547, 552, 553], "in_featur": [403, 423, 429], "in_graph": [133, 385], "in_graph_is_binari": [133, 385], "in_mp": 30, "inappropri": 488, "inc": [225, 301, 305, 429, 431, 441, 480, 481, 488, 494, 534, 543, 548, 552], "inc_model": [526, 538], "inc_target_devic": [443, 477], "incbench": 482, "incept": 553, "incid": 488, "incit": [474, 550], "includ": [138, 163, 169, 173, 175, 189, 191, 195, 209, 211, 218, 225, 281, 392, 397, 418, 431, 437, 441, 447, 465, 471, 476, 477, 480, 481, 483, 488, 493, 494, 495, 521, 532, 533, 534, 535, 536, 542, 544, 546, 547, 552], "include_lay": 452, "include_nod": 1, "include_tensors_kl": 1, "include_tensors_minmax": 1, "inclus": 488, "incompat": 527, "incorpor": [476, 494, 495, 523, 542, 552], "incorrect": [140, 396], "incquantizationconfigmixin": 451, "increas": [195, 472, 476, 522, 531, 539, 547, 552], "increasingli": 542, "increment": 552, "incub": 3, "incur": [472, 539], "incweightonlylinear": 429, "independ": [184, 257, 261, 495], "index": [52, 53, 55, 90, 151, 192, 195, 203, 207, 211, 324, 325, 327, 387, 465, 487, 492, 532, 535, 547, 550], "indexdataset": 207, "indexerror": [138, 397], "indexfetch": [203, 387], "indic": [140, 152, 162, 195, 203, 207, 209, 230, 387, 396, 409, 426, 443, 480, 490, 521, 527], "individu": [126, 175, 257, 261, 286, 487, 488, 542, 550], "industri": [535, 543], "infer": [1, 30, 90, 125, 145, 173, 243, 245, 262, 283, 301, 305, 390, 417, 433, 448, 473, 474, 475, 476, 479, 480, 487, 493, 494, 519, 523, 529, 536, 537, 540, 542, 543, 544, 547, 550, 552], "infer_onnx_shape_dtyp": 90, "infer_shap": 30, "inferenc": [472, 539], "influenc": [145, 542], "info": [30, 145, 154, 161, 177, 178, 192, 223, 239, 391, 412, 413, 417, 442, 447, 461, 462, 465, 490, 520, 538], "inform": [1, 135, 154, 169, 170, 173, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 195, 198, 199, 234, 389, 426, 465, 471, 472, 474, 476, 480, 482, 483, 488, 489, 491, 492, 493, 494, 495, 496, 498, 504, 507, 510, 519, 520, 528, 536, 538, 539, 542, 546, 547, 548, 550, 553, 554], "infrastructur": 522, "ingest": 230, "inherit": [162, 163, 185, 186, 190, 206, 225, 392, 493, 494], "init": [0, 4, 29, 148, 164, 170, 172, 193, 535, 552], "init_alpha": [413, 439], "init_quantize_config": 101, "init_tun": 153, "initi": [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 19, 21, 22, 23, 25, 26, 29, 30, 31, 90, 101, 133, 140, 153, 163, 180, 198, 199, 206, 209, 262, 278, 282, 285, 287, 291, 292, 293, 294, 295, 296, 297, 298, 300, 385, 396, 400, 409, 447, 448, 477, 480, 487, 495, 535, 542, 544, 550, 552], "initial_op_tuning_cfg": 277, "initial_tuning_cfg_with_quant_mod": 278, "initialize_int8_avgpool": 297, "initialize_int8_conv2d": 292, "initialize_int8_dens": 293, "initialize_int8_depthwise_conv2d": 294, "initialize_int8_maxpool": 297, "initialize_int8_separable_conv2d": 298, "initialize_name_count": 90, "inject": [44, 316, 536], "injectdummybiasaddoptim": [44, 316], "inlin": [133, 385], "innov": 543, "inplac": [29, 412, 413, 442, 477], "input": [1, 2, 29, 30, 31, 39, 45, 49, 52, 53, 55, 56, 57, 59, 67, 68, 70, 71, 90, 94, 95, 101, 107, 126, 133, 134, 142, 144, 145, 149, 154, 173, 174, 192, 195, 198, 199, 209, 210, 211, 213, 221, 224, 225, 234, 235, 239, 243, 262, 286, 311, 317, 321, 324, 325, 327, 328, 329, 331, 339, 340, 342, 343, 359, 360, 385, 387, 390, 391, 408, 411, 413, 417, 425, 429, 433, 435, 442, 447, 448, 456, 457, 458, 461, 464, 465, 470, 475, 476, 477, 487, 493, 494, 518, 519, 521, 523, 524, 526, 528, 530, 535, 536, 537, 538, 542, 544, 547, 550, 551], "input2tupl": 145, "input_data": [29, 521], "input_desc": 1, "input_dtyp": 90, "input_fil": 225, "input_fn": [133, 243, 390], "input_func": [145, 433], "input_graph": [116, 121, 128, 258, 261, 371, 376, 380, 493], "input_graph_def": [52, 53, 55, 324, 325, 327], "input_id": [209, 225, 536], "input_mask": [225, 536], "input_max": 413, "input_max_ab": 413, "input_min": 413, "input_minmax": 413, "input_model": 538, "input_model_tensor": 465, "input_nam": [52, 53, 87, 127, 195, 243, 324, 325, 390, 457, 458, 526], "input_name_to_nod": 456, "input_node_map": [52, 53, 324, 325], "input_node_nam": [69, 116, 121, 133, 341, 371, 376, 385], "input_output_nam": [60, 332], "input_pb": [129, 131, 132, 381, 383, 384], "input_scal": [142, 398, 413, 429], "input_shap": [90, 213, 387], "input_tensor": [133, 243, 385, 390], "input_tensor_data": 466, "input_tensor_ids_op_nam": [145, 417], "input_tensor_nam": [133, 243, 385, 390], "input_valu": [145, 433], "inputbatch": 225, "inputcapturemodul": 413, "inputfeatur": [209, 225], "inputs_as_nchw": [127, 457], "insecur": [140, 396], "insensit": 443, "insert": [62, 90, 92, 94, 98, 131, 149, 288, 334, 357, 359, 383, 413, 433, 442, 475, 476, 477, 479, 487, 490, 494, 521, 531, 536, 542, 544, 546, 547, 550], "insert_log": [130, 382], "insert_newlin": 465, "insert_print_nod": [61, 333], "insert_qdq_pattern": [91, 356], "insertlog": [131, 383], "insertprintminmaxnod": [62, 334], "inset": 536, "insid": [230, 476, 523, 527, 542, 545, 552], "insight": [543, 548, 552], "inspect": 548, "inspect_tensor": 493, "inspect_typ": 493, "inspir": [476, 547], "instal": [391, 480, 524, 527, 529, 554], "instanc": [100, 101, 151, 154, 195, 198, 199, 231, 232, 234, 235, 262, 266, 280, 409, 448, 465, 476, 482, 488, 489, 490, 493, 518, 529, 536, 547, 552, 553], "instance_index": 154, "instance_norm": 526, "instancenorm": [53, 325, 550], "instances_val2017": 210, "instanti": 541, "instead": [195, 208, 465, 475, 542, 547], "institut": 211, "instruct": [473, 474, 487, 494, 495, 532, 537, 542, 543, 544, 550, 553], "insuffici": 482, "insult": 488, "int": [1, 3, 29, 30, 31, 90, 125, 133, 143, 145, 152, 156, 161, 171, 195, 208, 209, 210, 221, 225, 228, 230, 234, 251, 257, 261, 280, 281, 283, 284, 288, 301, 302, 305, 385, 404, 413, 417, 418, 423, 425, 426, 429, 433, 439, 451, 457, 458, 461, 465, 476, 480, 520, 521, 535, 536, 547, 551], "int32": [429, 461, 476, 547], "int4": [487, 534, 544, 553], "int8": [5, 6, 30, 31, 72, 108, 109, 110, 116, 118, 119, 120, 121, 128, 133, 150, 151, 195, 221, 278, 280, 292, 293, 294, 297, 298, 299, 303, 344, 363, 364, 365, 371, 373, 374, 375, 376, 380, 409, 433, 439, 441, 456, 457, 458, 464, 465, 471, 472, 474, 476, 477, 478, 480, 487, 489, 490, 493, 494, 495, 518, 523, 528, 534, 536, 537, 539, 543, 544, 546, 547, 548, 549, 550, 551], "int8_conv_config": 494, "int8_model": [457, 458], "int8_model_path": 545, "int8_node_name_revers": 133, "int8_onnx_config": [195, 526], "int8_sequ": [33, 306], "int_label": 535, "int_max": 30, "integ": [162, 179, 180, 195, 230, 234, 281, 474, 476, 479, 487, 493, 495, 519, 544, 547, 550, 552], "integerop": 553, "integr": [133, 163, 385, 473, 477, 480, 487, 493, 536, 547], "intel": [154, 165, 177, 178, 188, 226, 233, 234, 246, 262, 270, 276, 290, 302, 303, 304, 305, 391, 392, 394, 436, 437, 438, 439, 440, 441, 442, 444, 445, 446, 447, 449, 451, 455, 467, 469, 471, 473, 474, 475, 476, 477, 478, 480, 481, 482, 484, 487, 488, 489, 491, 493, 494, 495, 519, 522, 523, 525, 526, 527, 528, 529, 533, 534, 537, 538, 540, 541, 542, 543, 544, 546, 547, 548, 550, 552, 553], "intel_extension_for_pytorch": [445, 475], "intelcaff": 543, "intellig": 543, "intelon": 543, "inteltensorflow": [214, 216], "intend": 489, "inter": 195, "inter_area": 221, "inter_num_of_thread": [195, 257, 261, 536], "inter_pol": 221, "interact": [492, 549], "interest": [488, 492], "interfac": [71, 98, 154, 301, 343, 390, 392, 454, 473, 475, 477, 480, 487, 531, 536, 544, 548], "interleav": 210, "intermedi": [30, 135, 163, 195, 487, 490, 531, 544], "intermediatelayersknowledgedistillationloss": 163, "intermediatelayersknowledgedistillationlossconfig": 195, "intern": [135, 207, 278, 387, 471, 521, 535, 542], "internal_pattern": 278, "internet": 211, "interpol": [186, 225, 535, 542, 551], "intersect": [234, 406, 493, 535], "interv": [186, 542], "intra": 195, "intra_num_of_thread": [195, 257, 261, 536], "introduc": [59, 331, 469, 476, 487, 493, 494, 495, 528, 536, 544, 547, 548, 550], "introduct": 469, "intuit": [476, 487, 547, 550], "inturn": 535, "inuput": 30, "invalid": 413, "invalid_lay": 175, "invent": [487, 544], "invers": [476, 547], "investig": [488, 520], "invok": [230, 494], "involv": 475, "io": [1, 140, 396, 439, 476, 492, 532], "iou": 234, "iou_thr": [230, 234, 535], "iou_typ": 230, "ipc": 492, "ipex": [145, 195, 411, 412, 413, 417, 437, 441, 445, 464, 473, 474, 531, 534, 536, 537, 550], "ipex_config": [145, 413], "ipex_config_path": [145, 413, 417], "ipexmodel": 244, "ir_vers": 29, "is_asymmetr": 494, "is_b_transpos": 30, "is_ckpt_format": [133, 385], "is_dynam": 409, "is_fused_modul": 145, "is_glob": 175, "is_hpex_avail": 445, "is_imposs": 225, "is_int8_model": 464, "is_ipex_avail": 445, "is_ipex_import": 445, "is_large_model": 30, "is_leaf": 420, "is_list_or_tupl": 90, "is_measur": 245, "is_model_quant": 1, "is_onnx_domain": 90, "is_package_avail": 445, "is_perchannel": 494, "is_qat": 144, "is_saved_model_format": [133, 385], "is_subgraph": 87, "is_transformers_import": 445, "isa": 473, "isiter": 1, "isn": [52, 53, 55, 324, 325, 327], "issu": [413, 487, 488, 489, 491, 492, 532, 544], "item": [30, 192, 195, 224, 278, 391, 465, 487, 519, 524, 542, 550, 552], "item_list": 30, "item_typ": 278, "itemstyl": 552, "iter": [1, 2, 90, 125, 133, 145, 151, 174, 180, 187, 190, 195, 198, 199, 203, 207, 211, 212, 235, 262, 283, 301, 305, 385, 387, 413, 417, 418, 425, 433, 439, 448, 451, 454, 476, 480, 481, 490, 493, 518, 521, 536, 542, 544, 550, 552], "iter_bar": 536, "iter_op": [133, 385], "iterabledataset": [207, 211], "iterablefetch": [203, 387], "iterablesampl": [207, 387], "iteration_list": 493, "iterativeschedul": 190, "iterator_sess_run": [133, 385], "itex": [32, 94, 195, 289, 359, 457, 480, 537, 544, 550], "itex_instal": 391, "itex_mod": [32, 33, 74, 92, 116, 121, 289, 306, 346, 357, 371, 376], "itex_qdq_mod": [56, 57, 328, 329], "itrex": [195, 474, 550], "its": [30, 45, 81, 133, 135, 173, 182, 185, 187, 192, 195, 205, 211, 225, 228, 229, 266, 317, 352, 406, 408, 456, 473, 476, 481, 487, 488, 533, 535, 537, 542, 547, 549, 551, 552], "itself": 542, "j": [474, 487, 492, 534, 542, 550, 553], "jan": 543, "jason": 550, "jbla": 31, "jeffrei": 519, "ji": [476, 487, 547], "jit": [173, 475, 550], "jitbasicsearch": 173, "jitter": 551, "john": [391, 465], "join": 492, "joint": 543, "jonathanhuang": 230, "journei": 543, "jpeg": 551, "jpg": [210, 214, 216, 492], "json": [145, 160, 210, 225, 411, 413, 417, 464, 476, 538, 547, 551], "json_file_path": [411, 464], "judg": 420, "juli": 543, "jun": 543, "june": [492, 543], "just": [82, 200, 223, 225, 245, 353, 387, 413, 475, 480, 487, 527, 536, 541, 544, 550, 551, 552], "k": [234, 262, 535, 542], "k_block": 31, "kappa": 425, "keep": [140, 161, 184, 192, 267, 396, 490, 493, 520, 548], "keep_mask_lay": 175, "keepdim": [487, 550], "kei": [133, 135, 140, 141, 173, 184, 192, 195, 243, 281, 390, 391, 396, 398, 413, 433, 452, 454, 465, 476, 487, 492, 494, 543, 547, 552], "kept": 179, "kera": [55, 101, 165, 173, 192, 195, 211, 218, 238, 243, 287, 290, 302, 305, 327, 390, 391, 478, 480, 494, 521, 524, 538], "keras_model": 237, "keras_sess": [243, 390], "kerasadaptor": 288, "kerasbasepattern": 175, "kerasbaseprun": 180, "kerasbasicprun": 181, "kerasconfigconvert": 288, "kerasmodel": [238, 390], "keraspatternnxm": 179, "kerasqueri": 288, "kerassurgeri": 288, "kernel": [31, 149, 195, 476, 493, 494, 552], "kernel_constraint": [292, 293], "kernel_initi": [292, 293], "kernel_regular": [292, 293], "kernel_s": [292, 294, 298], "keutzer": 542, "key_layer_nam": 184, "keynot": 543, "keyword": [140, 195, 396, 413, 431, 441], "kim": 542, "kind": [145, 536], "kit\u4e3aai\u5e94\u7528\u5e26\u6765\u9ad8\u6548\u5f02\u6784\u52a0\u901f\u670d\u52a1": 543, "kl": [1, 3, 195, 409, 413, 439, 452, 460, 494, 495, 519, 528, 536, 552], "kl_diverg": 459, "klcalibr": 3, "know": [520, 524, 548], "knowledg": [162, 163, 195, 479, 523, 525, 531, 536, 538], "knowledgedistillationframework": 163, "knowledgedistillationloss": [163, 536], "knowledgedistillationlossconfig": [195, 523, 536, 541], "known": [140, 266, 396, 471, 472, 536, 539, 542, 544, 552], "kriz": 211, "kullback": 495, "kwarg": [2, 30, 90, 107, 108, 109, 110, 111, 112, 113, 114, 117, 118, 119, 120, 122, 123, 141, 145, 171, 195, 211, 223, 225, 234, 235, 236, 238, 240, 242, 243, 244, 262, 277, 279, 281, 292, 293, 294, 297, 298, 363, 364, 365, 366, 367, 368, 369, 372, 373, 374, 375, 377, 378, 390, 398, 399, 418, 420, 429, 431, 433, 437, 439, 441, 447, 448, 451, 461, 462, 464, 465, 521], "kwon": 542, "l": [476, 482, 519, 552], "l1": 195, "l12": 553, "l2": [195, 542], "l6": 553, "l954": 227, "l983": 227, "label": [195, 198, 199, 209, 211, 212, 213, 214, 217, 221, 225, 227, 229, 234, 235, 262, 387, 413, 448, 480, 490, 521, 535, 536, 544, 551], "label_fil": [209, 225, 551], "label_list": [209, 234], "label_map": 535, "label_shap": [213, 387], "label_shift": [221, 551], "labelbalancecocorawfilt": 217, "labelbalancecocorecordfilt": 217, "labelshift": [221, 551], "lack": [521, 527], "lake": [473, 532, 537, 543], "lambada": [474, 550], "lambada_openai": [534, 553], "lambda": [140, 396, 545], "lamini": [474, 542, 550], "land": 543, "languag": [29, 149, 227, 413, 431, 441, 471, 472, 474, 476, 477, 479, 480, 487, 488, 526, 539, 543, 545, 547, 550], "laplacian": 476, "larei": 542, "larg": [29, 30, 149, 413, 471, 472, 474, 476, 477, 479, 480, 487, 521, 536, 539, 543, 545, 547, 550, 553], "larger": [152, 443, 476, 487, 494, 542, 547, 550], "lasso": [189, 531, 542], "lassounbalanc": 553, "last": [145, 169, 192, 195, 413, 471, 473, 474, 476, 521, 537, 544, 547, 550], "last_batch": [200, 202, 205, 206, 208, 387, 521], "last_conv_or_matmul_quant": [195, 544], "latenc": [549, 552], "latency_pattern": 482, "later": [140, 149, 396, 413, 443, 470, 520], "latest": [473, 477, 492, 532, 543, 548], "latin1": [140, 396], "launch": [482, 537], "launcher": 523, "layer": [32, 101, 102, 103, 104, 106, 107, 137, 139, 141, 149, 163, 166, 171, 173, 174, 175, 179, 184, 192, 194, 195, 288, 289, 291, 391, 395, 398, 413, 420, 429, 452, 454, 465, 469, 474, 475, 477, 487, 493, 494, 495, 523, 527, 531, 542, 547, 548], "layer1": [173, 195, 536, 542, 544], "layer2": [173, 536, 542, 544], "layer3": [536, 542], "layer_1": 174, "layer_2": 174, "layer_idx": 192, "layer_initi": 295, "layer_input": 192, "layer_map": [163, 195], "layer_nam": [195, 413, 542], "layer_norm": 526, "layer_tensor": 452, "layer_wis": [394, 464, 545], "layer_wise_qu": [136, 195, 545], "layerhistogramcollector": 452, "layernorm": [55, 327, 487, 550], "layerwisequ": 139, "layout": [39, 311], "layoutlmv2": 553, "layoutlmv3": 553, "lazi": [161, 465], "lazyimport": [161, 465], "ld_library_path": 527, "lead": [195, 473, 476, 480, 487, 520, 536, 537, 542, 547, 550], "leadership": 488, "leaky_relu": 526, "leakyrelu": [40, 312, 550], "learn": [469, 472, 473, 476, 477, 480, 487, 492, 493, 494, 521, 526, 530, 531, 532, 536, 537, 539, 542, 543, 544, 550, 552], "learning_r": [195, 536], "least": [188, 489, 536, 542, 552], "leav": 101, "lee": 542, "left": [221, 225, 487, 550, 551], "legal": [492, 554], "leibler": 495, "len": [135, 195, 225, 524, 551], "length": [184, 195, 209, 225, 230, 418, 476, 487, 535, 543, 544, 547, 551], "less": [40, 133, 145, 195, 312, 391, 433, 465, 518, 536, 542], "let": [495, 528, 542], "level": [31, 156, 173, 267, 281, 462, 471, 472, 487, 488, 539, 550, 552], "levelwis": 173, "leverag": [60, 332, 461, 470, 471, 475, 478, 481, 487, 526, 541, 544, 547, 552], "lib": 527, "libgl": 527, "libgl1": 527, "libglib2": 527, "librari": [174, 226, 257, 467, 473, 480, 492, 532, 536, 537, 543, 544], "licens": 489, "lie": 519, "light": 523, "lightn": 492, "lightweight": [483, 542], "like": [59, 81, 83, 133, 140, 156, 173, 192, 195, 198, 199, 200, 211, 234, 243, 262, 331, 352, 354, 385, 387, 390, 396, 448, 451, 473, 476, 480, 487, 489, 490, 492, 493, 494, 523, 531, 541, 542, 544, 547, 548, 550, 552], "limit": [138, 266, 397, 465, 472, 476, 477, 480, 492, 534, 539, 544, 547], "lin": [476, 487, 547], "line": [494, 520, 524, 531], "linear": [30, 142, 145, 149, 171, 173, 174, 179, 184, 192, 194, 195, 403, 413, 423, 427, 429, 433, 471, 474, 475, 476, 487, 490, 526, 536, 542, 547, 550, 552], "linear2linearsearch": 173, "linear_lay": 184, "linear_pattern": 174, "linearcompress": 174, "linearcompressioniter": 174, "linearli": 30, "link": [195, 209, 234, 262, 471, 477, 519, 526, 547, 553], "linkedin": 543, "linux": [154, 482, 483, 518, 527], "list": [1, 29, 30, 31, 39, 90, 125, 133, 135, 143, 145, 151, 152, 153, 154, 156, 173, 174, 179, 184, 188, 192, 194, 195, 198, 199, 203, 209, 221, 225, 227, 228, 230, 231, 232, 234, 235, 243, 249, 250, 253, 262, 277, 281, 283, 299, 302, 303, 305, 311, 385, 390, 398, 406, 413, 417, 418, 420, 433, 438, 439, 447, 448, 452, 457, 458, 465, 471, 474, 477, 479, 480, 490, 492, 493, 526, 528, 532, 534, 536, 540, 542, 544, 546, 550, 552], "liter": 281, "llama": [474, 483, 492, 534, 542, 543, 545, 547, 550, 553], "llama2": 492, "llamanorm": 550, "llm": [125, 126, 283, 286, 420, 439, 471, 472, 474, 475, 476, 479, 487, 529, 539, 542, 543, 545, 547, 550], "llm_weight_minmax": [92, 357], "lm": [476, 542], "lm_head": [476, 542, 547], "lm_head_config": 476, "ln": 527, "load": [133, 138, 140, 141, 160, 209, 224, 225, 235, 243, 262, 385, 390, 395, 397, 398, 408, 411, 412, 413, 415, 417, 431, 441, 444, 447, 464, 465, 471, 480, 494, 521, 527, 544, 545, 550], "load_and_cache_exampl": 209, "load_config_map": 160, "load_data_from_pkl": 465, "load_empty_model": [141, 398, 447, 476, 483, 545], "load_entri": 440, "load_huggingfac": [459, 536], "load_layer_wise_quantized_model": [141, 398], "load_modul": 398, "load_saved_model": [243, 390], "load_state_dict": [140, 396], "load_tensor": [141, 398], "load_tensor_from_shard": [141, 398], "load_valu": 398, "load_vocab": 224, "load_weight_onli": 464, "loadannot": 230, "loaded_model": 476, "loader": [1, 125, 198, 199, 235, 262, 283, 301, 305, 431, 448, 461, 521, 544], "loadformat": [431, 444], "loc": [140, 396], "local": [175, 195, 431, 441, 465, 476, 478, 492, 527, 532, 542, 549], "local_config": [192, 195], "local_config_fil": [32, 288, 289], "locat": [140, 146, 192, 225, 396, 413, 475, 480, 524, 544, 548, 551], "lock": [185, 531, 541, 542], "log": [131, 151, 159, 161, 173, 249, 250, 253, 383, 393, 413, 462, 482, 490, 549, 552], "log2": [472, 539], "log_fil": [151, 256, 260], "log_interv": 524, "log_process": 161, "log_quantizable_layers_per_transform": 420, "logfile_dict": 154, "logger": [161, 452, 459, 465], "logic": [421, 425, 443, 477], "logical_cpu": 154, "login": 549, "loglevel": 552, "logo": 533, "long": [225, 476, 520, 527, 547, 551], "long_str": 520, "longer": [209, 225, 418, 483, 551], "longest": [225, 551], "look": [133, 184, 479, 493, 495, 528, 535, 550], "lookup": 173, "loop": [448, 490, 494, 495, 528, 549, 552], "loss": [29, 153, 163, 195, 234, 448, 473, 475, 476, 480, 487, 519, 523, 524, 525, 534, 535, 536, 537, 541, 542, 543, 544, 547, 550, 552], "loss_func": [170, 188], "loss_sum": 536, "loss_typ": [163, 195, 536], "loss_weight": [163, 195, 536], "lossi": [487, 544], "lot": [487, 490, 550], "low": [30, 198, 199, 212, 213, 235, 387, 471, 473, 476, 481, 487, 493, 494, 518, 519, 524, 536, 537, 543, 544, 547, 550, 552], "low_cpu_mem_usag": 418, "low_gpu_mem_usag": [418, 439, 476], "low_memory_usag": 195, "lower": [224, 225, 232, 267, 413, 470, 471, 472, 475, 480, 487, 523, 539, 542, 543, 544, 550, 551, 552], "lowerbitssampl": 277, "lowercas": 209, "lowest": [542, 552], "lp_norm": 425, "lpot": [543, 548], "lr": [195, 418, 439, 451, 476, 524, 536], "lr_schedul": [418, 439, 476, 536, 542], "lstm": 16, "lstmoper": 17, "lvwerra": 553, "lwq": 476, "m": [30, 135, 177, 178, 195, 413, 433, 482, 489, 532, 542, 553], "machin": [154, 227, 476, 480, 483, 526, 532, 543, 550], "maco": 532, "made": [269, 487, 493, 544, 548, 552], "mae": [234, 535], "magnitud": [169, 191, 195, 234, 413, 531, 542], "magnitude_progress": 195, "magnitudecriterion": [169, 191], "mahonei": 542, "mai": [3, 133, 138, 140, 281, 385, 396, 397, 471, 473, 476, 477, 479, 487, 488, 489, 492, 494, 519, 520, 526, 527, 533, 537, 543, 544, 547, 550, 552], "mail": 488, "main": [3, 165, 184, 188, 301, 302, 305, 420, 437, 438, 442, 443, 476, 477, 478, 480, 482, 483, 487, 490, 521, 524, 536, 542, 544, 547], "mainli": [162, 190, 487, 492, 529, 536, 542, 544], "mainstream": [469, 492], "maintain": [234, 475, 476, 480, 487, 488, 489, 520, 538, 542, 547, 548], "mainten": 493, "major": [487, 530, 544, 550], "make": [30, 90, 128, 150, 175, 180, 188, 190, 207, 380, 465, 473, 474, 476, 479, 487, 488, 492, 493, 494, 518, 520, 521, 528, 535, 536, 542, 544, 545, 546, 547, 549, 550, 552], "make_dquant_nod": 30, "make_matmul_weight_only_nod": 31, "make_modul": 1, "make_nam": 90, "make_nc_model": 1, "make_nod": 30, "make_onnx_inputs_output": 90, "make_onnx_shap": 90, "make_quant_nod": 30, "make_sub_graph": 29, "make_symbol_block": 1, "makeiter": [133, 385], "male": 465, "malici": [140, 396], "manag": [152, 448, 454, 536], "mandatori": [198, 199, 262, 536], "mani": [31, 234, 262, 433, 476, 480, 487, 520, 521, 532, 547, 552], "manipul": [87, 88], "manner": [521, 538], "manual": [211, 542], "mao": 519, "map": [1, 30, 90, 133, 140, 145, 160, 195, 225, 229, 231, 232, 234, 396, 427, 442, 456, 458, 476, 487, 492, 520, 524, 535, 536, 542, 544, 547], "map_kei": 234, "map_loc": [140, 396], "map_numpy_to_onnx_dtyp": 90, "map_onnx_to_numpy_typ": 90, "map_point": [230, 234, 535], "map_tensorflow_dtyp": 90, "mar": 543, "mark": 519, "marketplac": [492, 543], "mask": [169, 175, 177, 180, 182, 186, 187, 209, 230, 542, 553], "mask_padding_with_zero": 209, "massiv": 542, "master": [3, 177, 178, 188, 227, 228, 231, 232, 234, 262, 536, 552], "match": [63, 87, 140, 173, 230, 231, 335, 396, 406, 475, 480, 482, 492, 547], "match_datatype_pattern": 145, "math": [51, 323, 487, 544], "mathemat": [474, 479, 487, 550], "matmul": [16, 31, 38, 44, 50, 58, 79, 94, 113, 122, 179, 195, 303, 310, 316, 322, 330, 350, 359, 368, 377, 528, 547, 552], "matmul_weight_only_nod": 31, "matmulfpq4": 31, "matmulnbit": 31, "matmuloper": 18, "matric": [487, 550], "matrix": [31, 234, 262, 479, 487], "matter": [207, 546], "max": [30, 89, 128, 150, 195, 225, 231, 232, 266, 380, 413, 433, 439, 465, 472, 476, 480, 487, 492, 532, 536, 539, 542, 544, 547, 550, 551, 552], "max_answer_length": [225, 551], "max_dim": [225, 551], "max_filter_tensor": 465, "max_grad_norm": 536, "max_inclusive_opset_vers": 89, "max_input_chars_per_word": 224, "max_length": 209, "max_min_data": [74, 75, 346], "max_num_class": 230, "max_ord": 228, "max_output": 490, "max_query_length": [225, 551], "max_seq_length": [209, 225, 420, 551], "max_sparsity_ratio_per_op": [175, 180, 195, 536, 542], "max_trial": [153, 195, 473, 481, 536, 552], "max_x": 413, "maxab": [439, 471], "maxabs_hw": [439, 471], "maxabs_hw_opt_weight": 471, "maxabs_pow2": 471, "maxim": [536, 542, 552], "maximum": [40, 153, 175, 180, 195, 209, 225, 228, 243, 266, 312, 390, 413, 425, 476, 487, 495, 519, 536, 542, 544, 550, 551], "maxpool": [16, 114, 123, 297, 369, 378, 528], "maxpooling2d": 297, "maxpooloper": 19, "mbzuai": [474, 550], "mckinstri": 519, "md": [177, 178, 195, 234, 262], "md5": 211, "mean": [29, 31, 175, 184, 195, 221, 225, 232, 234, 271, 413, 425, 431, 441, 471, 476, 478, 487, 490, 494, 495, 521, 524, 528, 535, 536, 542, 544, 545, 547, 550, 551, 552, 553], "mean_valu": [221, 551], "meaning": [536, 541], "meanwhil": 545, "measur": [133, 235, 385, 439, 460, 471, 476, 480, 487, 493, 518, 529, 535, 536, 547, 552], "measure_exclud": [439, 471], "mechan": [138, 169, 397, 469, 542, 549], "media": [488, 543], "median": [125, 283], "medium": [492, 543], "meet": [195, 201, 263, 265, 476, 478, 480, 481, 487, 490, 494, 540, 543, 544, 547, 552], "member": [488, 493], "memomeri": 139, "memori": [59, 145, 245, 331, 413, 433, 465, 471, 472, 473, 474, 476, 477, 479, 482, 487, 519, 521, 523, 536, 537, 539, 540, 542, 544, 545, 547, 550, 552, 553], "mention": [476, 487, 542, 547], "merg": [93, 202, 278, 358, 387, 482, 552], "merge_duplicated_qdq": [91, 356], "mergeduplicatedqdqoptim": [93, 358], "mesa": 527, "messag": [90, 131, 383, 482, 489, 552], "met": [153, 481, 487, 528, 544], "meta": [81, 352, 426, 483, 492, 534, 543, 553], "meta_info": 426, "meta_op_optim": [80, 351], "metaclass": 274, "metadata": [140, 396], "metagraphdef": [243, 390], "metainfochangingmemopoptim": [81, 352], "metal": [492, 527, 532], "metaop": [81, 352], "meteor": 532, "method": [31, 126, 128, 138, 140, 145, 189, 195, 203, 207, 208, 209, 211, 218, 225, 278, 280, 286, 380, 392, 396, 397, 417, 431, 441, 454, 459, 461, 462, 471, 476, 477, 478, 480, 487, 490, 492, 519, 520, 521, 523, 535, 536, 541, 542, 544, 546, 547, 550, 551, 552], "meticul": [472, 539], "metric": [153, 162, 195, 198, 199, 226, 235, 262, 448, 454, 469, 479, 493, 494, 524, 536, 537, 544, 549, 550, 552, 553], "metric_cl": [234, 262, 536], "metric_criterion": 245, "metric_fn": [231, 232], "metric_max_over_ground_truth": [231, 232], "metric_registri": 234, "metric_typ": 234, "metric_weight": 245, "mha": [176, 183, 542], "mha_compress": 184, "mha_head_s": 184, "mha_modul": 184, "mha_nam": 184, "mha_scor": 184, "mha_spars": [171, 542], "mhacompress": 184, "microcod": 553, "microsc": 477, "microsoft": [3, 472, 492, 493, 539], "middl": [487, 550], "migacz": 519, "might": [192, 473, 490, 520, 552], "migrat": [469, 474, 479, 487, 550], "mimic": [487, 544], "min": [128, 150, 195, 380, 433, 465, 472, 476, 480, 487, 539, 542, 544, 547, 550, 551, 552], "min_dim": [225, 551], "min_filter_tensor": 465, "min_max": 425, "min_sparsity_ratio_per_op": [175, 195, 536, 542], "min_train_sampl": 195, "min_x": 413, "mini": 553, "minilm": [543, 553], "minim": [128, 150, 266, 380, 471, 475, 476, 480, 487, 494, 495, 519, 525, 535, 536, 542, 544, 552], "minimum": [175, 195, 413, 425, 472, 495, 519, 536, 539, 542, 550, 552], "minmax": [1, 3, 303, 409, 413, 439, 475, 494, 495, 519, 528, 544], "minmax_file_path": 465, "minmax_lr": [418, 439, 451, 476], "minmaxcalibr": 3, "miou": 234, "misc": [138, 397, 533], "miss": [487, 542, 544], "mistral": 534, "mistralai": 534, "mitig": [476, 547], "mix": [134, 195, 235, 264, 278, 400, 437, 439, 469, 477, 492, 493, 499, 529, 531], "mix_precis": [195, 226, 281, 536, 537], "mixed_precis": [235, 394, 536], "mixed_precision_entri": 437, "mixed_precision_model": 134, "mixedprecis": [195, 536], "mixedprecisionconfig": [195, 235, 281, 437, 439, 473, 536, 537], "mixin": 451, "mixprecisionconfig": 437, "ml": 543, "mla": [493, 537, 544], "mleffici": 543, "mlp": [477, 542], "mlperf": [543, 553], "mm": 553, "mnist": [211, 524], "mnli": [209, 535, 553], "mobil": [536, 553], "mobilebert": 209, "mobilenet": [526, 549, 553], "mobilenetv2": 553, "mobiusml": [439, 476], "mod": 427, "mod_dict": 439, "mode": [28, 29, 30, 95, 140, 157, 161, 218, 230, 243, 278, 360, 390, 396, 404, 413, 437, 439, 442, 447, 464, 465, 471, 476, 477, 493, 494, 531, 544, 546, 547, 552], "model": [1, 2, 3, 16, 28, 29, 30, 31, 33, 34, 35, 36, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 54, 56, 57, 58, 59, 60, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 73, 74, 75, 76, 77, 78, 79, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 92, 93, 94, 101, 103, 125, 126, 127, 133, 134, 135, 139, 140, 141, 143, 144, 145, 149, 151, 153, 156, 162, 170, 171, 173, 180, 181, 182, 185, 187, 188, 190, 192, 195, 198, 199, 205, 208, 209, 211, 225, 226, 234, 235, 245, 256, 260, 261, 262, 263, 264, 266, 267, 271, 273, 274, 280, 281, 283, 286, 288, 301, 302, 305, 306, 307, 308, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 326, 328, 329, 330, 331, 332, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 345, 346, 347, 348, 349, 350, 352, 353, 354, 355, 357, 358, 359, 385, 388, 390, 391, 392, 396, 398, 406, 408, 411, 412, 413, 415, 417, 420, 431, 432, 433, 435, 437, 438, 441, 442, 447, 448, 449, 456, 457, 458, 461, 464, 465, 467, 469, 470, 471, 472, 473, 476, 477, 478, 479, 480, 483, 487, 489, 490, 493, 495, 499, 518, 519, 520, 521, 523, 524, 525, 529, 530, 531, 533, 535, 537, 540, 541, 543, 544, 548, 549, 551, 552], "model_attr": 156, "model_forward": [413, 433], "model_forward_per_sampl": 413, "model_info": 439, "model_level": 156, "model_loss": 552, "model_nam": [101, 195, 492], "model_name_or_path": [209, 431, 441, 492, 536, 545], "model_origin": [195, 262, 546], "model_path": [125, 133, 283, 385, 420, 439, 476], "model_proto": 90, "model_slim": [170, 184], "model_slim_ffn2": 171, "model_slim_mha": 171, "model_state_dict_path": [476, 483], "model_typ": [209, 465], "model_wis": 536, "model_wrapp": [2, 136, 388], "modelproto": [31, 235, 456, 538], "models": [195, 245, 536, 540], "modelwisetuningsampl": 277, "modern": [476, 487, 547], "modif": [489, 493, 528], "modifi": [184, 211, 261, 280, 471, 490, 495, 524, 528, 542], "modified_pickl": [137, 395], "modul": [136, 137, 155, 158, 170, 176, 183, 395, 407, 410, 414, 424, 428, 434, 446, 469, 471, 473, 476, 477, 481, 490, 492, 500, 520, 521, 529, 531, 535, 536, 538, 542, 546, 547], "module_debug_level1": 281, "module_hook_config": [145, 433], "module_nam": [141, 161, 169, 170, 180, 181, 182, 183, 185, 186, 187, 189, 191, 398, 465], "module_name_list": [145, 433], "module_node_map": 458, "module_typ": 420, "module_wrapp": 400, "modulelist": 420, "mold": 153, "momentum": [169, 531, 536, 542], "momentumbalanc": 553, "momentumunbalanc": 553, "monitor": [153, 442, 477], "more": [29, 133, 149, 156, 177, 178, 225, 385, 413, 439, 469, 471, 472, 473, 474, 476, 477, 480, 487, 491, 492, 494, 519, 520, 524, 526, 531, 532, 534, 536, 537, 539, 540, 541, 542, 546, 547, 550, 552, 553], "mosaicml": [474, 550, 553], "mose": 227, "mosesdecod": 227, "mosh": 542, "most": [195, 234, 471, 473, 476, 480, 487, 536, 537, 542, 544, 547, 550, 552, 553], "mostli": 520, "move": [63, 140, 335, 396, 413, 433, 476, 487, 490, 547, 548], "move_input_devic": 145, "move_input_to_devic": [413, 433], "move_squeeze_after_relu": [61, 333], "movesqueezeafterreluoptim": [63, 335], "mp": 480, "mpi": 552, "mpirun": 552, "mpt": [474, 542, 550, 553], "mrpc": [209, 234, 535, 542, 552, 553], "mscoco": 230, "mse": [31, 145, 195, 234, 262, 270, 465, 476, 487, 535, 547, 548], "mse_metric_gap": 465, "mse_v2": [195, 270], "mse_v2tunestrategi": 272, "mseloss": [487, 550], "msetunestrategi": 271, "msfp": [472, 539], "msft": 543, "msg": 462, "mt": 553, "mteval": 227, "much": [162, 169, 195, 225, 487, 550, 551], "mul": [40, 50, 51, 54, 149, 312, 322, 323, 326, 476, 526, 547, 550], "mullinear": [142, 429], "multi": [151, 154, 171, 173, 184, 230, 234, 262, 482, 521, 531, 536, 540, 542, 544, 552], "multi_object": 540, "multiclass": 535, "multilabel": 535, "multilingu": 553, "multiobject": 245, "multipl": [152, 165, 171, 196, 197, 201, 202, 209, 210, 212, 213, 214, 215, 216, 220, 222, 225, 235, 236, 237, 239, 245, 480, 518, 526, 529, 536, 541, 542, 549, 550, 552], "multipli": [3, 195, 470, 472, 476, 539, 547], "must": [225, 230, 451, 489, 490, 494, 518, 521, 532, 544, 551], "mx": [1, 402, 404, 439, 472, 477, 492, 529, 539], "mx_quant": 394, "mx_quant_entri": 437, "mx_spec": [403, 404], "mxfp4": [472, 539], "mxfp6": [472, 539], "mxfp8": [472, 539], "mxint8": [472, 539], "mxlinear": 403, "mxnet": [0, 1, 3, 195, 204, 208, 211, 214, 218, 225, 234, 235, 240, 262, 493, 494, 519, 521, 525, 528, 531, 536, 537, 538, 552], "mxnet_model": 237, "mxnetcifar10": 211, "mxnetcifar100": 211, "mxnetcropresizetransform": 225, "mxnetcroptoboundingbox": 225, "mxnetdataload": 204, "mxnetdataset": 211, "mxnetfashionmnist": 211, "mxnetfilt": 218, "mxnetimagefold": 211, "mxnetimagenetraw": 214, "mxnetmetr": 234, "mxnetmnist": 211, "mxnetmodel": 240, "mxnetnormalizetransform": 225, "mxnettransform": 225, "mxnettranspos": 225, "mxquantconfig": [437, 439, 472, 539], "mxquantiz": 403, "my": 489, "mydataload": [478, 480, 481], "n": [177, 178, 195, 210, 225, 228, 281, 487, 495, 520, 534, 542, 544, 550, 551], "n_best_siz": [225, 551], "n_bit": [487, 550], "n_block": [476, 547], "n_gpu": 536, "n_iter": 266, "n_sampl": [31, 145, 413, 451, 476], "n_warmup": 266, "na": [195, 239, 480, 531, 553], "name": [1, 30, 39, 52, 53, 55, 89, 90, 95, 101, 125, 133, 135, 140, 141, 144, 145, 146, 151, 152, 153, 156, 160, 166, 169, 173, 175, 180, 183, 184, 188, 189, 190, 191, 192, 194, 195, 209, 210, 211, 214, 218, 223, 225, 229, 234, 239, 243, 245, 262, 278, 280, 283, 292, 293, 297, 311, 324, 325, 327, 360, 385, 390, 391, 396, 398, 403, 412, 413, 417, 418, 420, 427, 433, 439, 442, 443, 445, 447, 452, 454, 456, 457, 458, 465, 471, 472, 475, 476, 477, 478, 489, 490, 495, 520, 524, 526, 528, 533, 535, 536, 538, 539, 542, 544, 548, 549, 552, 553], "namecollector": 1, "named_paramet": 524, "namespac": 520, "namhoon": 542, "nan": [41, 313], "narrow": [472, 539], "narrow_rang": 98, "nasconfig": 195, "nation": [211, 488], "nativ": 495, "natur": [227, 476, 526], "nbest_predict": [225, 551], "nbit": 426, "nblock": [418, 439], "nbsp": [552, 553], "nc": [549, 552], "nc_model": 1, "nc_resnet50_v1": 524, "nc_workspac": 195, "nchw": [39, 221, 311], "ncmodel": 1, "ndarrai": [1, 29, 30, 52, 53, 55, 225, 324, 325, 327, 452, 527, 551], "ndarray_to_devic": 1, "nearest": [173, 225, 439, 476, 477, 487, 547, 551], "nearst": 31, "necessari": [30, 188, 488, 494, 538, 542, 549, 552], "necessarili": [138, 397], "need": [1, 29, 90, 94, 151, 156, 173, 188, 195, 198, 199, 200, 207, 208, 211, 218, 225, 234, 235, 245, 262, 271, 359, 387, 404, 411, 413, 431, 441, 448, 458, 464, 465, 476, 479, 481, 483, 487, 490, 493, 520, 521, 524, 527, 531, 536, 542, 544, 545, 546, 547, 548, 550, 551, 552], "need_appli": [305, 442], "need_spac": 413, "neelnanda": [418, 451], "neither": 544, "neo": [529, 553], "neox": [534, 553], "nepoch": 536, "nest": [145, 391, 417, 465], "nesterov": 536, "net": [241, 391, 492], "netflix": 543, "nets_factori": 237, "network": [135, 169, 175, 176, 269, 439, 472, 473, 487, 519, 523, 526, 536, 539, 543, 544, 550, 552], "neural": [1, 135, 151, 154, 162, 165, 175, 176, 177, 178, 188, 195, 221, 222, 225, 226, 233, 234, 235, 239, 246, 262, 269, 270, 276, 290, 302, 303, 304, 305, 389, 392, 394, 436, 437, 438, 439, 440, 441, 442, 444, 445, 446, 447, 449, 451, 455, 467, 469, 471, 472, 473, 474, 475, 476, 477, 478, 480, 481, 482, 484, 487, 489, 493, 494, 495, 518, 519, 520, 522, 523, 524, 525, 526, 527, 528, 529, 530, 533, 534, 537, 538, 539, 540, 541, 543, 544, 547, 548, 550, 551, 552, 553], "neural_compressor": [470, 471, 472, 473, 474, 475, 476, 477, 478, 479, 480, 481, 483, 490, 492, 495, 518, 520, 521, 523, 524, 526, 529, 530, 535, 536, 537, 538, 539, 540, 541, 542, 544, 545, 546, 548, 549, 550, 551, 552], "neurip": 543, "neuron": 542, "never": [140, 396, 552], "nevertheless": [472, 539], "new": [1, 3, 31, 133, 151, 200, 211, 225, 245, 385, 387, 392, 413, 433, 443, 451, 469, 473, 474, 475, 476, 487, 489, 494, 524, 536, 537, 542, 543, 544, 547, 548, 549, 551], "new_api": [33, 34, 56, 57, 62, 64, 77, 84, 116, 121, 128, 306, 328, 329, 334, 336, 348, 371, 376, 380], "new_dtyp": 30, "new_func": [133, 385], "new_graph_def": [133, 385], "new_init": 31, "new_metr": 535, "new_modul": [141, 145, 398, 413, 433, 447], "new_quantized_nam": 30, "newapi": [79, 350], "newdataload": 521, "newli": [536, 542], "newlin": [232, 465], "newmetr": 535, "next": [45, 203, 281, 317, 387, 476, 487, 492, 494, 495, 521, 547, 552], "next_annotation_id": 230, "next_tune_cfg": 552, "nextplatform": 543, "nf4": [433, 476, 547], "nfl": 232, "ngram": [227, 535], "nhwc": [39, 221, 311], "ni_workload_nam": 195, "ninm": 176, "nll_loss": 524, "nlp": [188, 195, 473, 477, 480, 487, 542, 544], "nn": [141, 142, 145, 173, 174, 184, 194, 195, 235, 262, 398, 408, 412, 413, 417, 420, 427, 429, 431, 433, 435, 437, 438, 441, 442, 447, 458, 461, 464, 471, 476, 477, 487, 490, 536, 538, 547, 550], "nncf": 135, "no_absorb_lay": [145, 433], "node": [1, 29, 30, 31, 35, 39, 40, 41, 42, 45, 47, 49, 52, 53, 55, 59, 62, 65, 67, 68, 69, 83, 87, 88, 90, 95, 117, 125, 133, 154, 173, 243, 261, 283, 307, 311, 312, 313, 314, 317, 319, 321, 324, 325, 327, 331, 334, 337, 339, 340, 341, 354, 360, 372, 385, 390, 406, 413, 433, 443, 456, 458, 482, 493, 524, 545, 552, 553], "node1": 524, "node2": 524, "node_candidate_list": 406, "node_collector": 135, "node_def": [52, 53, 55, 324, 325, 327], "node_from_map": [52, 53, 55, 324, 325, 327], "node_index": 154, "node_list": 406, "node_map": [52, 53, 55, 324, 325, 327], "node_nam": [52, 53, 55, 133, 243, 251, 324, 325, 327, 390, 494], "node_name_from_input": [52, 53, 55, 324, 325, 327], "node_name_list": [131, 383], "node_op": 494, "node_set_from_user_config": 406, "nodedef": [52, 53, 55, 324, 325, 327], "non": [3, 465, 471, 473, 476, 490, 547, 552], "nondigit_punct_r": 227, "none": [1, 28, 30, 31, 32, 33, 34, 48, 74, 87, 89, 90, 95, 101, 127, 133, 135, 139, 140, 141, 142, 145, 151, 152, 153, 156, 161, 162, 163, 169, 170, 171, 173, 177, 188, 192, 195, 198, 199, 200, 202, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 216, 221, 225, 230, 234, 235, 245, 256, 260, 261, 262, 263, 264, 266, 267, 271, 273, 274, 278, 281, 284, 288, 289, 292, 293, 294, 297, 298, 299, 301, 302, 303, 305, 306, 320, 346, 360, 385, 387, 391, 392, 396, 398, 403, 404, 405, 413, 417, 418, 420, 423, 426, 429, 431, 432, 433, 435, 438, 439, 441, 442, 447, 448, 451, 452, 454, 457, 458, 461, 464, 465, 471, 472, 476, 477, 480, 482, 492, 493, 494, 521, 535, 539, 544, 547, 551, 552], "nor": 544, "norm": [16, 476], "normal": [3, 20, 225, 232, 476, 487, 536, 540, 547, 550, 551], "normalfloat": [476, 547], "normalizationoper": 20, "normalize_answ": 232, "normalizetftransform": 225, "normalizetransform": 225, "not_use_best_ms": [418, 439, 476], "notat": [195, 465], "note": [40, 138, 153, 179, 230, 272, 312, 392, 397, 469, 470, 471, 473, 474, 475, 476, 479, 482, 487, 492, 494, 495, 520, 521, 524, 526, 528, 529, 532, 534, 536, 542, 544, 547, 550, 552], "notebook": 469, "noteworthi": 519, "noth": [230, 552], "notic": [128, 150, 380, 473, 476, 533, 537, 548], "notimplementederror": 447, "nov": 543, "novel": 523, "now": [195, 225, 490, 495, 524, 551, 552], "np": [30, 225, 266, 524, 550, 551, 552], "np_dtype": 90, "npu": [195, 544], "npy": 210, "npy_dir": 210, "npz": 211, "nr": 90, "nsampl": [418, 420, 439, 547], "nsdf3": 211, "nuanc": 476, "num": [433, 465], "num_bin": [1, 3, 452], "num_bit": [31, 98, 142, 145, 413, 429, 487, 550], "num_c": 482, "num_class": 234, "num_cor": [209, 210, 214], "num_cores_on_numa": 482, "num_cores_per_inst": [154, 482], "num_correct": 234, "num_cpu": 154, "num_detect": [230, 234, 535, 536], "num_gt_box": 230, "num_i": 482, "num_inst": [154, 482], "num_of_inst": [151, 195, 518, 536], "num_of_process": 524, "num_quantized_bin": 3, "num_replica": 524, "num_sampl": 234, "num_train_epoch": [536, 542], "num_work": [200, 202, 205, 206, 208, 387, 521, 536, 544], "numa": [154, 482], "numa_index": 154, "numa_info": 154, "numa_node_index": 154, "numactl": [151, 154, 527], "number": [3, 31, 52, 53, 90, 125, 145, 152, 153, 161, 171, 177, 178, 195, 207, 210, 221, 225, 231, 232, 234, 257, 261, 266, 281, 283, 324, 325, 387, 413, 418, 426, 433, 443, 454, 465, 470, 476, 481, 482, 487, 518, 521, 524, 535, 542, 544, 547, 549, 550, 551, 552], "number_of_process": 552, "numer": [195, 234, 472, 473, 476, 480, 495, 537, 539, 543, 544, 547], "numpi": [29, 30, 52, 53, 55, 90, 133, 225, 230, 324, 325, 327, 527, 550, 551], "nvidia": [492, 519, 531, 532, 553], "nxm": [176, 186, 195, 542], "o": [140, 281, 396, 492, 520, 532], "o0": [267, 552], "o1": 552, "obj": [1, 90, 170, 192, 208, 235, 245, 262, 448, 454, 465], "obj1": 465, "obj2": 465, "obj_cl": 245, "obj_criterion": 245, "obj_weight": 245, "object": [1, 29, 30, 31, 59, 71, 90, 101, 117, 133, 134, 135, 138, 140, 144, 145, 151, 153, 160, 162, 169, 170, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 195, 198, 199, 200, 209, 210, 211, 225, 226, 230, 234, 235, 243, 244, 257, 261, 262, 266, 280, 331, 343, 372, 385, 387, 390, 391, 396, 397, 399, 406, 409, 411, 413, 417, 433, 447, 448, 451, 454, 464, 465, 469, 475, 477, 480, 490, 494, 499, 518, 520, 521, 527, 535, 536, 538, 541, 542, 544, 551, 552, 553], "object_detect": [195, 230], "objective_cfg": 245, "objective_cl": 245, "objective_custom_registri": 245, "objective_registri": 245, "oblig": 488, "observ": [145, 417, 439, 442, 470, 471, 475, 476, 477, 495, 547, 549, 552], "obstacl": [472, 539], "obtain": [171, 173, 182, 187, 189, 192, 487, 490, 494, 542, 549, 550, 552], "occupi": [472, 539], "occur": 475, "ocp": [472, 539], "oct": 543, "off": [3, 52, 53, 55, 324, 325, 327, 476, 487, 489, 547], "offens": 488, "offer": [472, 476, 480, 539], "offici": [133, 227, 231, 232, 385, 488, 550], "offlin": [465, 474, 479, 480, 487, 488, 536, 544, 550], "offset_height": [225, 551], "offset_width": [225, 551], "ofir": 542, "often": [192, 476, 521, 541, 542], "old": [391, 465, 474, 536, 548], "old_hist": [391, 465], "oliv": [492, 543], "omit": [471, 547], "omp_num_thread": 483, "ompi_mca_btl_vader_single_copy_mechan": 492, "on_after_compute_loss": [448, 523, 536, 541], "on_after_optimizer_step": [536, 542], "on_before_optimizer_step": [448, 523, 536, 541, 542], "on_epoch_begin": [448, 454, 523, 536, 541], "on_epoch_end": [448, 454, 523, 536, 541], "on_step_begin": [448, 454, 523, 536, 541, 542], "on_step_end": [448, 454, 523, 536, 541], "on_train_begin": [448, 490, 523, 536, 541, 542, 544], "on_train_end": [448, 523, 536, 541, 542, 544], "onc": [133, 140, 165, 190, 263, 265, 385, 396, 480, 494, 495, 521, 542, 543, 552, 553], "one": [31, 94, 95, 100, 140, 145, 151, 175, 179, 184, 187, 188, 190, 225, 227, 230, 234, 359, 360, 396, 413, 417, 433, 473, 476, 477, 480, 481, 482, 487, 493, 519, 523, 524, 528, 531, 532, 535, 536, 537, 540, 541, 542, 544, 545, 547, 548, 550, 551, 552], "oneapi": [469, 473, 532, 543], "onednn": [473, 480, 537, 544], "onednn_max_cpu_isa": 473, "ones": [140, 230, 396, 542], "oneshotschedul": 190, "onli": [29, 31, 39, 48, 55, 71, 94, 100, 128, 140, 149, 150, 151, 165, 170, 176, 183, 195, 209, 262, 272, 280, 281, 311, 320, 327, 343, 359, 380, 396, 413, 428, 429, 431, 432, 433, 439, 441, 458, 465, 469, 471, 473, 477, 481, 482, 493, 494, 495, 518, 519, 520, 521, 524, 527, 528, 529, 534, 536, 537, 542, 543, 544, 545, 550, 552], "onlin": [476, 488, 549], "onnx": [2, 3, 16, 28, 30, 31, 72, 127, 149, 195, 205, 235, 242, 257, 456, 457, 458, 463, 489, 492, 493, 494, 496, 521, 525, 526, 528, 531, 537, 538, 539, 543, 547, 550, 552], "onnx_graph": 86, "onnx_ml_pb2": [235, 538], "onnx_model": [237, 256], "onnx_nod": [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 86], "onnx_qlinear_to_qdq": 456, "onnx_quant": [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27], "onnx_schema": 86, "onnx_typ": 90, "onnxbilinearimagenettransform": 221, "onnxcommunitymeetup2023": 543, "onnxgraph": 87, "onnxmodel": [31, 242, 256], "onnxnod": 88, "onnxopschema": 89, "onnxprofilingpars": 249, "onnxqlinear2qdq": 195, "onnxqlinear2qdqconfig": 195, "onnxresizecropimagenettransform": 221, "onnxrt": [29, 30, 31, 209, 211, 218, 225, 234, 256, 463, 493, 537, 544, 553], "onnxrt_cuda_ep": [195, 537, 544], "onnxrt_dataload": 256, "onnxrt_dml_ep": [195, 544], "onnxrt_dnnl_ep": [195, 537, 544], "onnxrt_integ": 536, "onnxrt_integerop": [211, 218, 225], "onnxrt_qdq": [211, 218], "onnxrt_qlinear": 536, "onnxrt_qlinearop": [211, 218, 225], "onnxrt_qlinearopsadaptor": 493, "onnxrt_trt_ep": [195, 537, 544], "onnxrtaug": 2, "onnxrtbertdataload": 205, "onnxrtbertdataset": 209, "onnxrtcroptoboundingbox": 225, "onnxrtdataload": [205, 256], "onnxrtglu": 234, "onnxrtimagenetdataset": 214, "onnxrtitdataset": 211, "onnxrtitfilt": 218, "onnxrtitmetr": 234, "onnxrtittransform": 225, "onnxrtparserfactori": 248, "onnxrtqldataset": 211, "onnxrtqlfilt": 218, "onnxrtqlmetr": 234, "onnxrtqltransform": 225, "onnxruntim": [3, 195, 205, 211, 218, 257, 493, 519, 521, 531, 532, 537], "onto": [140, 396], "op": [1, 16, 36, 38, 50, 51, 52, 53, 54, 55, 56, 57, 59, 63, 66, 70, 73, 76, 77, 78, 79, 81, 90, 92, 94, 108, 109, 110, 116, 118, 119, 120, 121, 126, 128, 131, 133, 135, 144, 145, 149, 173, 195, 257, 261, 267, 269, 271, 278, 279, 280, 286, 308, 310, 322, 323, 324, 325, 326, 327, 328, 329, 331, 335, 338, 342, 345, 347, 348, 349, 350, 352, 357, 359, 363, 364, 365, 371, 373, 374, 375, 376, 380, 383, 385, 412, 413, 417, 433, 437, 447, 456, 458, 460, 465, 473, 474, 477, 487, 493, 494, 495, 528, 536, 537, 542, 544, 546, 548, 550, 552], "op_block_lst": 277, "op_cfg": 139, "op_defin": 251, "op_dict": 536, "op_dtyp": 277, "op_dtype_dict": 277, "op_infos_from_cfg": [145, 412, 413, 417], "op_level": 156, "op_list": 493, "op_nam": [145, 195, 279, 413, 417, 433, 447, 465, 466, 475, 494, 536, 542], "op_name_dict": [195, 475, 536, 544, 552], "op_name_or_module_typ": [152, 299, 303, 439], "op_name_typ": 278, "op_quant_mod": 279, "op_registri": 21, "op_run": 251, "op_typ": [21, 125, 126, 133, 194, 279, 283, 286, 303, 413, 417, 474, 475], "op_type_dict": [195, 475, 495, 544, 547, 552], "op_type_level": 156, "op_types_to_quant": 28, "op_user_cfg": 280, "op_user_cfg_modifi": 280, "op_wis": 536, "op_wise_config": [92, 116, 121, 357, 371, 376, 494], "op_wise_sequ": [116, 121, 371, 376], "open": [140, 226, 396, 454, 467, 488, 492, 526, 527, 536, 543], "openai": [474, 550], "opencv": 527, "opentri": 465, "openvinotoolkit": 135, "oper": [4, 30, 89, 95, 125, 133, 152, 156, 173, 174, 179, 195, 221, 257, 261, 283, 299, 360, 385, 406, 413, 470, 471, 473, 474, 475, 476, 477, 478, 479, 480, 487, 490, 518, 521, 526, 542, 544, 547, 550, 551, 552], "operator_name_or_list": 477, "operatorconfig": [299, 439], "ops_lst": [145, 417], "ops_nam": [145, 417], "opset": [29, 87, 89, 90, 195, 457, 458, 526], "opset_vers": [90, 127, 195, 457, 458, 526], "opt": [188, 474, 487, 492, 534, 542, 550, 552, 553], "opt_cfg": [60, 332], "opt_model": [470, 475, 536], "opt_param": 425, "optdecoderlay": 550, "optim": [39, 59, 60, 64, 65, 101, 103, 133, 164, 167, 168, 170, 173, 182, 187, 195, 266, 311, 331, 332, 336, 337, 385, 424, 439, 448, 450, 452, 465, 469, 475, 476, 479, 480, 481, 483, 487, 492, 518, 520, 523, 524, 528, 531, 532, 534, 536, 538, 543, 544, 546, 547, 549, 550, 552], "optimize_lay": 102, "optimize_qdq": [115, 370], "optimize_weights_proximal_legaci": 425, "optimized_model_tensor": 465, "optimized_tensor_data": 466, "optimizedmodel": 461, "optimizeqdqgraph": [116, 371], "optimizer_registri": 165, "optimizer_typ": 165, "optimum": [471, 547], "option": [3, 31, 90, 140, 145, 156, 161, 175, 195, 198, 199, 209, 225, 230, 234, 235, 262, 278, 280, 281, 391, 392, 396, 398, 408, 409, 413, 415, 418, 425, 431, 433, 435, 437, 438, 439, 441, 442, 447, 448, 457, 458, 459, 461, 465, 476, 477, 480, 487, 494, 495, 520, 521, 528, 532, 536, 542, 544, 547, 549, 550, 551, 552], "optuningconfig": [277, 278, 279], "optyp": [1, 195, 456, 494], "optype_wise_": 494, "optypes_to_exclude_output_qu": [28, 195, 544], "optypewis": 494, "optypewisetuningsampl": 277, "opwis": 494, "opwisetuningsampl": 277, "orchestr": [448, 469, 531], "order": [139, 145, 153, 227, 228, 266, 271, 280, 476, 481, 487, 490, 535, 547, 550, 552], "ordered_op": 145, "ordereddefaultdict": 280, "ordereddict": [403, 412, 416, 419, 430, 520], "ordinari": 549, "org": [169, 187, 230, 420, 439, 490, 492, 532, 542], "orient": 488, "orig_answer_text": 225, "orig_lay": [142, 429], "orig_model": 476, "orig_sav": 477, "orig_text": 225, "origin": [30, 31, 125, 133, 141, 145, 173, 185, 192, 195, 209, 225, 267, 280, 283, 385, 398, 413, 427, 431, 433, 441, 442, 461, 465, 476, 477, 478, 480, 487, 489, 542, 544, 547, 551, 552], "original_model": [431, 441, 476], "ort": 257, "ortsmoothqu": 29, "other": [52, 53, 55, 138, 149, 208, 232, 243, 324, 325, 327, 390, 397, 413, 472, 477, 480, 487, 488, 490, 494, 495, 500, 520, 528, 529, 531, 533, 536, 538, 539, 540, 542, 544, 550, 551, 552, 553], "otherwis": [140, 211, 225, 396, 406, 413, 427, 451, 465, 476, 488, 494, 547, 551], "ouput_dir": 545, "our": [128, 145, 195, 380, 413, 472, 492, 526, 536, 539, 549], "out": [178, 195, 209, 210, 211, 412, 413, 476, 478, 480, 487, 489, 490, 492, 542, 544, 547], "out_dtyp": 439, "out_featur": [403, 423, 429], "out_graph_def": [133, 385], "out_graph_fil": [133, 385], "outcom": 234, "outer": [202, 387], "outlier": [125, 283, 474, 476, 479, 487, 494, 519, 547, 550], "outlin": [494, 495], "outofcheeseerror": 520, "outperform": 476, "output": [29, 30, 31, 36, 39, 44, 59, 83, 90, 95, 133, 145, 166, 173, 174, 179, 192, 195, 198, 199, 227, 234, 235, 243, 262, 308, 311, 316, 331, 354, 360, 385, 390, 391, 408, 413, 415, 417, 425, 431, 433, 439, 442, 448, 457, 458, 461, 462, 465, 471, 476, 477, 478, 487, 490, 493, 494, 523, 524, 526, 528, 530, 535, 536, 538, 541, 542, 544, 547, 550, 551, 552], "output_data": 29, "output_dict": 31, "output_dir": [139, 408, 415, 431, 461, 477, 536], "output_fn": 225, "output_func": [145, 433], "output_graph": 195, "output_graph_def": 479, "output_handl": [161, 465], "output_index_map": [234, 535], "output_mod": 209, "output_model": [281, 536], "output_nam": [87, 127, 195, 243, 390, 457, 458, 526], "output_node_nam": [68, 69, 116, 117, 121, 133, 340, 341, 371, 372, 376, 385], "output_path": 230, "output_process": 166, "output_shap": 87, "output_tensor": [133, 243, 385, 390], "output_tensor_id_op_nam": [412, 413, 417], "output_tensor_ids_op_nam": [145, 413, 417], "output_tensor_nam": [133, 243, 385, 390], "output_valu": [145, 433], "outputs_to_valu": 90, "over": [90, 140, 211, 234, 396, 494, 525, 531, 535, 542, 550, 552], "overal": [476, 495, 547], "overflow": [487, 544], "overhead": [476, 550], "overli": 520, "overrid": [195, 465, 477, 520], "overridden": 552, "overview": [492, 529, 552], "overwrit": 211, "overwrite_exist": 151, "own": [59, 140, 207, 225, 245, 331, 396, 469, 487, 494, 521, 531, 535, 540, 547, 549], "p": [3, 476, 483, 487, 547], "p_conf": [536, 541], "pack": [30, 46, 318, 421, 426], "packag": [89, 445, 492, 493, 520, 527, 532, 543, 548, 552], "package_nam": 445, "packer": 421, "pad": [16, 31, 56, 57, 209, 225, 292, 294, 297, 298, 328, 329, 551], "pad_max_length": 547, "pad_tensor": 31, "pad_token": 209, "pad_token_segment_id": 209, "paddedcentercroptransform": 225, "padding_mod": 551, "pade": 31, "padoper": 22, "page": [488, 489], "pager": 520, "pain": [487, 544], "pair": [92, 195, 357, 406, 473, 475, 494, 521, 536, 537], "paper": [474, 476, 487, 542, 547, 550], "paragraph": [231, 232], "parallel": [210, 257, 261, 536, 552], "param": [145, 151, 154, 156, 165, 200, 234, 266, 387, 465, 471, 493, 538, 552], "param1": 281, "param2": 281, "param3": 281, "param_alia": 465, "param_dict": [163, 165], "param_nam": [398, 465], "paramet": [1, 3, 29, 30, 31, 52, 53, 55, 71, 90, 101, 117, 125, 126, 133, 134, 135, 140, 141, 144, 145, 146, 151, 152, 153, 154, 156, 160, 161, 162, 163, 165, 167, 169, 170, 171, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 194, 195, 198, 199, 208, 209, 211, 218, 221, 225, 227, 228, 230, 231, 232, 234, 235, 239, 243, 245, 257, 261, 262, 266, 274, 278, 280, 281, 283, 286, 301, 305, 324, 325, 327, 343, 372, 385, 390, 391, 396, 398, 404, 406, 408, 409, 411, 412, 413, 415, 417, 418, 420, 422, 425, 427, 431, 433, 435, 437, 438, 439, 441, 442, 443, 445, 447, 448, 454, 456, 457, 458, 461, 462, 464, 465, 472, 474, 475, 476, 479, 480, 482, 487, 490, 494, 521, 524, 531, 535, 536, 539, 542, 544, 545, 547, 549, 550, 551, 552], "parameter": 542, "parameter1": 281, "parameter2": 281, "paramlevel": 156, "params_list": [152, 156], "parent": [185, 186, 190, 413, 433], "pars": [90, 133, 145, 154, 209, 210, 221, 225, 249, 250, 253, 385, 390, 412, 413, 417, 494, 495, 551], "parse_auto_slim_config": [171, 542], "parse_cfg": 417, "parse_last_linear": 192, "parse_last_linear_tf": 192, "parse_saved_model": [133, 385], "parse_str2list": 154, "parse_to_prun": 192, "parse_to_prune_tf": 192, "parse_tune_config": 1, "parse_valid_pruner_typ": 183, "parsedecodebert": 209, "parsedecodecoco": 210, "parsedecodeimagenet": [221, 551], "parsedecodeimagenettransform": 221, "parsedecodevoctransform": 225, "parserfactori": 247, "part": [145, 171, 180, 433, 469, 473, 487, 490, 532, 537, 542, 545, 550], "parti": [230, 487, 489, 533, 544], "partial": [184, 480, 542, 544], "particip": 488, "particular": [492, 542, 547], "particularli": 480, "partit": [524, 542], "partner": 543, "parzen": 552, "pascal": 211, "paser_cfg": 145, "pass": [62, 133, 138, 140, 151, 161, 234, 262, 334, 385, 391, 396, 397, 411, 413, 431, 441, 464, 465, 476, 487, 489, 490, 493, 518, 523, 524, 530, 535, 536, 542, 544, 546, 550], "past": [476, 487, 493, 547], "pat": 543, "patch": 427, "patch_hqq_moduil": 427, "path": [90, 125, 133, 141, 145, 160, 173, 188, 192, 209, 210, 211, 225, 235, 243, 261, 262, 278, 283, 385, 390, 398, 405, 412, 413, 415, 416, 417, 431, 442, 457, 458, 461, 465, 471, 475, 476, 477, 483, 490, 493, 524, 530, 535, 536, 537, 538, 541, 547, 551], "path_to_sav": 448, "pathlik": [140, 396], "pattern": [43, 44, 46, 63, 81, 92, 93, 94, 116, 121, 145, 169, 170, 173, 174, 180, 181, 182, 183, 185, 187, 189, 195, 211, 278, 315, 316, 318, 335, 352, 357, 358, 359, 371, 376, 406, 470, 475, 479, 482, 493, 520, 528, 531, 536, 541, 550, 552, 553], "pattern_analyz": 172, "pattern_detector": 136, "pattern_factori": 406, "pattern_lock": [183, 195], "pattern_lst": [143, 417], "pattern_pair": 406, "pattern_to_intern": 278, "pattern_to_path": 278, "patternmha": 177, "patternpair": 406, "pb": [151, 195, 235, 243, 262, 390, 480, 518, 524, 536, 538, 553], "pbound": 266, "pc": 489, "pdf": 3, "peak": [245, 482, 540], "pegasu": 553, "peleenet": 553, "penal": 542, "penalti": [227, 228, 535], "pend": 527, "pentium": 533, "peopl": [487, 544], "pep": [281, 520], "per": [29, 30, 31, 149, 151, 195, 398, 413, 433, 437, 460, 471, 472, 474, 476, 482, 493, 495, 521, 539, 542, 546, 547, 553], "per_channel": [98, 409, 439, 494, 495, 528, 544], "per_channel_symmetr": 495, "per_tensor": [292, 293, 294, 297, 298, 299, 303, 409, 439, 478, 494, 495, 528, 544], "per_tensor_symmetr": 495, "percdamp": [31, 439, 476, 547], "percent": 31, "percentag": [232, 476, 519, 547], "percentil": [3, 31, 125, 283, 303, 433, 519], "percentilecalibr": 3, "perceptron": 542, "perchannel": 31, "perform": [81, 125, 151, 189, 195, 209, 221, 234, 245, 262, 267, 271, 283, 284, 352, 413, 470, 471, 473, 475, 476, 477, 478, 480, 481, 482, 483, 487, 489, 490, 492, 493, 494, 518, 522, 523, 525, 526, 529, 531, 532, 535, 536, 537, 538, 540, 541, 542, 543, 544, 545, 546, 547, 550, 552, 553], "performance_onli": [32, 33, 34, 92, 116, 121, 132, 289, 306, 357, 371, 376, 384, 536], "perm": [225, 551], "perman": [171, 488, 542], "permiss": 488, "permut": [225, 551], "perplex": 553, "persist": 538, "person": [391, 465, 488, 543], "perspect": 552, "phase": [146, 447, 480, 487, 536, 542, 544, 546, 552], "phi": 533, "philip": 542, "philosophi": [475, 480, 544], "physic": [151, 154, 488, 518], "physical_cpu": 154, "pickl": [138, 140, 396, 397], "pickle_load_arg": [140, 396], "pickle_modul": [140, 170, 396], "pickle_protocol": 170, "pickleerror": [138, 397], "pickler": [138, 397], "pickletool": [138, 397], "picklingerror": [138, 397], "piec": [224, 227, 476, 487, 535, 547], "pil": [225, 551], "pile": [418, 451], "pin": 521, "pin_memori": [200, 202, 205, 206, 208, 387, 521], "ping_memori": [536, 544], "pip": [492, 524, 527, 529, 532, 548], "pipe": 520, "pipelin": [153, 162, 489, 523, 536, 541], "piqa": 553, "pixel": 551, "pkl": 465, "pl": 227, "place": [412, 413, 433, 442, 477, 523, 532, 542, 552], "placehold": [42, 207, 314, 387, 409, 520], "placeholder_dtyp": 173, "placeholder_shap": 173, "plai": [236, 390, 476, 487, 543, 547, 550], "plan": [477, 531], "platform": [465, 482, 487, 531, 543, 544], "platinum": 553, "pleas": [29, 135, 149, 169, 177, 178, 179, 187, 188, 195, 209, 210, 211, 214, 234, 262, 281, 413, 420, 469, 471, 473, 474, 475, 476, 477, 478, 479, 487, 490, 491, 492, 493, 518, 519, 523, 524, 526, 532, 534, 535, 537, 542, 544, 546, 547, 548, 549, 550, 552], "plu": 537, "plug": 543, "png": 211, "point": [30, 31, 221, 231, 232, 266, 425, 433, 465, 470, 471, 472, 473, 474, 475, 476, 479, 487, 535, 539, 544, 547, 550, 551, 552], "pointwise_constraint": 298, "pointwise_initi": 298, "pointwise_regular": 298, "polici": [263, 265, 271, 481, 488, 492, 554], "polit": 488, "pollut": 520, "pont": 532, "pool": 16, "pool2d": 295, "pool_siz": 297, "pooloper": 23, "poor": 477, "popen": 520, "popular": [226, 467, 469, 477, 481, 487, 492, 493, 494, 519, 525, 526, 534, 536, 542, 544, 547, 552], "popularli": 535, "port": [52, 53, 55, 324, 325, 327], "portabl": [138, 397], "portion": 209, "pose": [472, 539, 545], "posit": [225, 442, 488, 535], "possibl": [140, 396, 406, 471, 541, 542, 545, 546, 552], "post": [29, 82, 83, 149, 187, 195, 198, 199, 262, 353, 354, 413, 420, 439, 472, 474, 475, 476, 477, 479, 481, 487, 488, 492, 493, 494, 523, 524, 526, 531, 532, 539, 542, 543, 545, 547, 550, 552], "post_batch": 1, "post_hostconst_convert": [80, 351], "post_node_nam": [62, 334], "post_quantized_op_cs": [80, 351], "post_training_auto_qu": 552, "post_training_dynamic_qu": [536, 552], "post_training_static_qu": [536, 552], "postcompressionutil": 174, "postcseoptim": [83, 354], "posterior": 552, "postfix": [74, 75, 346], "posthostconstconvert": [82, 353], "postposttrainingquantconfig": 546, "postprocess": [195, 222, 225, 234, 262, 454, 493, 536, 551], "postprocess_cfg": 454, "postprocess_cl": [223, 536], "postprocess_model": 447, "posttrainingquantconfig": [195, 262, 490, 495, 521, 526, 535, 536, 538, 544, 545, 546, 547, 549, 550, 552], "power": [471, 472, 480, 536, 539, 543], "pp": 542, "pr": [489, 521, 535, 548], "practic": [472, 539], "pre": [64, 101, 141, 173, 198, 199, 209, 235, 262, 336, 398, 439, 448, 475, 476, 481, 487, 520, 523, 536, 542, 543, 544, 547, 552], "pre_batch": 1, "pre_node_nam": [62, 334], "pre_optim": [61, 333], "pre_post_process_quant": [195, 544], "pre_process": 524, "preced": [227, 487, 550, 552], "precis": [134, 195, 198, 199, 232, 234, 235, 245, 264, 267, 278, 289, 399, 400, 401, 406, 437, 439, 465, 469, 471, 472, 475, 476, 477, 481, 487, 492, 493, 494, 499, 518, 519, 523, 524, 528, 529, 531, 539, 543, 544, 547, 550, 552], "pred": [133, 234, 385, 535], "pred_list": 234, "pred_text": 225, "predefin": 481, "predict": [133, 225, 227, 231, 232, 234, 262, 385, 476, 487, 535, 547, 550, 551], "prefer": [151, 262, 476, 487, 542, 547], "prefix": [133, 140, 141, 144, 145, 151, 154, 385, 396, 398, 433, 471], "preoptim": [64, 336], "prepar": [1, 31, 145, 392, 412, 415, 431, 437, 442, 447, 470, 471, 472, 474, 475, 476, 477, 480, 483, 487, 490, 492, 524, 529, 542, 544], "prepare_compress": [195, 448, 490, 523, 536, 541, 542, 544], "prepare_dataload": 1, "prepare_input": 31, "prepare_model": 1, "prepare_model_data": 1, "prepare_prun": [170, 542], "prepared_model": [470, 474, 475, 476, 483, 529], "preprint": [472, 476, 487, 519, 539, 542, 547, 550], "preprocess": [145, 195, 209, 225, 280, 433, 454, 524, 551], "preprocess_user_cfg": 280, "present": [52, 53, 55, 324, 325, 327, 487, 543, 550], "preserv": [169, 472, 476, 519, 539, 542, 547], "pretrain": [420, 461], "pretrained_model_name_or_path": [139, 141, 398, 447], "prettyt": 465, "preval": [476, 487, 547], "previou": [192, 469, 477, 487, 494, 495, 536, 542, 548, 550, 552, 553], "previous": 521, "primari": [481, 519, 552], "primit": [140, 396], "print": [62, 135, 173, 234, 281, 334, 420, 425, 465, 482, 487, 524, 535, 536, 542, 550, 552], "print_iter": 173, "print_op_list": 465, "print_tabl": 465, "printer": [161, 465], "prior": [1, 73, 345, 552], "prioriti": [152, 443, 445, 520], "privat": 488, "prob": 490, "probabl": [3, 195, 460, 476, 487, 547], "problem": [138, 209, 234, 397, 473, 535, 537], "proce": [181, 182, 187], "procedur": [542, 552], "proceed": [487, 550], "process": [101, 125, 135, 151, 153, 159, 161, 175, 180, 181, 182, 188, 190, 192, 195, 198, 199, 209, 210, 211, 221, 225, 235, 262, 263, 265, 266, 283, 412, 413, 447, 448, 464, 465, 470, 471, 472, 475, 476, 479, 480, 481, 483, 487, 493, 494, 495, 519, 521, 523, 524, 526, 536, 539, 541, 542, 544, 545, 547, 550, 551], "process_and_check_config": 192, "process_config": 192, "process_weight_config": 192, "process_yaml_config": 192, "processor": [161, 439, 447, 473, 483, 487, 492, 534, 537, 543, 544, 546], "processor_typ": [439, 483], "processortyp": [161, 439, 447], "product": [169, 473, 487, 531, 537, 543, 544, 549, 552], "profession": 488, "profil": [151, 195, 226], "profilerfactori": [254, 255, 259], "profilingpars": 250, "profilingresult": 251, "program": [475, 492, 524, 533], "progress": [30, 183, 211, 542, 544], "project": [225, 468, 488, 489, 543, 549, 552, 554], "promis": [471, 523, 536, 542], "promot": [472, 476, 539], "prompt": 524, "prone": 542, "propag": [1, 85, 355], "properti": [209, 280, 533], "proport": 234, "propos": [473, 476, 487, 493, 537, 547, 550], "protect": [476, 547], "protected_nod": [65, 337], "proto": [221, 225, 551], "protobuf": [90, 243, 390], "prototyp": 490, "prove": [476, 487, 519, 547, 550], "provid": [29, 30, 31, 87, 90, 95, 173, 198, 199, 225, 230, 235, 262, 360, 409, 413, 448, 459, 461, 469, 471, 473, 474, 475, 476, 477, 478, 479, 480, 481, 482, 483, 484, 487, 492, 493, 494, 495, 518, 521, 523, 524, 525, 529, 531, 532, 534, 535, 536, 537, 538, 542, 544, 547, 550, 552, 553], "proxi": 490, "prune": [162, 169, 170, 171, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 189, 190, 191, 192, 195, 465, 469, 492, 524, 525, 528, 529, 531, 541, 543], "prune_conf": 536, "prune_config": 192, "pruner": [536, 542], "pruner2": 542, "pruner_class": 187, "pruner_info": 188, "pruners_info": 192, "pruning_class": 188, "pruning_config": [195, 536, 542], "pruning_end": 542, "pruning_frequ": [180, 195, 536, 542], "pruning_func": 536, "pruning_op_typ": [195, 536, 542], "pruning_pattern": 542, "pruning_scop": [195, 536, 542], "pruning_start": 542, "pruning_typ": [195, 536, 542], "pruningcallback": 162, "pruningconfig": 448, "pruningcriterion": [169, 191], "pruningschedul": 190, "pseudo": [198, 199, 262, 448, 476, 547], "pt": [140, 396, 464, 476, 492, 529, 532, 538, 543, 544, 546, 547], "pt2e": [405, 407, 409, 435, 437, 441], "pt2e_dynamic_quant_entri": 437, "pt2e_export": 434, "pt2e_quant": 394, "pt2e_static_quant_entri": 437, "pt_fp32_model": 458, "pt_int8_model": 458, "ptq": [195, 262, 474, 475, 479, 480, 490, 524, 531, 536, 544, 550, 552], "public": [281, 488], "publish": [473, 488, 533, 534, 537, 550], "pull": [52, 53, 55, 324, 325, 327], "punct_nondigit_r": 227, "punctuat": [224, 227, 232], "pure": 542, "purif": 543, "purpos": [473, 474, 475, 476, 478, 528, 537, 544], "push": [472, 476, 487, 489, 539, 542, 547, 550], "put": [140, 211, 396], "py": [3, 133, 135, 151, 154, 180, 195, 228, 230, 231, 232, 281, 385, 443, 478, 482, 483, 490, 493, 520, 524, 532, 536, 544, 548], "pycocotool": [230, 527], "pyhessian": 135, "pylanc": 520, "pyobject": 527, "pypi": 532, "pytest": 489, "python": [3, 60, 133, 138, 140, 161, 211, 226, 281, 332, 385, 396, 397, 443, 465, 467, 483, 490, 492, 520, 524, 527, 532, 536, 542, 543, 551], "python3": 527, "pythonmultiheadattentionprun": 184, "pytorch": [163, 165, 166, 170, 173, 176, 179, 180, 183, 188, 194, 195, 208, 209, 211, 214, 218, 225, 234, 235, 244, 262, 272, 392, 394, 435, 436, 437, 438, 439, 440, 441, 442, 444, 445, 446, 447, 458, 459, 465, 472, 477, 489, 490, 492, 493, 494, 495, 500, 519, 520, 521, 523, 525, 528, 529, 531, 532, 534, 536, 537, 538, 539, 542, 543, 547, 548, 550, 552], "pytorch_cpu": 495, "pytorch_fx": [211, 218, 536], "pytorch_ipex": [211, 218, 536], "pytorch_prun": 188, "pytorchalignimagechannel": 225, "pytorchbasemodel": 244, "pytorchbasepattern": [175, 189], "pytorchbaseprun": 180, "pytorchbasicprun": 181, "pytorchbertdataset": 209, "pytorchblockmaskprun": 182, "pytorchcifar10": 211, "pytorchcifar100": 211, "pytorchcriterion": 163, "pytorchcropresizetransform": 225, "pytorchcrossentropyloss": 163, "pytorchdataload": 206, "pytorchdataset": 211, "pytorchdynamo": 477, "pytorchfashionmnist": 211, "pytorchfilt": 218, "pytorchfxmodel": 244, "pytorchimagenetraw": 214, "pytorchintermediatelayersknowledgedistillationloss": 163, "pytorchintermediatelayersknowledgedistillationlosswrapp": 163, "pytorchknowledgedistillationloss": [163, 536], "pytorchknowledgedistillationlosswrapp": 163, "pytorchloss": 234, "pytorchmetr": 234, "pytorchmnist": 211, "pytorchmodel": 244, "pytorchmxnettransform": 225, "pytorchmxnetwrapdataset": 211, "pytorchmxnetwrapfunct": [211, 225], "pytorchnormalizetransform": 225, "pytorchoptim": 165, "pytorchpatternlockprun": 185, "pytorchpatternninm": 178, "pytorchpatternnxm": 179, "pytorchprogressiveprun": 186, "pytorchretrainfreeprun": 187, "pytorchselfknowledgedistillationloss": 163, "pytorchselfknowledgedistillationlosswrapp": 163, "pytorchsgd": 165, "pytorchtransform": 225, "pytorchtranspos": 225, "q": [30, 31, 92, 94, 116, 357, 359, 371, 470, 475, 477, 487, 547, 550], "q_conf": 523, "q_config": [28, 145, 292, 293, 294, 297, 298, 458, 493], "q_dataload": [198, 199, 263, 264, 266, 267, 271, 273, 274, 530, 552], "q_func": [198, 199, 263, 264, 266, 267, 271, 273, 274, 413, 493, 494, 536, 552], "q_hook": [198, 199, 263, 264, 266, 267, 271, 273, 274], "q_max": [487, 550], "q_min": [487, 550], "q_model": [135, 139, 195, 262, 301, 305, 417, 470, 474, 475, 479, 481, 490, 521, 524, 526, 530, 535, 536, 538, 544, 545, 546, 547], "q_tensor": 433, "q_weight": [31, 423], "q_x": [487, 550], "qa": [231, 232, 492], "qactivationoper": 5, "qargmaxoper": 6, "qas_id": 225, "qat": [97, 144, 195, 243, 492, 523, 524, 529, 531, 536, 544], "qat_clone_funct": 101, "qat_op_name_dict": 195, "qattent": 7, "qattentionoper": 7, "qavgpool2d": 297, "qbinari": 8, "qbinaryoper": 8, "qconcat": 9, "qconcatoper": 9, "qconfig": [1, 145, 417, 464, 471, 476, 492, 547], "qconfig_file_path": 160, "qconv2d": 292, "qconvoper": 10, "qd": 475, "qdens": 293, "qdepthwiseconv2d": 294, "qdirect": 11, "qdirectoper": 11, "qdq": [29, 72, 97, 98, 127, 145, 195, 288, 344, 362, 433, 456, 457, 458, 479, 493, 526, 531, 544, 550], "qdq_enabl": [33, 306], "qdq_op_fp32_bia": 195, "qdq_op_fp32_bias_qdq": 195, "qdq_op_int32_bia": 195, "qdq_quantiz": 412, "qdq_tensor": 31, "qdq_weight_actor": 433, "qdq_weight_asym": 433, "qdq_weight_sym": 433, "qdqlayer": [398, 429], "qembedlayernorm": 12, "qembedlayernormalizationoper": 12, "qgather": 13, "qgatheroper": 13, "qgemm": 15, "qgemmoper": 15, "qglobalaveragepooloper": 14, "qintegerop": [531, 544], "qkv": 184, "qkv_modul": 184, "qkv_name": 184, "qlinear": [195, 211, 218, 234, 456, 493], "qlinear2qdq": 455, "qlinearaveragepool": 23, "qlinearconv": 10, "qlinearglobalaveragepool": 14, "qlinearmatmul": 18, "qlinearop": [456, 531, 544, 553], "qlora": [476, 487, 547], "qmatmuloper": 18, "qmax": 145, "qmaxpool": 19, "qmaxpool2d": 297, "qmaxpooloper": 19, "qmin": 145, "qmodel": [135, 478, 480], "qnli": [209, 535, 553], "qop_registri": 21, "qoper": [5, 21, 195, 526], "qpad": 22, "qpadoper": 22, "qpooloper": 23, "qqp": [209, 535, 553], "qresiz": 25, "qresizeoper": 25, "qscheme": 495, "qseparableconv2d": 298, "qsplit": 26, "qsplitoper": 26, "qsym_model": 1, "qt_config": [33, 306], "qtensor": [423, 424], "qtensor_to_tensor": 1, "qtensorconfig": 422, "qtensormetainfo": 426, "qtype": [29, 30, 493], "quadrat": [439, 476], "quala": 543, "qualiti": [227, 520], "quant": [31, 133, 145, 195, 278, 285, 287, 288, 289, 299, 303, 413, 416, 433, 438, 439, 476, 487, 490, 520, 534, 536, 544], "quant_axi": [292, 293, 294, 297, 298], "quant_block_list": [418, 439], "quant_config": [288, 289, 301, 305, 391, 392, 403, 405, 412, 416, 418, 419, 420, 427, 430, 432, 442, 447, 470, 472, 474, 475, 476, 477, 478, 479, 480, 483, 529, 539], "quant_dequant_data": 29, "quant_dequant_w_v1": 413, "quant_dequant_x_v1": 413, "quant_format": [195, 458, 526], "quant_level": [195, 547, 550, 552], "quant_lm_head": [420, 439, 451, 476], "quant_max": 495, "quant_min": 495, "quant_mod": [32, 278, 289, 292, 293, 294, 297, 298, 494, 495], "quant_mode_from_pattern": 278, "quant_narrow_rang": [292, 293, 294, 297, 298], "quant_opt": 280, "quant_round_mod": [292, 293, 294, 297, 298], "quant_scal": [439, 476], "quant_statu": [292, 293, 294, 297, 298], "quant_t": [292, 293, 294, 297, 298], "quant_tensor": [31, 433], "quant_typ": 280, "quant_weight_w_scal": 433, "quant_zero": [439, 476], "quantformat": 30, "quantif": [474, 476, 479, 547, 550], "quantil": [433, 552], "quantit": 476, "quantiz": [1, 3, 4, 29, 30, 31, 33, 34, 73, 77, 79, 81, 84, 92, 97, 98, 99, 100, 101, 102, 103, 104, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 134, 135, 137, 141, 142, 145, 149, 151, 153, 157, 159, 161, 162, 195, 198, 199, 221, 226, 267, 269, 271, 280, 283, 284, 286, 288, 289, 290, 291, 292, 293, 294, 295, 297, 298, 392, 395, 398, 402, 403, 404, 405, 408, 409, 411, 412, 413, 415, 416, 417, 418, 419, 420, 422, 423, 424, 425, 426, 429, 430, 431, 432, 433, 434, 435, 436, 447, 448, 451, 452, 458, 460, 461, 464, 465, 469, 473, 479, 481, 484, 493, 499, 500, 520, 521, 524, 525, 528, 529, 530, 531, 535, 538, 541, 543, 548, 551, 552], "quantizable_nod": 1, "quantizable_op": [145, 413, 417], "quantization_aware_training_conf": 536, "quantization_cfg": 493, "quantization_config": 450, "quantization_param": 28, "quantizationawaretrainingcallback": 162, "quantizationawaretrainingconfig": [195, 448, 490, 523, 526, 536, 544, 546, 552], "quantizationmethod": 451, "quantizationmod": 30, "quantizationspec": 409, "quantize_4bit": 433, "quantize_config": [99, 494], "quantize_data": 30, "quantize_data_per_channel": 30, "quantize_data_with_scale_zero": 30, "quantize_elemwise_op": 404, "quantize_graph": [96, 361], "quantize_graph_bas": [97, 362], "quantize_graph_bn": [97, 362], "quantize_graph_common": [96, 361], "quantize_graph_concatv2": [97, 362], "quantize_graph_conv": [97, 362], "quantize_graph_for_intel_cpu": [97, 362], "quantize_graph_matmul": [97, 362], "quantize_graph_pool": [97, 362], "quantize_help": 99, "quantize_lay": 99, "quantize_layer_add": 102, "quantize_layer_bas": 102, "quantize_layer_bn": 102, "quantize_model": [305, 478, 479, 480, 487], "quantize_model_with_single_config": 305, "quantize_mx_op": 404, "quantize_nod": 458, "quantize_nparrai": 30, "quantize_per_channel": [487, 550], "quantize_per_tensor_absmax": [487, 550], "quantize_rang": 30, "quantize_recip": 101, "quantize_sym_model": 1, "quantize_wrapp": 99, "quantizeconfig": [100, 101], "quantized_data": 30, "quantized_dict": 135, "quantized_model": [476, 483, 529], "quantized_nod": [92, 357], "quantized_value_typ": 30, "quantizedconcatv2": [109, 119, 364, 374], "quantizedconv": [76, 77, 347, 348], "quantizeddeconv": [76, 347], "quantizediniti": 30, "quantizedinput": [221, 551], "quantizedmatmul": [78, 79, 349, 350], "quantizedmatmulwithbiasanddequant": [79, 350], "quantizedrnnconvert": 84, "quantizedvalu": 30, "quantizedvaluetyp": 30, "quantizegraph": [117, 372], "quantizegraphbas": [117, 372], "quantizegraphforintel": [121, 376], "quantizegraphhelp": [124, 379], "quantizelay": 105, "quantizelayeradd": 104, "quantizelayerbas": 105, "quantizelayerbatchnorm": 106, "quantizelinear": 30, "quantizenodebas": [117, 372], "quantizer_cl": 447, "quantizev2": [83, 354], "quantizewrapp": [101, 107], "quantizewrapperbas": 107, "quantiztaion": [195, 417], "quantopt": 280, "quanttyp": [30, 280], "queri": [1, 32, 133, 145, 173, 184, 195, 288, 289, 417, 447, 487, 494, 495, 544], "query_framework_cap": 494, "query_fused_pattern": 493, "query_fw_cap": [493, 495], "query_layer_nam": 184, "query_quantizable_nod": 1, "querybackendcap": [493, 494], "question": [225, 231, 232, 487, 488, 489, 492, 493, 532, 542, 550, 551, 553], "question_text": 225, "quick": [469, 483, 528, 537, 542], "quickli": [481, 534, 552], "quint8": [30, 413], "quit": 542, "qweight_config_path": 547, "qwen2": [492, 543], "r": [30, 128, 150, 380, 474, 475, 476, 478, 480, 482, 487, 532, 544, 553], "r1": [133, 385], "r34": 490, "race": 488, "rais": [52, 53, 55, 90, 138, 140, 145, 170, 176, 183, 192, 230, 235, 281, 324, 325, 327, 396, 397, 413, 433, 435, 447, 492, 520, 542, 543], "ram": [140, 396, 476, 483], "ran": 162, "rand": [418, 439, 476, 487, 550], "randn": [195, 526], "random": [41, 133, 161, 195, 221, 225, 266, 270, 313, 391, 418, 465, 476, 536, 542, 551], "random_crop": [221, 551], "random_flip_left_right": [221, 551], "random_se": [195, 266, 536], "randomcrop": 551, "randomcroptftransform": 225, "randomcroptransform": 225, "randomhorizontalflip": [225, 536, 551], "randomli": [225, 266, 487, 550, 551, 552], "randomresizedcrop": [536, 551], "randomresizedcropmxnettransform": 225, "randomresizedcroppytorchtransform": 225, "randomresizedcroptftransform": 225, "randomresizedcroptransform": 225, "randomst": 266, "randomtunestrategi": 273, "randomverticalflip": [225, 551], "rang": [212, 213, 225, 281, 387, 433, 448, 461, 470, 472, 473, 476, 477, 480, 482, 487, 492, 493, 495, 519, 523, 524, 536, 539, 541, 542, 544, 547, 550, 551], "rank": 524, "rapid": [532, 534], "rate": [476, 487, 536, 542, 544], "rather": [476, 530, 547], "ratio": [31, 128, 150, 175, 180, 192, 195, 221, 225, 380, 534, 536, 542, 551, 553], "ratiospars": 553, "raw": [30, 151, 210, 214, 217, 271, 412, 415, 431, 437, 535, 552], "raw_cmd": [151, 154], "raw_func": 445, "raw_imag": 211, "rawgptquant": 420, "rb": [140, 396], "rcnn": 526, "re": 547, "reach": [153, 175, 190, 195, 489, 521, 542, 552], "read": [90, 133, 140, 214, 225, 385, 396, 546, 549], "read_graph": [133, 385], "read_squad_exampl": 225, "read_tensorflow_node_attr": 90, "readabl": [154, 520], "readi": 542, "readlin": [140, 396], "readm": 524, "real": [30, 212, 387, 487, 494, 519, 524, 543, 544], "realdiv": [51, 54, 323, 326], "realiz": [524, 540, 546, 549], "rearrang": [31, 187, 476, 542, 547], "reason": [476, 487, 488, 494, 521, 547, 552], "rebuild": [133, 385], "recal": [232, 234], "receiv": 549, "recent": [473, 536, 537], "recip": [33, 173, 195, 306, 472, 481, 492, 529, 536, 539, 545, 547, 550, 552], "recipe_sampl": 173, "recipesearch": 173, "recogn": [227, 447, 552], "recognit": [473, 524, 526, 542], "recognitionimagenet": 553, "recommend": [234, 445, 471, 473, 483, 492, 493, 528, 529, 542, 552], "recommendation_system": 195, "reconstruct": [133, 385, 543], "reconstruct_saved_model": [133, 385], "record": [135, 145, 163, 166, 209, 210, 211, 217, 433, 465, 481, 547, 549, 552], "record_max_info": [303, 413], "record_output": 166, "recov": [29, 411, 413, 433, 464, 465, 493, 523], "recover_config": 34, "recover_forward": 433, "recover_model_from_json": [411, 464], "rectangl": [476, 545], "recurs": [194, 465], "recursivescriptmodul": 415, "red": 553, "redpajama": [474, 550], "reduc": [16, 195, 439, 473, 474, 475, 476, 479, 480, 487, 493, 519, 523, 536, 537, 542, 543, 544, 545, 546, 547, 550, 552], "reduce_rang": [2, 28, 29, 195, 495], "reducemax": 24, "reducemin": 24, "reduceminmaxoper": 24, "reduceoper": 24, "reduct": [542, 545], "redund": [76, 78, 347, 349, 447], "ref": [3, 133, 385], "refer": [29, 135, 149, 169, 177, 178, 179, 187, 188, 192, 195, 209, 227, 228, 234, 262, 281, 413, 420, 439, 471, 473, 474, 475, 477, 478, 479, 480, 490, 492, 493, 494, 518, 521, 523, 524, 526, 530, 532, 533, 535, 536, 537, 540, 545, 548, 551, 552], "reference_corpu": 228, "refin": [443, 480, 530, 542], "reflect": [535, 551], "reg": [170, 181, 182, 187, 195], "reg_term": 189, "regard": [488, 546], "regardless": 488, "region": [474, 550], "regist": [3, 21, 138, 140, 146, 152, 163, 165, 169, 170, 175, 176, 180, 183, 188, 189, 190, 191, 211, 218, 225, 234, 245, 274, 280, 299, 391, 396, 397, 398, 413, 439, 443, 447, 493, 520, 524, 535, 536, 540, 550, 552], "register_acceler": 443, "register_algo": [391, 447, 520], "register_autotun": 413, "register_config": [152, 520], "register_criterion": [169, 191], "register_customer_metr": 234, "register_packag": [140, 396], "register_pattern": 175, "register_prun": [180, 188], "register_reg": 189, "register_schedul": 190, "register_supported_configs_for_fwk": 152, "register_weight_hook": 398, "registr": [146, 211, 218, 225], "registri": [152, 169, 175, 180, 188, 189, 190, 191, 443], "registry_criterion": 163, "regress": [209, 489], "regul": [181, 182, 187], "regular": [189, 227], "regulariz": 189, "reinstal": 527, "reject": 488, "rel": [195, 245, 536, 552, 553], "relat": [174, 189, 230, 280, 407, 410, 414, 424, 446, 454, 495, 529, 542, 547], "relationship": 195, "relative_loss": 153, "releas": [470, 475, 492, 529, 532, 554], "relev": [266, 494, 495, 520, 542], "reli": [477, 536, 550], "religion": 488, "reload": 160, "relu": [59, 63, 94, 331, 335, 359, 490, 528, 550], "relu6": [59, 331, 528], "remain": [431, 441], "remaind": 519, "remap": [55, 140, 327, 396], "remov": [5, 30, 36, 42, 45, 59, 65, 68, 69, 70, 81, 83, 125, 171, 184, 232, 283, 308, 314, 317, 331, 337, 340, 341, 342, 352, 354, 447, 488, 536, 542], "removableactivationoper": 5, "remove_init_from_model_input": 30, "remove_training_nod": [61, 333], "removetrainingnodesoptim": [65, 337], "renam": [66, 338, 477, 548], "rename_batch_norm": [61, 333], "renamebatchnormoptim": [66, 338], "repeat": 552, "repercuss": 488, "replac": [3, 141, 145, 232, 398, 406, 413, 427, 433, 470, 472, 475, 520, 524, 536, 539, 548], "replace_forward": 433, "replace_pattern": 406, "replacement_fn": 427, "replic": 552, "replica": 552, "repo": [209, 468, 489, 525, 554], "repo_id": [141, 398, 447], "repo_typ": [141, 398, 447], "report": [488, 489, 492, 549], "repositori": 489, "repr": 451, "repres": [30, 152, 153, 156, 157, 175, 179, 180, 188, 189, 192, 211, 216, 230, 232, 234, 406, 426, 475, 476, 480, 487, 488, 495, 519, 526, 542, 544, 545, 552], "represent": [30, 138, 397, 472, 476, 487, 488, 490, 519, 523, 539, 542, 544], "reproduc": 418, "requant": [77, 79, 348, 350], "requantize_cfg": 145, "request": [475, 492, 544], "requir": [145, 195, 201, 243, 261, 390, 433, 471, 473, 475, 476, 480, 487, 490, 493, 494, 518, 519, 521, 523, 524, 527, 528, 536, 537, 538, 542, 544, 547, 548, 549, 550, 552], "requirements_pt": [527, 532], "requirements_tf": 532, "rerang": [132, 384], "rerange_quant": [132, 384], "rerange_quantized_concat": [130, 382], "rerangequantizedconcat": [132, 384], "rerewrit": [36, 308], "resblock": 195, "rescal": [221, 225, 551], "rescalekeraspretraintransform": 225, "rescaletftransform": 225, "rescaletransform": 225, "research": [477, 492, 533, 550, 553], "reserv": [198, 199], "reset": 535, "reset_none_to_default": 192, "reshap": [46, 52, 53, 58, 318, 324, 325, 330, 413, 487, 550], "reshape_in0_ndef": [52, 53, 324, 325], "reshape_in1_ndef": [52, 53, 324, 325], "reshape_in_channel_to_last": 413, "reshape_scale_as_input": 413, "reshape_scale_as_weight": 413, "reshuffl": 521, "resid": [140, 396], "resiz": [16, 209, 210, 221, 225, 551], "resize_method": 221, "resize_shap": 216, "resize_sid": [221, 551], "resizecropimagenet": [524, 551], "resizemxnettransform": 225, "resizeoper": 25, "resizepytorchtransform": 225, "resizetftransform": 225, "resizetransform": 225, "resizewithaspectratio": 221, "resizewithratio": [225, 551], "resnest50": 553, "resnet": [524, 553], "resnet101": 553, "resnet18": [471, 492, 537, 553], "resnet34": [490, 553], "resnet50": [195, 478, 492, 524, 526, 537, 542, 544, 549, 553], "resnet50_fp32_pretrained_model": 524, "resnet50_v1": [524, 536], "resnetv2": 553, "resnext101_32x8d": 553, "resolut": 519, "resolv": [490, 491], "resort": 536, "resourc": 552, "respect": [487, 488, 528, 542, 550], "respons": [249, 250, 253, 478, 544], "rest": [145, 433], "restor": [476, 547], "restrict": [55, 140, 195, 327, 396, 542, 549], "restructuredtext": 281, "result": [30, 133, 135, 145, 221, 225, 227, 230, 231, 232, 234, 262, 269, 385, 406, 408, 417, 448, 451, 464, 465, 469, 470, 471, 474, 476, 479, 481, 482, 487, 488, 492, 521, 524, 531, 533, 535, 536, 540, 542, 543, 544, 547, 549, 550, 551, 552, 553], "resum": [195, 198, 199, 263, 264, 266, 267, 271, 273, 274], "resume_from": [161, 195, 465], "retain": 519, "retrac": 546, "retrain": [187, 475, 523], "retrain_fre": [169, 183, 542], "retrainfreecriterion": 169, "retrainfreeprun": [187, 188], "retri": 413, "retriev": [152, 159, 207, 387, 406, 413, 542], "return": [1, 3, 31, 39, 52, 53, 55, 59, 90, 101, 133, 134, 135, 140, 144, 145, 146, 151, 152, 154, 160, 161, 163, 165, 170, 173, 175, 176, 180, 183, 188, 189, 190, 192, 194, 198, 199, 211, 218, 221, 225, 227, 228, 230, 231, 232, 234, 235, 239, 243, 245, 257, 261, 262, 266, 274, 278, 280, 281, 299, 301, 303, 305, 311, 324, 325, 327, 331, 385, 390, 391, 396, 398, 404, 406, 408, 409, 411, 412, 413, 415, 417, 418, 420, 425, 427, 431, 433, 435, 437, 438, 439, 441, 442, 445, 447, 448, 451, 454, 458, 464, 465, 473, 477, 478, 481, 487, 490, 494, 495, 521, 524, 535, 538, 540, 542, 544, 547, 550, 552], "return_int": [433, 547], "reus": 477, "revers": [133, 154], "reversed_numa_info": 154, "revert": [272, 280, 552], "reverted_data_typ": 280, "review": [488, 489, 492, 543], "revis": [141, 398, 431, 441, 447], "rewrit": [35, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 91, 92, 93, 94, 170, 307, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 406], "rgb": 221, "right": [140, 221, 230, 396, 487, 488, 489, 490, 550, 551], "rmax": [30, 480, 487, 544], "rmin": [30, 472, 480, 487, 539, 544], "rmse": [234, 535, 552], "rnn": 84, "rnn_convert": 80, "rnn_detail": 84, "roberta": [209, 553], "roc": 234, "role": [236, 390, 476, 487, 547, 550], "rollov": [200, 202, 205, 206, 208, 387, 521], "romanian": 542, "root": [173, 209, 210, 211, 214, 234, 524, 535, 536], "root_linear": 174, "root_rank": 524, "roughli": [476, 487, 547], "rouhani": [472, 539], "round": [31, 128, 150, 380, 404, 439, 470, 471, 476, 477, 487, 492, 543, 544, 547, 550], "round_": [487, 550], "round_method": 439, "round_multipli": 171, "roundingmod": 404, "row": [465, 487, 550], "rowi": 31, "rte": [209, 535, 553], "rtn": [31, 145, 303, 392, 428, 437, 438, 439, 477, 483, 487, 520, 545, 547], "rtn_algo_entri": 520, "rtn_arg": [476, 545, 547], "rtn_entri": 437, "rtn_g32asym": 547, "rtn_quantiz": 31, "rtnconfig": [437, 438, 439, 447, 451, 476, 477, 481, 529], "rtnquantiz": 430, "rtnw4g32asym": 553, "rtnw4g32sym": 553, "rule": [480, 542], "run": [1, 125, 133, 140, 151, 180, 192, 195, 198, 199, 208, 224, 235, 262, 266, 283, 385, 396, 413, 448, 471, 473, 476, 477, 480, 482, 483, 487, 492, 493, 518, 524, 527, 528, 536, 543, 544, 547, 548, 549, 552], "run_arg": [438, 442, 477], "run_cmd": 552, "run_fn": [412, 413, 438, 442, 474, 475, 476, 477], "run_forward": 1, "run_inst": 151, "run_multi_instance_command": 154, "runtim": [470, 487, 489, 492, 493, 494, 496, 521, 525, 528, 531, 537, 539, 547, 552], "rw": 553, "s1": 552, "s2": 552, "s3": 552, "s4": 552, "s5": 552, "s6": 552, "s7": 552, "s8": [292, 293, 294, 297, 298, 458], "sa_optim": 167, "sacrif": [472, 539, 543], "safe": 489, "safetensor": 492, "salient": [31, 476, 542, 547], "same": [68, 126, 133, 153, 187, 195, 209, 225, 230, 286, 340, 385, 413, 465, 471, 472, 476, 481, 482, 487, 493, 495, 518, 521, 524, 528, 536, 539, 542, 544, 547, 550, 551, 552], "sampl": [31, 62, 145, 153, 195, 203, 207, 209, 210, 211, 221, 225, 234, 266, 334, 387, 413, 418, 476, 480, 481, 482, 487, 521, 525, 531, 544, 547, 550, 551, 552, 553], "sampler": [153, 200, 202, 205, 206, 208, 277, 387, 418, 439, 476, 481, 521, 524], "sampling_s": 536, "samsum": 553, "sapphir": [532, 534], "satisfi": [208, 532], "satur": 551, "save": [90, 133, 139, 140, 160, 170, 195, 211, 243, 262, 385, 390, 396, 398, 408, 411, 415, 431, 442, 448, 452, 457, 458, 461, 465, 471, 477, 478, 487, 490, 492, 493, 530, 536, 537, 538, 541, 544, 545, 547, 550], "save_config_map": 160, "save_for_huggingface_upstream": [461, 536], "save_load": [158, 407, 410, 414, 428], "save_path": [457, 458, 493, 538], "save_protobuf": 90, "save_q_input": 413, "save_to_disk": 493, "saved_dir": [461, 547], "saved_model": [133, 385, 480, 545], "saved_model_sess": [243, 390], "saved_model_tag": [243, 390], "saved_path": 398, "saved_result": [408, 415, 431, 441, 476, 477, 538, 547], "savedmodel": [235, 243, 262, 390], "scalabl": [473, 480, 487, 492, 532, 534, 537, 543, 544, 546], "scalar": [198, 199, 235, 262, 448, 535, 544, 552], "scale": [3, 30, 31, 85, 126, 128, 142, 145, 149, 150, 221, 225, 286, 292, 293, 294, 297, 298, 355, 380, 413, 422, 425, 426, 429, 433, 470, 471, 472, 474, 475, 476, 480, 487, 539, 544, 547, 549, 550, 551, 552], "scale_bit": 404, "scale_c": [128, 150, 380], "scale_dtyp": [418, 429, 439, 451, 461, 476, 547], "scale_info": 465, "scale_method": [439, 471], "scale_nam": 30, "scale_param": 439, "scale_propag": [80, 351], "scale_quant_group_s": [439, 476], "scale_shar": [413, 439], "scale_valu": 30, "scalepropagationtransform": [85, 355], "scaler": 285, "scales_per_op": [126, 286, 303], "scan": [489, 492], "scenario": [476, 477, 487, 493, 518, 536, 542, 547], "scene": 542, "schedul": [170, 180, 181, 182, 187, 189, 195, 476, 536, 541], "schema": [89, 433], "scheme": [29, 30, 31, 142, 145, 413, 417, 429, 433, 493, 494, 495, 521, 528, 547, 552], "scienc": 532, "scipi": 266, "scope": [133, 385, 477, 489, 494, 536], "score": [169, 175, 180, 184, 191, 195, 227, 228, 230, 231, 232, 234, 269, 454, 490, 535, 540, 542, 549, 552], "script": [154, 173, 227, 228, 231, 232, 489, 492, 524, 531, 543], "seamlessli": [472, 539, 542, 552], "search": [133, 173, 187, 195, 198, 199, 227, 266, 406, 420, 433, 465, 469, 476, 477, 479, 492, 520, 531, 535, 542, 543, 547, 550, 552], "search_algorithm": 195, "search_clip": 433, "search_pattern": 406, "search_spac": 195, "searcher": [173, 195], "searching_result": 173, "sec": [482, 553], "second": [49, 140, 174, 195, 209, 267, 321, 396, 465, 476, 483, 487, 536, 547, 550, 552], "section": [281, 495, 520, 523, 542, 547], "secur": [138, 397, 492, 543, 554], "sed": 548, "see": [138, 225, 227, 397, 471, 476, 487, 488, 489, 490, 491, 520, 533, 536, 547, 550, 552], "seed": [133, 161, 195, 391, 418, 439, 465, 476, 536], "seek": [140, 396, 547], "seem": 520, "seen": [465, 493], "segment": [209, 228, 230, 489], "segment_id": [225, 536], "select": [189, 192, 195, 209, 433, 437, 443, 461, 471, 476, 487, 490, 519, 531, 532, 542, 544, 547, 552], "self": [48, 145, 173, 195, 245, 320, 433, 477, 493, 494, 521, 531, 535, 549, 552], "selfknowledg": 163, "selfknowledgedistillationloss": 163, "selfknowledgedistillationlossconfig": [195, 536], "selfmhasearch": 173, "semant": [493, 528], "send": [489, 494], "senior": 519, "sensit": [169, 531, 542], "sensitivitybalanc": 553, "sentenc": 520, "sep": [492, 543], "separ": [298, 418, 488, 520, 530, 532, 533, 541], "separable_conv2d": 295, "separableconv2d": 298, "seq_len": 451, "seq_length": 209, "seqlen": [418, 439, 476], "seqtyp": 90, "sequenc": [48, 90, 174, 177, 178, 195, 209, 224, 225, 228, 232, 320, 418, 476, 487, 493, 528, 542, 547, 551], "sequencediagram": [494, 495], "sequenti": [153, 207, 263, 265, 387, 391, 420, 481, 552], "sequentialsampl": [153, 207, 387], "seri": [221, 492, 532, 536, 543, 551], "serial": [138, 140, 396, 397], "serv": [195, 243, 390, 487], "server": [161, 483], "servic": [492, 543], "sess": [133, 243, 385, 390], "session": [31, 133, 208, 243, 385, 390, 536], "sessionopt": 257, "set": [1, 30, 36, 81, 90, 100, 133, 140, 145, 151, 152, 153, 154, 161, 165, 192, 195, 198, 199, 200, 209, 211, 214, 225, 230, 234, 235, 243, 261, 262, 281, 288, 302, 308, 352, 385, 387, 389, 390, 396, 406, 409, 413, 431, 433, 438, 439, 441, 447, 448, 465, 471, 473, 474, 476, 477, 478, 479, 481, 482, 483, 487, 488, 492, 494, 518, 521, 524, 526, 527, 528, 530, 531, 535, 536, 537, 542, 544, 547, 549, 550, 552], "set_all_env_var": 151, "set_cores_for_inst": 154, "set_eager_execut": 261, "set_env_var": 151, "set_epoch": 524, "set_loc": [470, 474, 475, 476, 477, 478], "set_modul": [145, 413, 433, 447], "set_nam": 90, "set_random_se": [161, 195, 465], "set_resume_from": [161, 195, 465], "set_tensor": 493, "set_tensorboard": [161, 195, 465], "set_workspac": [161, 195, 465], "settings_recommend": 520, "setup": [492, 528, 532, 542], "sever": [124, 190, 225, 379, 472, 473, 483, 487, 523, 531, 536, 537, 539, 542, 545, 550, 551, 552], "sex": [465, 488], "sexual": 488, "sf": 527, "sgd": [165, 195, 536], "shaji": 476, "shape": [30, 31, 90, 133, 175, 212, 213, 221, 225, 230, 385, 387, 420, 426, 435, 476, 480, 487, 528, 536, 547, 550, 551], "shape_overrid": 127, "shard": [141, 398], "share": [30, 31, 67, 83, 94, 126, 286, 339, 354, 359, 433, 476, 487, 527, 528, 547, 550, 552], "share_qdq_y_pattern": [91, 356], "shared_criterion": [413, 439, 550], "shareqdqforitexypatternoptim": [94, 359], "shell": [154, 492], "shen": [533, 542], "shift": [128, 150, 221, 380, 551], "shop": 520, "short": 552, "shortcut": 209, "shorter": [209, 225, 551], "shot": [169, 187, 190, 476, 480, 531, 536, 542, 543, 547], "should": [40, 100, 101, 140, 162, 171, 173, 184, 195, 198, 199, 207, 209, 211, 225, 228, 234, 235, 262, 281, 301, 305, 312, 396, 413, 427, 431, 441, 448, 458, 465, 475, 477, 478, 479, 480, 482, 487, 490, 493, 494, 495, 524, 535, 536, 540, 542, 544, 547, 551, 552], "show": [180, 465, 472, 487, 488, 524, 536, 539, 550, 552], "show_memory_info": 465, "show_nam": [131, 383], "show_op": [131, 383], "shown": [471, 472, 474, 487, 521, 535, 536, 539, 540, 541, 542, 545, 550, 552], "shrink": 542, "shuffl": [200, 202, 205, 206, 208, 387, 521, 536, 544], "shufflenet": 553, "side": [225, 492, 551], "sigmoid": 526, "sign": [280, 439, 476, 487, 489, 492, 495, 519, 543, 544, 547, 549], "signatur": [243, 390], "signed_flag": 280, "signifi": 90, "signific": [480, 487, 542, 543, 545, 550], "significantli": [473, 476, 536, 537, 542, 552], "signround": 476, "sigopt": [197, 543], "sigopt_api_token": [536, 549, 552], "sigopt_experiment_id": 549, "sigopt_experiment_nam": [536, 549, 552], "sigopt_project_id": [536, 549, 552], "sigopttunestrategi": 198, "silicon": [472, 539], "similar": [184, 487, 536, 550, 552], "similarli": [487, 550], "simpl": [156, 225, 471, 480, 487, 536, 542, 549, 550, 552], "simple_attr": 156, "simple_infer": [145, 417], "simple_progress_bar": 30, "simplest": 519, "simpli": [524, 538], "simplic": [487, 550], "simplifi": [542, 543], "simul": [168, 477, 495], "simultan": [184, 541], "sinc": [195, 227, 471, 476, 487, 526, 535, 541, 547], "since_vers": 89, "singl": [169, 190, 195, 203, 209, 225, 230, 234, 262, 305, 387, 406, 413, 476, 490, 492, 532, 542, 545, 550], "single_output": 234, "singleton": [95, 161, 360, 391, 465], "site": 548, "situat": [195, 477, 524, 542], "sixteen": [473, 537], "size": [83, 153, 177, 178, 202, 203, 208, 211, 217, 221, 225, 243, 245, 354, 387, 390, 418, 426, 433, 465, 472, 475, 476, 487, 488, 494, 521, 524, 527, 536, 539, 540, 542, 544, 545, 547, 550, 551, 553], "skip": [140, 396, 552], "skip_convers": 88, "skip_first": 277, "skip_verified_config": 153, "skylak": 532, "slave": [280, 552], "slice": 90, "slim": [171, 172, 173, 230, 241, 243, 390, 391, 538, 542], "slim_sess": [243, 390], "slower": [476, 547], "small": [3, 52, 53, 54, 55, 269, 324, 325, 326, 327, 476, 487, 542, 547, 552, 553], "smaller": [55, 225, 327, 472, 536, 539, 542, 551], "smbo": 552, "smooth": [3, 125, 126, 133, 149, 195, 283, 284, 285, 286, 301, 303, 412, 413, 437, 439, 477, 492, 520, 529, 542, 552], "smooth_distribut": 3, "smooth_quant": [4, 139, 145, 148, 195, 394, 417, 520, 544, 550], "smooth_quant_arg": [195, 544, 550], "smooth_quant_calibr": 96, "smooth_quant_config": 301, "smooth_quant_en": [145, 417], "smooth_quant_entri": [301, 437, 520], "smooth_quant_scal": 96, "smoother": 282, "smoothquant": [29, 145, 149, 284, 410, 412, 413, 439, 469, 474, 476, 477, 479, 487, 534, 543, 547], "smoothquant_scale_info": [145, 413], "smoothquantcalibr": [125, 283], "smoothquantcalibrationllm": [125, 283], "smoothquantconfig": [284, 301, 303, 437, 439, 474, 479, 480], "smoothquantquant": 412, "smoothquantsampl": 277, "smoothquantscal": [126, 286], "smoothquantscalerllm": [126, 286], "smt": 227, "snapshot": 464, "snip": [169, 195, 531, 542, 553], "snip_momentum": [169, 195, 536, 542], "snip_momentum_progress": 195, "snip_progress": 195, "snipcriterion": 169, "snipmomentumcriterion": 169, "snippet": [520, 531], "so": [31, 90, 153, 225, 280, 442, 469, 471, 472, 476, 477, 480, 487, 490, 492, 493, 527, 531, 537, 539, 544, 546, 547, 550, 551], "social": [488, 543], "socio": 488, "socket": [151, 154, 465, 553], "soft": 195, "softwar": [492, 533, 542, 543, 548], "solut": [128, 150, 380, 474, 476, 479, 487, 492, 493, 494, 527, 543, 547, 548, 550, 552], "solv": [487, 489, 544, 548], "some": [171, 173, 195, 209, 476, 477, 487, 492, 494, 495, 520, 526, 529, 532, 535, 536, 540, 542, 544, 546, 547, 550, 552], "someth": [198, 199, 211, 262, 448], "sometim": [90, 487, 490, 544], "somewhat": 494, "soon": 534, "sort": [195, 271, 476, 547, 552], "sota": 543, "sound": 532, "sourc": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 73, 74, 75, 76, 77, 78, 79, 81, 82, 83, 84, 85, 87, 88, 89, 90, 92, 93, 94, 95, 98, 100, 101, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 131, 132, 133, 134, 135, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 149, 150, 151, 152, 153, 154, 156, 157, 159, 160, 161, 162, 163, 165, 166, 169, 170, 171, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 194, 195, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 216, 217, 218, 221, 223, 224, 225, 226, 227, 228, 230, 231, 232, 234, 235, 236, 238, 239, 240, 241, 242, 243, 244, 245, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 271, 272, 273, 274, 277, 278, 279, 280, 281, 283, 284, 286, 288, 289, 292, 293, 294, 297, 298, 299, 301, 302, 303, 305, 306, 307, 308, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 345, 346, 347, 348, 349, 350, 352, 353, 354, 355, 357, 358, 359, 360, 363, 364, 365, 366, 367, 368, 369, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 383, 384, 385, 387, 389, 390, 391, 392, 396, 397, 398, 399, 401, 403, 404, 405, 406, 408, 409, 411, 412, 413, 415, 416, 417, 418, 419, 420, 421, 422, 423, 425, 426, 427, 429, 430, 431, 432, 433, 435, 437, 438, 439, 441, 442, 443, 444, 445, 447, 448, 451, 452, 454, 456, 457, 458, 460, 461, 462, 463, 464, 465, 466, 467, 490, 492, 533, 536, 543], "space": [151, 181, 182, 187, 195, 198, 199, 232, 235, 262, 266, 271, 278, 477, 481, 487, 488, 489, 493, 494, 495, 520, 542, 544, 550], "spacetobatchnd": [43, 315], "spanbert": 553, "spars": [171, 185, 543], "sparse_dummy_v2": 213, "sparse_gpt": 542, "sparse_ratio": 213, "sparsecategoricalcrossentropyloss": 163, "sparsedummydataset": 213, "sparsegpt": [188, 542], "sparsegptprun": 188, "sparsiti": [175, 177, 178, 180, 181, 182, 185, 187, 190, 192, 195, 465, 469, 476, 492, 531, 536, 553], "sparsity_decay_typ": [195, 536, 542], "speak": [476, 487, 547], "special": [101, 140, 173, 245, 396, 477, 490, 521, 535, 536, 540, 542, 547], "specif": [29, 89, 101, 151, 152, 154, 165, 192, 195, 209, 210, 211, 212, 216, 218, 234, 262, 387, 389, 409, 413, 447, 472, 473, 475, 476, 477, 480, 483, 488, 493, 494, 519, 520, 521, 528, 530, 534, 535, 536, 537, 538, 539, 540, 542, 547, 552], "specifi": [95, 140, 145, 151, 156, 192, 195, 198, 199, 225, 230, 234, 235, 262, 281, 360, 396, 404, 408, 413, 417, 418, 439, 441, 447, 448, 451, 464, 465, 477, 483, 487, 494, 495, 524, 528, 535, 536, 540, 542, 547, 551, 552], "speed": [471, 487, 519, 536, 542, 543, 544, 552], "speedup": [487, 525, 531, 544], "spellcheck": 489, "spent": 552, "spevif": 433, "spiq": [29, 149, 413, 487, 550], "split": [16, 30, 67, 224, 225, 339, 418, 487, 490, 545, 547, 550, 551], "split_shared_bia": 30, "split_shared_input": [61, 333], "splitoper": 26, "splitsharedinputoptim": [67, 339], "spot": [474, 550], "spr": [32, 289], "sprase": 171, "sq": [284, 412, 480, 534, 550], "sq_config": 479, "sq_weight_tensor": 133, "sq_weights_nod": 133, "sqlalchemi": 527, "sqlinearwrapp": 413, "sqrt": [54, 326], "squad": [209, 225, 231, 232, 234, 535, 542, 551, 553], "squadexampl": 225, "squadf1": [234, 535], "squadv1": [225, 551], "squar": [234, 271, 471, 476, 535, 552], "squeez": [63, 335, 490], "squeezenet": 553, "squeezer": 174, "squential": 207, "src": 90, "ssd": [490, 526, 553], "ssd_mobilenet_v1": 536, "ssh": 524, "sst": [542, 553], "st": [209, 535], "stabil": [476, 547], "stabilityai": [474, 550], "stabl": [492, 542, 543], "stablelm": [474, 550], "stack": [420, 492], "stage": [152, 161, 263, 265, 272, 542, 552], "stai": [474, 476, 477, 547, 550], "stand": [542, 552], "stand_norm": [212, 213, 387], "standard": [211, 225, 489, 494, 520, 526, 535, 551, 552], "star": 489, "start": [154, 195, 225, 230, 267, 469, 532, 543, 551, 552, 554], "start_epoch": 536, "start_posit": 225, "start_step": [180, 195, 536, 542], "stat": [154, 447], "state": [135, 174, 476, 483, 495, 542], "state_dict": [135, 398, 476, 524, 547], "statement": 520, "static": [28, 29, 32, 149, 173, 195, 262, 278, 287, 288, 289, 299, 301, 303, 413, 416, 417, 437, 439, 442, 458, 477, 492, 493, 494, 495, 526, 529, 531, 536, 545, 550, 552, 553], "static_config": 479, "static_graph": 173, "static_group": [439, 451, 476, 547], "static_qu": [282, 394, 478, 520], "static_quant_entri": [301, 437], "static_quant_export": 458, "staticmethod": [124, 379], "staticqu": [414, 416], "staticquantconfig": [288, 289, 299, 303, 391, 437, 439, 475, 478, 479, 480, 481], "staticquantquant": 416, "statist": [161, 465, 466, 471], "statu": [173, 477, 482, 488, 521, 539, 540, 542], "std": [221, 225, 536, 551], "std_valu": 221, "stderr": [391, 465], "step": [169, 179, 180, 181, 182, 186, 187, 190, 195, 448, 470, 474, 475, 476, 487, 494, 495, 523, 524, 536, 541, 542, 546, 547, 549, 550, 552], "step1": 278, "step2": 278, "step3": 278, "step4": 278, "step5": 278, "step_siz": 550, "still": [477, 479, 487, 519, 536, 543, 544, 546], "stock": [32, 289, 550], "stop": [153, 195, 469, 481, 536, 552], "stopgradi": [65, 337], "storag": [140, 396, 476, 487, 535, 547, 550], "store": [125, 169, 170, 173, 180, 181, 182, 183, 184, 185, 186, 187, 189, 191, 195, 211, 283, 408, 413, 530], "storywrit": 553, "str": [1, 29, 30, 31, 125, 135, 140, 141, 143, 144, 145, 146, 152, 154, 156, 160, 161, 163, 165, 170, 173, 194, 195, 209, 210, 211, 218, 221, 225, 227, 228, 230, 232, 234, 251, 256, 258, 260, 261, 277, 280, 281, 283, 299, 302, 303, 305, 391, 396, 398, 399, 404, 406, 408, 409, 413, 415, 417, 418, 425, 427, 431, 433, 435, 437, 439, 441, 442, 443, 445, 447, 451, 454, 457, 458, 461, 465, 466, 476, 477, 480, 520, 521, 535, 551], "str2arrai": 465, "str_label": 535, "straightforward": [476, 480, 487, 542, 547, 550], "strategi": [1, 145, 187, 195, 196, 211, 226, 469, 481, 487, 492, 493, 494, 495, 499, 519, 520, 521, 524, 531, 536, 543, 544, 546, 547, 548], "strategy_kwarg": [195, 549, 552], "strategy_registri": [274, 552], "stream": [391, 465, 553], "streamlin": [532, 543], "stretch": 471, "strftime": 195, "strict": 451, "stride": [90, 225, 292, 294, 297, 298, 551], "string": [30, 101, 133, 138, 140, 151, 161, 163, 165, 173, 175, 180, 188, 189, 190, 192, 195, 211, 227, 230, 239, 243, 385, 390, 391, 396, 397, 420, 447, 451, 454, 465, 471, 480, 535, 551], "strip": [52, 53, 55, 68, 69, 133, 324, 325, 327, 340, 341, 385], "strip_equivalent_nod": [61, 133, 333, 385], "strip_unused_lib": [133, 385], "strip_unused_nod": [61, 133, 333, 385], "stripequivalentnodesoptim": [68, 340], "stripunusednodesoptim": [69, 341], "stroke": 552, "structur": [174, 185, 186, 195, 279, 420, 465, 469, 477, 487, 531, 542, 543, 544, 553], "stsb": 553, "student": [162, 166, 195, 209, 523, 553], "student1_layer_name1": 195, "student1_layer_name2": 195, "student2_layer_name1": 195, "student2_layer_name2": 195, "student_layer_nam": 195, "student_layer_output_process": 195, "student_loss": 523, "student_model": [163, 195, 536], "student_output": 523, "style": [203, 216, 281, 520, 530], "style_fold": 216, "style_transfer_dataset": 215, "styletransferdataset": 216, "sub": [51, 145, 151, 173, 323, 417, 520, 552], "sub_class": [234, 262], "sub_modul": 520, "subclass": [3, 21, 146, 165, 175, 180, 188, 190, 204, 208, 211, 218, 225, 234, 245, 274, 413, 493], "subfold": 211, "subgraph": [40, 51, 90, 144, 312, 323, 545, 552], "subgraphstyl": 552, "subject": 533, "submit": [489, 543], "subpixel": 221, "subprocess": [154, 520, 521], "subsect": [487, 550], "subsequ": [184, 494], "subset": [211, 214], "subsidiari": 533, "substanti": 545, "substitut": [301, 305, 480], "success": 532, "successfulli": [490, 492, 524, 543], "successor": [76, 77, 78, 79, 347, 348, 349, 350], "sudo": 527, "suffici": 549, "suffix": [133, 385], "suggest": [477, 490, 520, 549], "suit": 532, "suitabl": 477, "sum": [195, 234], "summar": [131, 383, 520], "summari": [151, 154, 448, 553], "summary_benchmark": 151, "summary_latency_throughput": 154, "super": 232, "supplement": 480, "suppli": 1, "support": [1, 29, 30, 31, 82, 89, 149, 152, 163, 165, 170, 176, 183, 187, 195, 198, 199, 208, 209, 211, 218, 221, 225, 226, 234, 235, 239, 245, 262, 272, 278, 281, 353, 413, 437, 447, 448, 454, 460, 461, 465, 467, 469, 470, 475, 478, 481, 487, 492, 494, 520, 529, 534, 536, 543, 546, 549, 552], "supported_lay": [145, 420, 433], "supported_op_typ": [48, 320], "suppos": [487, 550], "suppress": [476, 487, 547, 550], "sure": [175, 180, 188, 190, 492, 518], "surg": [140, 396], "surrog": 552, "suyu": 533, "sweet": [474, 550], "switch": [70, 342], "switch_optim": [61, 333], "switchoptim": [70, 342], "sy": [391, 451, 465, 520], "sym": [29, 30, 31, 409, 413, 433, 451, 494, 495, 528, 544, 547], "sym_full_rang": 547, "sym_model": 1, "symbol": [1, 30, 144, 145, 227, 235, 262, 490, 538], "symbol_r": 227, "symbolblock": 1, "symbolic_trac": 136, "symmetr": [98, 409, 413, 461, 480, 495, 544, 547, 551, 552], "symnet": 1, "synchron": [445, 552], "syntax": 528, "sys_nic": 492, "system": [135, 140, 151, 154, 396, 465, 472, 473, 483, 518, 539, 542, 553], "systemat": [474, 479, 550], "szymon": 519, "t": [30, 52, 53, 55, 128, 140, 150, 175, 195, 225, 232, 324, 325, 327, 380, 396, 473, 474, 475, 480, 482, 490, 493, 520, 524, 536, 537, 542, 544, 547, 552], "t10k": 211, "t5": 542, "t5norm": 550, "tab": 232, "tabl": [173, 184, 465, 472, 492, 495, 526, 529, 539, 553], "table_entri": 465, "taco": [492, 543], "tag": [140, 243, 390, 396, 487, 550], "tail": 476, "tailor": [476, 483], "take": [3, 175, 195, 198, 199, 203, 225, 234, 235, 262, 266, 387, 448, 473, 476, 480, 483, 488, 490, 492, 521, 528, 536, 542, 544, 546, 547, 551, 552], "taken": [198, 199, 235, 262, 448, 544], "tamper": [140, 396], "tar": 211, "target": [1, 29, 30, 87, 145, 173, 190, 192, 195, 266, 288, 406, 420, 461, 471, 477, 524, 536, 542, 551, 552], "target_boxes_num": 535, "target_depth": [145, 417], "target_dtyp": [277, 406], "target_height": [225, 551], "target_lay": 173, "target_linear": 174, "target_op_lut": 173, "target_spars": [175, 195, 536, 542], "target_sparsity_ratio": 180, "target_width": [225, 551], "targetspac": 266, "task": [128, 209, 216, 234, 380, 471, 474, 476, 483, 487, 523, 526, 531, 535, 536, 542, 545, 547, 550, 553], "taskdataset": 553, "taskset": 483, "tbb": 527, "td": 552, "teacher": [162, 195, 523, 536, 553], "teacher_layer_nam": 195, "teacher_layer_name1": 195, "teacher_layer_name2": 195, "teacher_layer_output_process": 195, "teacher_logit": 536, "teacher_model": [163, 195, 523, 536], "team": [159, 232, 488, 546], "technic": 492, "techniqu": [226, 467, 469, 475, 480, 481, 487, 492, 529, 531, 536, 541, 542, 543, 544, 553], "technologi": [211, 472, 534, 536, 539], "tel2p1": 553, "tell": [140, 234, 262, 396], "temp_path": [125, 283], "temperatur": [163, 195, 536], "templat": [188, 536, 542], "template_config": 192, "temporari": [125, 145, 283, 413, 465, 488], "temporarili": 488, "ten": 483, "tencent": [492, 543], "tend": 542, "tensor": [1, 2, 3, 30, 31, 55, 90, 125, 133, 135, 140, 141, 145, 169, 170, 179, 180, 181, 182, 183, 184, 185, 186, 187, 189, 191, 195, 225, 243, 271, 283, 327, 385, 390, 391, 396, 398, 404, 406, 408, 411, 412, 413, 417, 422, 423, 425, 426, 433, 438, 442, 456, 458, 461, 464, 465, 470, 471, 472, 477, 480, 490, 495, 520, 521, 539, 542, 544, 548, 551, 552], "tensor2tensor": 228, "tensor_data": [74, 346, 391, 465, 466], "tensor_dict": 493, "tensor_dtyp": 90, "tensor_nam": [30, 133, 140, 141, 385, 396, 398], "tensor_to_nod": 1, "tensor_v": 133, "tensor_valu": 30, "tensorboard": [161, 195, 454, 465, 493, 536], "tensorcollector": 1, "tensordataset": 209, "tensorflow": [37, 39, 60, 61, 62, 72, 80, 86, 87, 88, 89, 90, 91, 95, 96, 97, 99, 102, 115, 125, 126, 127, 130, 133, 163, 165, 191, 195, 208, 209, 210, 211, 214, 216, 218, 225, 226, 228, 230, 234, 235, 243, 256, 257, 260, 261, 262, 272, 457, 458, 465, 479, 489, 493, 494, 500, 519, 520, 521, 523, 525, 528, 529, 531, 536, 537, 538, 539, 542, 543, 549, 550, 552], "tensorflow1": 208, "tensorflow_addon": 165, "tensorflow_dataload": 260, "tensorflow_itex": [211, 214, 216, 218, 521], "tensorflow_itexadaptor": [32, 289], "tensorflow_model": [237, 260], "tensorflowadam": 165, "tensorflowadamw": 165, "tensorflowadaptor": [32, 289], "tensorflowbasemodel": [243, 260, 390], "tensorflowbertdataload": 208, "tensorflowbertdataset": 209, "tensorflowcheckpointmodel": [243, 390], "tensorflowcifar10": 211, "tensorflowcifar100": 211, "tensorflowcocomap": 234, "tensorflowconfig": 289, "tensorflowconfigconvert": 289, "tensorflowcriterion": 163, "tensorflowcroptoboundingbox": 225, "tensorflowcrossentropyloss": 163, "tensorflowdataload": [208, 260], "tensorflowdataset": 211, "tensorflowfashionmnist": 211, "tensorflowfilt": 218, "tensorflowglobalconfig": 389, "tensorflowimagenetdataset": 214, "tensorflowimagenetraw": 214, "tensorflowimagerecord": 211, "tensorflowknowledgedistillationloss": 163, "tensorflowknowledgedistillationlossextern": 163, "tensorflowknowledgedistillationlosswrapp": 163, "tensorflowllmmodel": [243, 390], "tensorflowmap": 234, "tensorflowmetr": 234, "tensorflowmnist": 211, "tensorflowmodel": [243, 390], "tensorflowmodelzoobertdataload": 208, "tensorflowmodelzoobertdataset": [209, 210], "tensorflowoptim": 165, "tensorflowparserfactori": 252, "tensorflowprofilingpars": 253, "tensorflowqatmodel": 243, "tensorflowqdqtoonnxqdqconvert": 127, "tensorflowqueri": [32, 289, 493], "tensorflowrandomhorizontalflip": 225, "tensorflowrandomverticalflip": 225, "tensorflowresizecropimagenettransform": 221, "tensorflowresizewithratio": 225, "tensorflowsavedmodelmodel": [243, 390], "tensorflowsgd": 165, "tensorflowshiftrescal": 221, "tensorflowsparsecategoricalcrossentropi": 163, "tensorflowtfrecorddataset": 211, "tensorflowtopk": 234, "tensorflowtransform": 225, "tensorflowtranspos": 225, "tensorflowtransposelastchannel": 221, "tensorflowvocmap": 234, "tensorflowvocrecord": 211, "tensorflowwrapfunct": 225, "tensorproto": [30, 90], "tensorrt": [30, 519, 537, 544], "tensorrtexecutionprovid": [537, 544], "tensors_kl": 1, "tensors_minmax": 1, "teq": [428, 437, 439, 477, 492, 543, 545, 547], "teq_arg": 476, "teq_quantize_entri": 437, "teqconfig": [437, 439, 451, 476], "teqlinearfakequ": [142, 429], "tequant": 432, "term": [162, 181, 182, 187, 189, 477, 480, 489, 519, 533, 535, 540, 541, 552], "test": [151, 195, 225, 489, 492, 553], "test_func": 524, "text": [90, 188, 224, 225, 227, 232, 472, 474, 476, 487, 526, 533, 539, 542, 543, 547, 550, 551, 553], "tf": [90, 101, 126, 133, 173, 192, 208, 209, 210, 211, 225, 241, 243, 286, 303, 305, 361, 385, 387, 389, 390, 391, 478, 480, 492, 520, 524, 532, 538, 543, 546, 551], "tf1": [208, 538], "tf2": 538, "tf2onnx": [195, 455], "tf2onnx_convert": 96, "tf2onnx_util": 86, "tf2onnxconfig": [195, 526], "tf_criteria": 170, "tf_modul": 261, "tf_to_fp32_onnx": 457, "tf_to_int8_onnx": 457, "tfdatadataload": 208, "tfmodelzoocollecttransform": 225, "tfrecord": [209, 210, 211], "tfslimnetsfactori": [241, 391], "tfsquadv1modelzooposttransform": 225, "tfsquadv1posttransform": 225, "th": [74, 75, 346], "thalaiyasingam": 542, "than": [40, 133, 209, 225, 312, 391, 418, 443, 465, 472, 476, 487, 492, 518, 530, 539, 540, 541, 542, 544, 547, 549, 551, 552], "theblok": 492, "thei": [140, 281, 396, 473, 488, 520, 528, 536, 540], "them": [140, 173, 209, 396, 476, 477, 487, 490, 495, 521, 526, 528, 530, 532, 541, 542, 547, 552], "themselv": 544, "theoret": [476, 487, 544, 547], "therefor": [482, 487, 490, 536, 542, 544, 545, 548, 550], "thi": [29, 71, 95, 117, 124, 128, 132, 135, 138, 140, 145, 150, 152, 153, 154, 162, 166, 171, 173, 175, 177, 178, 179, 180, 184, 185, 186, 187, 188, 189, 190, 195, 198, 199, 208, 209, 210, 211, 212, 213, 214, 216, 225, 227, 230, 231, 232, 234, 235, 245, 262, 266, 271, 280, 281, 343, 360, 372, 379, 380, 384, 387, 396, 397, 413, 417, 442, 448, 464, 465, 469, 471, 473, 474, 475, 476, 478, 479, 480, 481, 487, 488, 489, 490, 492, 493, 494, 495, 519, 520, 521, 523, 524, 526, 527, 528, 531, 532, 533, 534, 535, 536, 537, 538, 542, 544, 546, 547, 548, 549, 550, 551, 552], "think": [476, 547], "third": [230, 489, 533], "those": [59, 140, 271, 331, 396, 465, 475, 480, 487, 523, 530, 536, 537, 541, 542, 544, 552], "though": [487, 550], "thread": [151, 195, 257, 261, 521, 527], "threaten": 488, "three": [59, 192, 209, 263, 265, 331, 473, 477, 481, 487, 490, 493, 494, 519, 532, 537, 541, 544, 546, 549, 550], "threshold": [1, 147, 452, 460, 535], "through": [135, 198, 199, 234, 235, 262, 475, 476, 477, 487, 492, 518, 528, 530, 531, 535, 540, 541, 542, 544, 547], "throughput_pattern": 482, "throw": 521, "thu": [230, 487, 536, 542, 544], "thudm": 534, "tian": 533, "tiiuae": [474, 534, 550, 553], "tile": 520, "till": [161, 465, 552], "tim": [476, 487, 547], "time": [133, 140, 161, 195, 225, 234, 245, 266, 385, 391, 396, 465, 475, 476, 477, 479, 481, 483, 487, 492, 494, 521, 524, 527, 536, 540, 542, 543, 544, 547, 549, 550, 551, 552], "time_limit": 465, "timeout": [195, 536, 552], "tinybert": 553, "tip": 483, "titl": [465, 533, 552], "tloss": 524, "tmp_file_path": [391, 465], "to_numpi": 30, "toarrai": [225, 551], "todo": [156, 209, 212, 230, 278, 387, 420, 443], "togeth": [152, 195, 225, 532, 543, 551], "togethercomput": [474, 550], "token": [209, 222, 225, 227, 228, 418, 451, 461, 474, 476, 487, 535, 536, 547, 549, 550, 551, 552], "token_is_max_context": 225, "token_to_orig_map": 225, "token_type_id": [209, 536], "tokenzi": 224, "toler": [153, 480], "tolerable_loss": [153, 195, 481, 536, 552], "tolist": 550, "tondarrai": 551, "tondarraytransform": 225, "tool": [3, 133, 385, 457, 465, 487, 492, 493, 536, 542, 543, 544], "toolchain": [527, 543], "toolkit": [469, 490, 532, 543], "top": [225, 234, 489, 535, 551], "top1": [448, 535, 542, 544, 553], "topilimag": 551, "topk": [234, 262, 524, 535, 536, 544], "torch": [134, 135, 136, 137, 140, 141, 142, 143, 144, 145, 149, 153, 160, 170, 173, 174, 176, 184, 195, 226, 235, 262, 458, 461, 464, 470, 471, 472, 473, 474, 475, 476, 481, 483, 487, 490, 495, 496, 524, 526, 527, 529, 536, 537, 538, 539, 544, 547, 550], "torch2onnx": [195, 455], "torch2onnxconfig": [195, 526], "torch_dtyp": [492, 495], "torch_load": 137, "torch_model": 237, "torch_to_fp32_onnx": 458, "torch_to_int8_onnx": 458, "torch_util": [439, 545, 550], "torchbaseconfig": 439, "torchdynamo": 477, "torchfunctyp": 406, "torchimport": 477, "torchscript": [441, 526, 545, 550], "torchsmoothqu": [412, 413, 550], "torchvis": [225, 471, 492, 525], "toronto": 211, "torr": 542, "total": [30, 180, 225, 234, 418, 476, 542, 547, 551, 553], "total_block_arg": 145, "total_block_kwarg": 145, "total_execution_tim": 251, "total_valu": [145, 433], "totensor": [536, 551], "tow": 524, "toward": 488, "tpe": 197, "tpetunestrategi": 199, "tqdm": [30, 536], "trace": [135, 144, 145, 173, 195, 269, 408, 412, 413, 417, 438, 442, 458, 475, 477, 490, 552], "trace_and_fuse_sub_graph": 144, "trace_gptq_target_block": 420, "traceabl": 490, "traced_model": [144, 413], "tracer": 490, "track": [161, 549], "trackabl": [133, 385], "trade": [476, 487, 547], "tradit": [480, 542], "train": [29, 42, 65, 149, 162, 181, 182, 185, 187, 195, 198, 199, 209, 211, 225, 226, 262, 314, 337, 413, 420, 439, 454, 472, 473, 474, 475, 476, 477, 479, 481, 492, 493, 494, 499, 523, 526, 529, 531, 537, 539, 541, 543, 545, 547, 549, 550, 552], "train_cfg": 454, "train_dataload": [536, 542, 544], "train_dataset": [524, 544], "train_fn": 476, "train_fun": 536, "train_func": [448, 524, 536, 544], "train_kwarg": 524, "train_load": 524, "train_loop": [448, 536, 541], "train_sampl": 524, "trainabl": [432, 476, 492, 543, 547], "trainableequivalenttransform": 432, "trainer": 536, "training_arg": 536, "training_func": 536, "training_func_for_nc": 523, "trane": 477, "transact": 550, "transfer": [162, 216, 487, 523, 536, 550], "transform": [30, 35, 128, 130, 131, 132, 143, 187, 209, 210, 211, 212, 213, 214, 216, 218, 220, 307, 380, 382, 383, 384, 387, 406, 412, 413, 417, 420, 432, 439, 445, 474, 475, 476, 479, 487, 490, 492, 519, 523, 524, 525, 529, 534, 536, 542, 543, 546, 547, 550, 552], "transform_func": 225, "transform_graph": [96, 361], "transform_list": [225, 551], "transform_registri": 225, "transform_typ": 225, "transformer_block": 420, "transformerbasedmodelblockpatterndetector": [143, 417], "transformers_nam": 420, "transformers_pr": 420, "translat": [227, 228, 472, 539, 542, 552], "translation_corpu": 228, "transpos": [30, 58, 179, 221, 225, 330, 457, 547, 551], "travers": [481, 494, 495, 547, 552], "treat": [140, 396, 521], "tree": [188, 278], "tri": [152, 195, 520, 552], "trial": [153, 481, 552], "trigger": [151, 154, 180, 482], "troll": 488, "trt_env_setup": 30, "true": [1, 30, 31, 70, 98, 131, 133, 140, 151, 153, 195, 207, 209, 211, 212, 224, 225, 228, 234, 245, 262, 277, 281, 292, 293, 294, 298, 299, 303, 342, 383, 385, 387, 396, 398, 406, 412, 413, 418, 420, 423, 427, 429, 432, 433, 439, 442, 451, 454, 458, 461, 464, 465, 470, 474, 475, 476, 477, 478, 480, 481, 482, 487, 494, 521, 524, 528, 535, 536, 544, 545, 547, 550, 551, 552], "true_sequenti": [439, 451, 476, 547], "truncat": [209, 225, 418, 551], "trust": [140, 396], "trust_remote_cod": [431, 441], "truth": [231, 232], "try": [207, 243, 390, 480, 487, 490, 492, 527, 542, 544, 550, 552], "try_cnt": [133, 385], "try_loading_kera": [243, 390], "tunabl": [152, 156], "tunable_typ": 156, "tune": [1, 151, 152, 153, 156, 159, 195, 198, 199, 209, 211, 235, 245, 262, 263, 264, 265, 266, 267, 268, 269, 271, 272, 273, 274, 277, 278, 279, 280, 302, 413, 438, 439, 448, 465, 473, 474, 475, 476, 477, 481, 484, 492, 493, 494, 519, 520, 521, 524, 529, 531, 533, 536, 537, 540, 542, 543, 546, 548, 549], "tune_cfg": [1, 134, 145, 412, 413, 417, 447, 493, 495, 552], "tune_config": [153, 302, 438, 473, 477, 478, 479, 480, 481, 494], "tuner": [198, 199, 235, 262, 448, 544], "tunestrategi": [274, 552], "tunestrategymeta": 274, "tuning_cfg_to_fw": 494, "tuning_config": 153, "tuning_criterion": [195, 536, 540, 549, 552], "tuning_history_path": 465, "tuning_items_prior": 277, "tuning_order_lst": 277, "tuning_param": 155, "tuning_sampl": 276, "tuning_spac": [276, 277, 279], "tuning_strategi": 195, "tuning_struct": [276, 277, 278], "tuningconfig": [153, 302, 438, 473, 477, 478, 479, 480, 481], "tuningcriterion": [195, 536, 540, 549, 552], "tuningitem": 278, "tuninglogg": [153, 159], "tuningmonitor": 153, "tuningord": 277, "tuningparam": 156, "tuningsampl": 277, "tuningspac": [277, 278], "tupl": [1, 90, 133, 145, 153, 195, 198, 199, 221, 225, 235, 262, 277, 302, 305, 399, 406, 408, 411, 412, 413, 417, 418, 425, 426, 435, 437, 438, 439, 442, 447, 448, 458, 464, 477, 480, 494, 520, 535, 536, 544, 551], "turbo": 553, "turn": [535, 545], "tutori": [469, 490, 543], "twitter": 543, "two": [133, 135, 140, 151, 174, 179, 186, 190, 211, 216, 230, 272, 396, 465, 471, 472, 473, 475, 476, 479, 481, 484, 487, 489, 490, 520, 521, 524, 526, 528, 536, 537, 539, 542, 544, 546, 547, 549, 550, 552], "txt": [214, 527, 532], "type": [1, 3, 29, 30, 31, 59, 81, 90, 101, 107, 117, 125, 133, 134, 135, 140, 145, 146, 152, 153, 154, 156, 160, 161, 163, 165, 173, 174, 175, 180, 188, 189, 190, 192, 194, 195, 207, 209, 211, 218, 225, 227, 228, 230, 234, 243, 245, 266, 267, 274, 278, 280, 281, 283, 301, 305, 331, 352, 372, 385, 390, 391, 396, 398, 403, 404, 406, 408, 409, 411, 413, 417, 418, 420, 425, 426, 427, 431, 433, 435, 437, 438, 439, 442, 447, 458, 464, 465, 469, 471, 472, 473, 474, 475, 476, 477, 478, 480, 483, 493, 494, 524, 526, 528, 531, 536, 537, 539, 544, 545, 547, 549, 551, 552], "typealia": 520, "types_to_splic": [65, 337], "typic": [492, 523, 525, 542, 553], "u": [128, 150, 380], "ubuntu": 532, "ubuntu22": 492, "ubyt": 211, "uint4": 495, "uint8": [30, 221, 230, 280, 409, 433, 439, 480, 487, 493, 528, 544, 551], "ultim": [487, 544], "ultra": [492, 532, 553], "unaccept": 488, "unari": 27, "unary_op": 16, "unarydirect8bitoper": 27, "unaryoper": 27, "unbalanc": 553, "uncas": [209, 225, 551, 553], "uncertain": 542, "undefin": [140, 192, 396], "under": [95, 195, 211, 360, 391, 447, 461, 464, 481, 489, 492, 533, 535, 536, 541, 542, 543, 545, 547, 552], "underli": [52, 53, 55, 140, 324, 325, 327, 396], "understand": [469, 487, 544], "understudi": 227, "unicod": 224, "unicodedecodeerror": [140, 396], "unicoderegex": 227, "unifi": [159, 392, 435, 493, 494, 495, 521, 530, 531, 535, 536, 538], "uniform": [476, 519, 547], "uniformli": [476, 547], "union": [152, 234, 435, 438, 439, 447, 448, 477, 480, 535], "uniqu": [230, 487, 544], "unique_id": 225, "unit": [175, 293, 489, 542], "unit_scal": 471, "unk": 224, "unk_token": 224, "unless": [140, 396, 528], "unlik": 480, "unnecessari": 536, "unpack": [421, 429], "unpack_weight": 429, "unpack_zp": 429, "unpackedweightonlylinearparam": 429, "unpickl": [138, 140, 396, 397], "unpicklingerror": [138, 397], "unpreced": 542, "unquant": 406, "unquantized_node_set": 406, "unsaf": [140, 396], "unseen": [480, 487, 544], "unset": 31, "unsign": [145, 280, 495, 547], "unstructur": [195, 531, 542, 553], "unsupport": [526, 536, 542], "until": [413, 471, 494, 552], "untrac": 490, "untrust": [140, 396], "unus": [69, 133, 341, 385, 447], "unwelcom": 488, "up": [1, 85, 184, 225, 355, 417, 471, 487, 492, 524, 525, 527, 528, 531, 542, 543, 544, 549, 551, 552], "up1": 528, "up2": 528, "updat": [59, 141, 145, 169, 175, 192, 234, 262, 331, 398, 413, 417, 469, 476, 527, 534, 535, 536, 542, 547, 550, 552], "update_config": 195, "update_modul": [141, 398], "update_param": 192, "update_sq_scal": [145, 413], "upgrad": 536, "upload": 531, "upstream": [431, 441], "url": [211, 420, 489, 492, 532, 533, 542], "us": [1, 3, 21, 29, 30, 31, 33, 34, 55, 88, 90, 101, 126, 135, 140, 145, 151, 152, 154, 161, 163, 165, 169, 173, 175, 180, 184, 185, 188, 190, 191, 195, 198, 199, 207, 208, 209, 210, 211, 212, 213, 216, 224, 225, 227, 228, 230, 234, 245, 257, 261, 262, 266, 269, 271, 274, 278, 280, 281, 286, 288, 289, 301, 305, 306, 327, 387, 391, 396, 404, 405, 406, 408, 409, 412, 413, 416, 417, 418, 425, 426, 427, 433, 438, 441, 442, 443, 447, 448, 451, 452, 453, 454, 457, 458, 459, 461, 465, 471, 472, 473, 474, 475, 476, 477, 478, 480, 481, 483, 487, 488, 489, 490, 493, 494, 518, 519, 520, 523, 524, 526, 528, 529, 530, 533, 536, 537, 538, 539, 540, 542, 543, 544, 545, 546, 547, 548, 549, 551, 552, 553], "usabl": 492, "usag": [145, 152, 153, 156, 208, 230, 281, 391, 433, 443, 444, 447, 477, 478, 483, 487, 494, 524, 525, 540, 547, 551], "use_auto_clip": [439, 476], "use_auto_scal": [439, 476], "use_bf16": [33, 34, 306], "use_bia": [292, 293, 294, 298], "use_bp": 228, "use_double_qu": [439, 476], "use_full_length": 547, "use_full_rang": [439, 476], "use_layer_wis": [420, 439, 451, 476], "use_max_length": [420, 547], "use_mse_search": [439, 451, 476], "use_optimum_format": [429, 461, 547], "use_sym": [439, 476, 481], "user": [140, 151, 165, 173, 185, 192, 195, 198, 199, 211, 214, 218, 225, 234, 235, 245, 262, 267, 280, 396, 406, 413, 417, 439, 447, 448, 465, 472, 473, 474, 475, 476, 477, 478, 479, 480, 481, 483, 487, 490, 493, 494, 495, 499, 518, 520, 521, 523, 526, 528, 531, 534, 535, 536, 537, 538, 539, 540, 541, 542, 543, 544, 545, 546, 548, 550, 551, 552], "user_cfg": [413, 417], "user_config": 192, "user_eval_fns1": 153, "user_eval_fns2": 153, "user_eval_fns3": 153, "user_eval_fns4": 153, "user_metr": [234, 262], "user_model": [472, 529, 539], "user_obj_cfg": 245, "user_object": 245, "user_postprocess": 223, "user_processor_typ": 447, "userfloatmodel": [470, 475], "usr": 527, "usr_cfg": 245, "usual": [209, 480, 487, 494, 541, 542, 544, 545, 550], "utf": [140, 224, 396], "util": [0, 4, 90, 95, 96, 124, 127, 134, 135, 136, 137, 144, 152, 153, 155, 164, 170, 193, 195, 226, 228, 270, 290, 301, 302, 304, 305, 395, 402, 407, 410, 414, 418, 428, 436, 437, 439, 469, 471, 480, 483, 494, 495, 496, 519, 520, 524, 536, 542, 544, 552], "v": [542, 552], "v0": [474, 534, 550], "v1": [133, 221, 231, 232, 234, 243, 385, 390, 474, 485, 524, 526, 527, 535, 538, 542, 548, 549, 550, 553], "v14": 227, "v2": [135, 269, 474, 521, 524, 526, 527, 534, 548, 550, 552, 553], "v3": [485, 553], "v4": 553, "v5": 489, "v5s6": 553, "val": [133, 192, 211, 214, 426, 536], "val2017": 210, "val_dataload": [478, 536, 544], "val_dataset": [478, 536, 544], "val_load": 544, "val_map": 214, "valid": [40, 52, 53, 90, 159, 180, 183, 192, 195, 211, 230, 243, 292, 294, 297, 298, 312, 324, 325, 390, 409, 492, 493, 525, 528, 531, 533, 536, 542, 544, 547, 548], "valid_keras_format": 391, "valid_mixed_precis": 528, "valid_reshape_input": [52, 53, 324, 325], "validate_and_inference_input_output": [243, 390], "validate_graph_nod": [243, 390], "valu": [3, 30, 31, 41, 52, 53, 55, 74, 75, 90, 128, 133, 140, 145, 150, 151, 169, 173, 174, 184, 191, 192, 195, 198, 199, 209, 212, 213, 221, 225, 230, 234, 235, 262, 266, 271, 278, 280, 281, 313, 324, 325, 327, 346, 380, 387, 396, 398, 413, 417, 425, 429, 448, 452, 454, 465, 470, 471, 472, 473, 474, 476, 479, 480, 487, 490, 494, 495, 519, 528, 535, 536, 537, 539, 540, 542, 544, 547, 550, 551, 552], "valuabl": 542, "value_layer_nam": 184, "valueerror": [52, 53, 55, 145, 230, 281, 324, 325, 327, 433, 527], "valueinfo": 30, "values_from_const": [52, 53, 55, 324, 325, 327], "vanhouck": 519, "vanilla": [493, 494, 531], "vari": [542, 550, 553], "variabl": [30, 138, 151, 189, 195, 211, 266, 280, 397, 443, 473, 477, 483, 542, 552], "varianc": [128, 150, 380], "variant": 205, "varieti": [477, 481, 525, 552], "variou": [235, 392, 472, 475, 477, 480, 495, 531, 539, 542, 545], "vault": 492, "vcvtne2ps2bf16": [473, 537], "vcvtneps2bf16": [473, 537], "vdpbf16p": [473, 537], "vecchio": 532, "vector": 473, "ventura": 532, "verbos": [30, 266, 425, 458], "veri": [469, 476, 487, 536, 544, 547, 552], "verifi": [526, 534], "version": [1, 39, 89, 142, 145, 173, 195, 226, 311, 429, 445, 457, 458, 469, 474, 488, 490, 492, 493, 520, 528, 532, 533, 536, 543, 550, 552], "version1": [133, 391, 465], "version1_eq_version2": [133, 391, 465], "version1_gt_version2": [133, 391, 465], "version1_gte_version2": [133, 391, 465], "version1_lt_version2": [133, 391, 465], "version1_lte_version2": [133, 391, 465], "version2": [133, 391, 465], "vertic": [179, 225, 551], "vgg": 553, "vgg16": [526, 553], "vgg19": 553, "via": [439, 476, 487, 488, 492, 524, 531, 536, 542, 543], "view": [489, 492, 525, 548], "viewpoint": 488, "vincent": 519, "violat": [138, 397], "virtual": [280, 543], "visibl": 482, "vision": [471, 487, 492, 526, 550], "visit": 553, "visual": [195, 549, 552], "vit": 553, "vmware": 543, "vnni": [487, 525, 531, 544], "voc": [211, 234], "vocab": 224, "vocab_fil": [224, 225, 551], "vocabulari": [209, 224, 225, 551], "vocmap": 535, "vscode": 520, "vtune": 533, "w": [31, 225, 420, 474, 487, 542, 550, 551], "w8a8": [405, 470, 475, 476, 487, 545, 547], "w8a8pt2equant": 405, "w_algo": 439, "w_dq": [487, 550], "w_dtype": [439, 472, 474, 475, 539], "w_fp32": [128, 150, 380], "w_granular": 439, "w_int8": [128, 150, 380], "w_q": [487, 550], "w_scale": [487, 550], "w_sym": 439, "wa": [140, 195, 396, 472, 474, 493, 536, 539, 543, 552], "wai": [173, 210, 211, 214, 243, 390, 476, 479, 487, 495, 521, 535, 536, 541, 542, 544, 547, 550, 552], "wanda": 170, "want": [52, 53, 55, 173, 195, 207, 209, 267, 324, 325, 327, 448, 490, 493, 521, 524, 536, 540, 544, 547, 549, 552], "waq": 550, "warm": 417, "warmup": [195, 518, 536], "warn": [413, 462, 520], "wasn": [140, 396], "wasserblat": 542, "we": [29, 30, 52, 53, 55, 59, 71, 128, 140, 149, 150, 151, 153, 173, 177, 184, 195, 208, 227, 230, 269, 324, 325, 327, 331, 343, 380, 396, 413, 469, 470, 474, 475, 476, 477, 479, 480, 481, 482, 483, 487, 488, 490, 492, 493, 494, 495, 520, 521, 524, 526, 528, 529, 534, 535, 536, 540, 541, 542, 544, 545, 547, 548, 549, 550, 552], "web": 492, "websit": 532, "wechat": [492, 543], "wei": [476, 487, 547, 550], "weight": [29, 30, 31, 45, 46, 107, 125, 126, 128, 133, 135, 145, 150, 153, 169, 170, 174, 177, 178, 179, 180, 181, 182, 183, 185, 186, 187, 189, 191, 195, 234, 262, 269, 278, 280, 283, 286, 317, 318, 380, 398, 413, 422, 428, 429, 431, 432, 433, 439, 441, 458, 465, 466, 469, 470, 471, 474, 475, 477, 478, 479, 480, 481, 493, 494, 495, 519, 523, 528, 529, 530, 534, 536, 540, 542, 543, 544, 545, 550, 552], "weight_algorithm": 303, "weight_bit": 494, "weight_clip": [303, 413], "weight_config": [31, 420, 432], "weight_correct": [148, 195, 544], "weight_decai": 536, "weight_dict": 135, "weight_dtyp": [299, 303, 451, 478], "weight_empir": [128, 380], "weight_granular": [299, 303, 478], "weight_max_lb": 413, "weight_max_valu": [292, 293, 294, 297, 298], "weight_min_valu": [292, 293, 294, 297, 298], "weight_name_map": [125, 283], "weight_onli": [4, 195, 394, 439, 464, 472, 520, 539, 545, 547], "weight_shap": 31, "weight_slim": [172, 184], "weight_sym": [299, 303, 478, 480, 481], "weight_tensor": 465, "weight_typ": 458, "weightcorrect": 150, "weightdetail": 465, "weightonli": 31, "weightonlylinear": [429, 476, 547], "weightonlyqu": 476, "weightonlyquantsampl": 277, "weightpruningconfig": [195, 536, 541, 542], "weights_detail": 459, "weights_onli": [140, 396], "weightsdetail": 466, "weightsstatist": 466, "welcom": [468, 488, 489, 492, 554], "well": [198, 199, 235, 262, 448, 472, 487, 492, 520, 539, 542, 544, 548, 550], "wenhua": [476, 487], "were": [140, 234, 396, 542], "wget": 527, "what": [145, 180, 207, 234, 262, 417, 448, 480, 488, 543], "when": [30, 39, 49, 55, 133, 138, 140, 153, 174, 180, 185, 192, 195, 209, 210, 218, 225, 228, 262, 301, 305, 311, 321, 327, 385, 396, 397, 406, 448, 471, 475, 476, 480, 481, 482, 483, 487, 488, 494, 520, 521, 536, 542, 544, 547, 550, 551, 552], "where": [30, 140, 195, 230, 234, 280, 396, 408, 465, 487, 495, 519, 550], "whether": [1, 30, 31, 90, 101, 133, 140, 145, 175, 195, 207, 209, 221, 225, 228, 230, 234, 305, 385, 391, 396, 409, 412, 413, 420, 425, 426, 433, 442, 445, 454, 461, 464, 465, 476, 482, 493, 535, 544, 547, 550, 551], "which": [1, 29, 41, 68, 95, 135, 140, 152, 169, 173, 174, 176, 180, 181, 182, 184, 187, 188, 190, 192, 195, 209, 210, 211, 221, 227, 232, 234, 239, 245, 262, 266, 313, 340, 360, 391, 396, 413, 420, 425, 426, 447, 465, 469, 471, 473, 475, 476, 477, 478, 480, 481, 487, 488, 490, 493, 494, 495, 519, 521, 524, 527, 528, 531, 535, 536, 537, 538, 541, 542, 544, 545, 546, 547, 548, 550, 551, 552], "while": [174, 185, 192, 266, 473, 475, 476, 480, 487, 492, 493, 494, 525, 531, 537, 542, 544, 547, 550], "white_list": [152, 299, 303, 439], "white_module_list": 447, "white_nod": 2, "whitespac": [224, 232], "whitespace_token": 224, "whl": [492, 532], "who": [267, 488], "whole": [470, 487, 495, 544, 553], "whose": [149, 175, 243, 390, 413, 530, 550, 552], "why": [487, 550], "wide": [473, 476, 487, 492, 525, 537, 542, 544], "wideresnet40": 553, "width": [179, 221, 225, 487, 519, 524, 542, 544, 551], "wiki": 488, "wikitext": 553, "window": [151, 154, 482, 483, 518, 532], "winogrand": 553, "winter": [487, 550], "wip": 534, "wise": [128, 137, 139, 141, 150, 195, 266, 267, 271, 380, 395, 398, 404, 469, 494, 531, 542, 547, 550, 552], "wish": 533, "with_arg": 495, "within": [89, 152, 153, 181, 182, 187, 194, 230, 243, 257, 261, 390, 473, 476, 488, 490, 495, 519, 537, 542, 543, 547, 550, 552], "without": [34, 75, 133, 185, 225, 280, 385, 445, 471, 472, 487, 488, 524, 536, 539, 542, 543, 544, 552], "without_scal": 471, "wnli": [209, 535], "won": [195, 544, 547], "woq": [431, 439, 441, 472, 492, 534, 539], "woqmodelload": 431, "word": [227, 476, 487, 520, 535, 542, 547, 553], "word_perplex": 553, "wordpiec": [224, 225, 551], "wordpiecetoken": 224, "work": [195, 301, 305, 477, 480, 482, 483, 487, 491, 494, 520, 521, 546, 547, 548, 550], "worker": [536, 544], "workflow": [469, 472, 492, 494, 495, 526, 529, 532, 537, 539], "workload": [465, 473, 543], "workload_loc": 465, "workshop": 543, "workspac": [161, 195, 464, 465, 538], "workspace_path": 195, "worth": [520, 542], "would": [475, 487, 489, 536, 542, 544, 550], "wrap": [1, 90, 101, 163, 230, 305, 389, 490, 524], "wrapmxnetmetr": 234, "wraponnxrtmetr": 234, "wrapped_lay": 101, "wrapper": [60, 87, 88, 89, 90, 107, 125, 134, 142, 153, 163, 170, 208, 225, 230, 234, 239, 243, 283, 332, 389, 390, 401, 429, 433, 480, 546], "wrapperlay": 413, "wrappytorchmetr": 234, "write": [133, 218, 385, 465, 524, 530, 536], "write_graph": [133, 385], "written": 536, "wt_compare_dict": 135, "www": [211, 553], "x": [1, 40, 59, 174, 195, 208, 225, 266, 281, 312, 331, 413, 481, 487, 492, 519, 520, 524, 529, 532, 537, 538, 544, 545, 550, 551], "x1": [487, 550, 552], "x2": [487, 550, 552], "x86": [473, 537], "x86_64": 518, "x86_inductor_quant": 409, "x86inductorquant": [409, 470], "x_max": 266, "x_q": [487, 550], "x_scale": [487, 550], "x_tmp": [487, 550], "xdoctest": [140, 396], "xeon": [473, 482, 487, 492, 532, 533, 534, 537, 543, 544, 546, 553], "xgb": 195, "xgboost": 542, "xiao": [476, 487, 547, 550], "xiui": [476, 487, 547, 550], "xlm": [209, 553], "xlnet": 209, "xpu": [195, 417, 443, 477, 480, 544], "xpu_acceler": 443, "xx": [145, 433], "xx_func": 520, "xxx": [154, 211, 536], "xxy": 211, "xxz": 211, "y": [94, 195, 225, 266, 359, 487, 520, 527, 550, 551], "y_dq": [487, 550], "y_max": 266, "y_q": [487, 550], "yaml": [192, 195, 198, 199, 209, 211, 288, 464, 465, 493, 495, 530, 535, 536, 540, 551], "yaml_fil": [465, 524], "yaml_file_path": 524, "yao": 135, "year": 533, "yet": 544, "yield": [153, 198, 199, 207, 235, 262, 266, 281, 387, 448, 487, 521, 544, 552], "yolo": 553, "yolov3": 553, "yolov5": 542, "you": [29, 140, 195, 207, 209, 234, 262, 396, 413, 469, 471, 489, 490, 494, 520, 521, 524, 527, 532, 533, 535, 537, 542, 544, 547, 548, 549, 550], "your": [207, 209, 469, 475, 489, 492, 520, 521, 524, 533, 536, 542, 543, 549, 552], "your_node1_nam": 524, "your_node2_nam": 524, "your_script": 548, "yourmodel": 476, "yourself": 542, "youtub": 543, "yum": [527, 532], "yvinec": [487, 550], "z": [30, 482, 487, 519, 520, 550], "za": 482, "zafrir": 542, "zero": [3, 30, 31, 180, 192, 225, 292, 293, 294, 298, 413, 422, 425, 426, 433, 465, 472, 475, 476, 487, 539, 542, 544, 547, 550, 551, 552], "zero_grad": [524, 536, 542], "zero_point": [30, 31, 451], "zero_point_nam": 30, "zeropoint": [480, 487, 544], "zfnet": 553, "zhen": 135, "zhewei": 135, "zip": [413, 490], "zo_valu": 30, "zone": 543, "zoo": [208, 225, 492, 525, 553], "zp": [31, 429, 433, 487, 550], "\u03b1": 519, "\u03b2": 519, "\u2776": 494, "\u2777": 494, "\u2778": 494, "\u2779": 494, "\u277a": 494, "\u277b": 494, "\u277c": 494, "\u817e\u8baf\u4e91taco": 543, "\u96c6\u6210\u82f1\u7279\u5c14": 543}, "titles": ["neural_compressor.adaptor.mxnet_utils", "neural_compressor.adaptor.mxnet_utils.util", "neural_compressor.adaptor.ox_utils.calibration", "neural_compressor.adaptor.ox_utils.calibrator", "neural_compressor.adaptor.ox_utils", "neural_compressor.adaptor.ox_utils.operators.activation", "neural_compressor.adaptor.ox_utils.operators.argmax", "neural_compressor.adaptor.ox_utils.operators.attention", "neural_compressor.adaptor.ox_utils.operators.binary_op", "neural_compressor.adaptor.ox_utils.operators.concat", "neural_compressor.adaptor.ox_utils.operators.conv", "neural_compressor.adaptor.ox_utils.operators.direct_q8", "neural_compressor.adaptor.ox_utils.operators.embed_layernorm", "neural_compressor.adaptor.ox_utils.operators.gather", "neural_compressor.adaptor.ox_utils.operators.gavgpool", "neural_compressor.adaptor.ox_utils.operators.gemm", "neural_compressor.adaptor.ox_utils.operators", "neural_compressor.adaptor.ox_utils.operators.lstm", "neural_compressor.adaptor.ox_utils.operators.matmul", "neural_compressor.adaptor.ox_utils.operators.maxpool", "neural_compressor.adaptor.ox_utils.operators.norm", "neural_compressor.adaptor.ox_utils.operators.ops", "neural_compressor.adaptor.ox_utils.operators.pad", "neural_compressor.adaptor.ox_utils.operators.pooling", "neural_compressor.adaptor.ox_utils.operators.reduce", "neural_compressor.adaptor.ox_utils.operators.resize", "neural_compressor.adaptor.ox_utils.operators.split", "neural_compressor.adaptor.ox_utils.operators.unary_op", "neural_compressor.adaptor.ox_utils.quantizer", "neural_compressor.adaptor.ox_utils.smooth_quant", "neural_compressor.adaptor.ox_utils.util", "neural_compressor.adaptor.ox_utils.weight_only", "neural_compressor.adaptor.tensorflow", "neural_compressor.adaptor.tf_utils.graph_converter", "neural_compressor.adaptor.tf_utils.graph_converter_without_calib", "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert", "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer", "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer", "neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base", "neural_compressor.adaptor.tf_utils.graph_rewriter", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation", "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx", "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph", "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node", "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema", "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils", "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq", "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern", "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq", "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern", "neural_compressor.adaptor.tf_utils.graph_util", "neural_compressor.adaptor.tf_utils", "neural_compressor.adaptor.tf_utils.quantize_graph", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize", "neural_compressor.adaptor.tf_utils.quantize_graph.qat", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling", "neural_compressor.adaptor.tf_utils.quantize_graph_common", "neural_compressor.adaptor.tf_utils.smooth_quant_calibration", "neural_compressor.adaptor.tf_utils.smooth_quant_scaler", "neural_compressor.adaptor.tf_utils.tf2onnx_converter", "neural_compressor.adaptor.tf_utils.transform_graph.bias_correction", "neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base", "neural_compressor.adaptor.tf_utils.transform_graph", "neural_compressor.adaptor.tf_utils.transform_graph.insert_logging", "neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat", "neural_compressor.adaptor.tf_utils.util", "neural_compressor.adaptor.torch_utils.bf16_convert", "neural_compressor.adaptor.torch_utils.hawq_metric", "neural_compressor.adaptor.torch_utils", "neural_compressor.adaptor.torch_utils.layer_wise_quant", "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle", "neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize", "neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load", "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils", "neural_compressor.adaptor.torch_utils.model_wrapper", "neural_compressor.adaptor.torch_utils.pattern_detector", "neural_compressor.adaptor.torch_utils.symbolic_trace", "neural_compressor.adaptor.torch_utils.util", "neural_compressor.algorithm.algorithm", "neural_compressor.algorithm.fast_bias_correction", "neural_compressor.algorithm", "neural_compressor.algorithm.smooth_quant", "neural_compressor.algorithm.weight_correction", "neural_compressor.benchmark", "neural_compressor.common.base_config", "neural_compressor.common.base_tuning", "neural_compressor.common.benchmark", "neural_compressor.common", "neural_compressor.common.tuning_param", "neural_compressor.common.utils.constants", "neural_compressor.common.utils", "neural_compressor.common.utils.logger", "neural_compressor.common.utils.save_load", "neural_compressor.common.utils.utility", "neural_compressor.compression.callbacks", "neural_compressor.compression.distillation.criterions", "neural_compressor.compression.distillation", "neural_compressor.compression.distillation.optimizers", "neural_compressor.compression.distillation.utility", "neural_compressor.compression.hpo", "neural_compressor.compression.hpo.sa_optimizer", "neural_compressor.compression.pruner.criteria", "neural_compressor.compression.pruner", "neural_compressor.compression.pruner.model_slim.auto_slim", "neural_compressor.compression.pruner.model_slim", "neural_compressor.compression.pruner.model_slim.pattern_analyzer", "neural_compressor.compression.pruner.model_slim.weight_slim", "neural_compressor.compression.pruner.patterns.base", "neural_compressor.compression.pruner.patterns", "neural_compressor.compression.pruner.patterns.mha", "neural_compressor.compression.pruner.patterns.ninm", "neural_compressor.compression.pruner.patterns.nxm", "neural_compressor.compression.pruner.pruners.base", "neural_compressor.compression.pruner.pruners.basic", "neural_compressor.compression.pruner.pruners.block_mask", "neural_compressor.compression.pruner.pruners", "neural_compressor.compression.pruner.pruners.mha", "neural_compressor.compression.pruner.pruners.pattern_lock", "neural_compressor.compression.pruner.pruners.progressive", "neural_compressor.compression.pruner.pruners.retrain_free", "neural_compressor.compression.pruner.pruning", "neural_compressor.compression.pruner.regs", "neural_compressor.compression.pruner.schedulers", "neural_compressor.compression.pruner.tf_criteria", "neural_compressor.compression.pruner.utils", "neural_compressor.compression.pruner.wanda", "neural_compressor.compression.pruner.wanda.utils", "neural_compressor.config", "neural_compressor.contrib", "neural_compressor.contrib.strategy", "neural_compressor.contrib.strategy.sigopt", "neural_compressor.contrib.strategy.tpe", "neural_compressor.data.dataloaders.base_dataloader", "neural_compressor.data.dataloaders.dataloader", "neural_compressor.data.dataloaders.default_dataloader", "neural_compressor.data.dataloaders.fetcher", "neural_compressor.data.dataloaders.mxnet_dataloader", "neural_compressor.data.dataloaders.onnxrt_dataloader", "neural_compressor.data.dataloaders.pytorch_dataloader", "neural_compressor.data.dataloaders.sampler", "neural_compressor.data.dataloaders.tensorflow_dataloader", "neural_compressor.data.datasets.bert_dataset", "neural_compressor.data.datasets.coco_dataset", "neural_compressor.data.datasets.dataset", "neural_compressor.data.datasets.dummy_dataset", "neural_compressor.data.datasets.dummy_dataset_v2", "neural_compressor.data.datasets.imagenet_dataset", "neural_compressor.data.datasets", "neural_compressor.data.datasets.style_transfer_dataset", "neural_compressor.data.filters.coco_filter", "neural_compressor.data.filters.filter", "neural_compressor.data.filters", "neural_compressor.data", "neural_compressor.data.transforms.imagenet_transform", "neural_compressor.data.transforms", "neural_compressor.data.transforms.postprocess", "neural_compressor.data.transforms.tokenization", "neural_compressor.data.transforms.transform", "neural_compressor", "neural_compressor.metric.bleu", "neural_compressor.metric.bleu_util", "neural_compressor.metric.coco_label_map", "neural_compressor.metric.coco_tools", "neural_compressor.metric.evaluate_squad", "neural_compressor.metric.f1", "neural_compressor.metric", "neural_compressor.metric.metric", "neural_compressor.mix_precision", "neural_compressor.model.base_model", "neural_compressor.model", "neural_compressor.model.keras_model", "neural_compressor.model.model", "neural_compressor.model.mxnet_model", "neural_compressor.model.nets_factory", "neural_compressor.model.onnx_model", "neural_compressor.model.tensorflow_model", "neural_compressor.model.torch_model", "neural_compressor.objective", "neural_compressor.profiling", "neural_compressor.profiling.parser.factory", "neural_compressor.profiling.parser.onnx_parser.factory", "neural_compressor.profiling.parser.onnx_parser.parser", "neural_compressor.profiling.parser.parser", "neural_compressor.profiling.parser.result", "neural_compressor.profiling.parser.tensorflow_parser.factory", "neural_compressor.profiling.parser.tensorflow_parser.parser", "neural_compressor.profiling.profiler.factory", "neural_compressor.profiling.profiler.onnxrt_profiler.factory", "neural_compressor.profiling.profiler.onnxrt_profiler.profiler", "neural_compressor.profiling.profiler.onnxrt_profiler.utils", "neural_compressor.profiling.profiler.profiler", "neural_compressor.profiling.profiler.tensorflow_profiler.factory", "neural_compressor.profiling.profiler.tensorflow_profiler.profiler", "neural_compressor.profiling.profiler.tensorflow_profiler.utils", "neural_compressor.quantization", "neural_compressor.strategy.auto", "neural_compressor.strategy.auto_mixed_precision", "neural_compressor.strategy.basic", "neural_compressor.strategy.bayesian", "neural_compressor.strategy.conservative", "neural_compressor.strategy.exhaustive", "neural_compressor.strategy.hawq_v2", "neural_compressor.strategy", "neural_compressor.strategy.mse", "neural_compressor.strategy.mse_v2", "neural_compressor.strategy.random", "neural_compressor.strategy.strategy", "neural_compressor.strategy.utils.constant", "neural_compressor.strategy.utils", "neural_compressor.strategy.utils.tuning_sampler", "neural_compressor.strategy.utils.tuning_space", "neural_compressor.strategy.utils.tuning_structs", "neural_compressor.strategy.utils.utility", "neural_compressor.template.api_doc_example", "neural_compressor.tensorflow.algorithms", "neural_compressor.tensorflow.algorithms.smoother.calibration", "neural_compressor.tensorflow.algorithms.smoother.core", "neural_compressor.tensorflow.algorithms.smoother", "neural_compressor.tensorflow.algorithms.smoother.scaler", "neural_compressor.tensorflow.algorithms.static_quant", "neural_compressor.tensorflow.algorithms.static_quant.keras", "neural_compressor.tensorflow.algorithms.static_quant.tensorflow", "neural_compressor.tensorflow", "neural_compressor.tensorflow.keras", "neural_compressor.tensorflow.keras.layers.conv2d", "neural_compressor.tensorflow.keras.layers.dense", "neural_compressor.tensorflow.keras.layers.depthwise_conv2d", "neural_compressor.tensorflow.keras.layers", "neural_compressor.tensorflow.keras.layers.layer_initializer", "neural_compressor.tensorflow.keras.layers.pool2d", "neural_compressor.tensorflow.keras.layers.separable_conv2d", "neural_compressor.tensorflow.keras.quantization.config", "neural_compressor.tensorflow.keras.quantization", "neural_compressor.tensorflow.quantization.algorithm_entry", "neural_compressor.tensorflow.quantization.autotune", "neural_compressor.tensorflow.quantization.config", "neural_compressor.tensorflow.quantization", "neural_compressor.tensorflow.quantization.quantize", "neural_compressor.tensorflow.quantization.utils.graph_converter", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base", "neural_compressor.tensorflow.quantization.utils.graph_rewriter", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern", "neural_compressor.tensorflow.quantization.utils.graph_util", "neural_compressor.tensorflow.quantization.utils", "neural_compressor.tensorflow.quantization.utils.quantize_graph", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling", "neural_compressor.tensorflow.quantization.utils.quantize_graph_common", "neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction", "neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base", "neural_compressor.tensorflow.quantization.utils.transform_graph", "neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging", "neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat", "neural_compressor.tensorflow.quantization.utils.utility", "neural_compressor.tensorflow.utils.constants", "neural_compressor.tensorflow.utils.data", "neural_compressor.tensorflow.utils", "neural_compressor.tensorflow.utils.model", "neural_compressor.tensorflow.utils.model_wrappers", "neural_compressor.tensorflow.utils.utility", "neural_compressor.torch.algorithms.base_algorithm", "neural_compressor.torch.algorithms.fp8_quant.utils.logger", "neural_compressor.torch.algorithms", "neural_compressor.torch.algorithms.layer_wise", "neural_compressor.torch.algorithms.layer_wise.load", "neural_compressor.torch.algorithms.layer_wise.modified_pickle", "neural_compressor.torch.algorithms.layer_wise.utils", "neural_compressor.torch.algorithms.mixed_precision.half_precision_convert", "neural_compressor.torch.algorithms.mixed_precision", "neural_compressor.torch.algorithms.mixed_precision.module_wrappers", "neural_compressor.torch.algorithms.mx_quant", "neural_compressor.torch.algorithms.mx_quant.mx", "neural_compressor.torch.algorithms.mx_quant.utils", "neural_compressor.torch.algorithms.pt2e_quant.core", "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter", "neural_compressor.torch.algorithms.pt2e_quant", "neural_compressor.torch.algorithms.pt2e_quant.save_load", "neural_compressor.torch.algorithms.pt2e_quant.utility", "neural_compressor.torch.algorithms.smooth_quant", "neural_compressor.torch.algorithms.smooth_quant.save_load", "neural_compressor.torch.algorithms.smooth_quant.smooth_quant", "neural_compressor.torch.algorithms.smooth_quant.utility", "neural_compressor.torch.algorithms.static_quant", "neural_compressor.torch.algorithms.static_quant.save_load", "neural_compressor.torch.algorithms.static_quant.static_quant", "neural_compressor.torch.algorithms.static_quant.utility", "neural_compressor.torch.algorithms.weight_only.autoround", "neural_compressor.torch.algorithms.weight_only.awq", "neural_compressor.torch.algorithms.weight_only.gptq", "neural_compressor.torch.algorithms.weight_only.hqq.bitpack", "neural_compressor.torch.algorithms.weight_only.hqq.config", "neural_compressor.torch.algorithms.weight_only.hqq.core", "neural_compressor.torch.algorithms.weight_only.hqq", "neural_compressor.torch.algorithms.weight_only.hqq.optimizer", "neural_compressor.torch.algorithms.weight_only.hqq.qtensor", "neural_compressor.torch.algorithms.weight_only.hqq.quantizer", "neural_compressor.torch.algorithms.weight_only", "neural_compressor.torch.algorithms.weight_only.modules", "neural_compressor.torch.algorithms.weight_only.rtn", "neural_compressor.torch.algorithms.weight_only.save_load", "neural_compressor.torch.algorithms.weight_only.teq", "neural_compressor.torch.algorithms.weight_only.utility", "neural_compressor.torch.export", "neural_compressor.torch.export.pt2e_export", "neural_compressor.torch", "neural_compressor.torch.quantization.algorithm_entry", "neural_compressor.torch.quantization.autotune", "neural_compressor.torch.quantization.config", "neural_compressor.torch.quantization", "neural_compressor.torch.quantization.load_entry", "neural_compressor.torch.quantization.quantize", "neural_compressor.torch.utils.auto_accelerator", "neural_compressor.torch.utils.constants", "neural_compressor.torch.utils.environ", "neural_compressor.torch.utils", "neural_compressor.torch.utils.utility", "neural_compressor.training", "neural_compressor.transformers.quantization.utils", "neural_compressor.transformers.utils", "neural_compressor.transformers.utils.quantization_config", "neural_compressor.utils.collect_layer_histogram", "neural_compressor.utils.constant", "neural_compressor.utils.create_obj_from_config", "neural_compressor.utils.export", "neural_compressor.utils.export.qlinear2qdq", "neural_compressor.utils.export.tf2onnx", "neural_compressor.utils.export.torch2onnx", "neural_compressor.utils", "neural_compressor.utils.kl_divergence", "neural_compressor.utils.load_huggingface", "neural_compressor.utils.logger", "neural_compressor.utils.options", "neural_compressor.utils.pytorch", "neural_compressor.utils.utility", "neural_compressor.utils.weights_details", "neural_compressor.version", "Intel\u00ae Neural Compressor Documentation", "2.X API User Guide", "Dynamic Quantization", "FP8 Quantization", "Microscaling Quantization", "PyTorch Mixed Precision", "PyTorch Smooth Quantization", "PyTorch Static Quantization", "PyTorch Weight Only Quantization", "Torch", "TensorFlow Quantization", "Smooth Quant", "TensorFlow", "AutoTune", "Benchmark", "Quantization on Client", "Design", "Version mapping between Intel Neural Compressor to Gaudi Software Stack", "<no title>", "Quantization", "Contributor Covenant Code of Conduct", "Contribution Guidelines", "FX", "Security Policy", "Intel\u00ae Neural Compressor", "Adaptor", "How to Add An Adaptor", "How to Support New Data Type, Like Int4, with a Few Line Changes", "Adaptor", "ONNX Runtime", "Torch Utils", "2.0 API", "3.0 API", "API Document Example", "APIs", "Benchmark", "Compression", "Config", "Mix Precision", "Model", "Objective", "Quantization", "Strategy", "Tensorflow Quantization AutoTune", "Tensorflow Quantization Base API", "Tensorflow Quantization Config", "Pytorch Quantization AutoTune", "Pytorch Quantization Base API", "Pytorch Quantization Config", "Training", "Benchmarking", "Calibration Algorithms in Quantization", "INC Coding Conventions", "DataLoader", "Design", "Distillation for Quantization", "Distributed Training and Inference (Evaluation)", "Examples", "Export", "Frequently Asked Questions", "Framework YAML Configuration Files", "Getting Started", "Incompatible changes between v1.2 and v1.1", "Infrastructure of Intel\u00ae Neural Compressor", "Installation", "Legal Information", "LLMs Quantization Recipes", "Metrics", "Code Migration from Intel Neural Compressor 1.X to Intel Neural Compressor 2.X", "Mixed Precision", "Model", "Microscaling Quantization", "Objective", "Optimization Orchestration", "Pruning", "Full Publications/Events (84)", "Quantization", "Layer Wise Quantization (LWQ)", "Turn OFF Auto Mixed Precision during Quantization", "Weight Only Quantization (WOQ)", "Release", "SigOpt Strategy", "Smooth Quant", "Transform", "Tuning Strategies", "Validated Models", "Intel\u00ae Neural Compressor Documentation"], "titleterms": {"": [492, 532], "0": [499, 500, 553], "1": [524, 527, 530, 536, 553], "15": [543, 553], "17": 553, "2": [469, 499, 524, 527, 530, 536, 553], "2018": 543, "2020": 543, "2021": 543, "2022": 543, "2023": 543, "2024": 543, "25": 543, "3": [500, 527], "35": 543, "4": [527, 543], "5": [527, 543], "64": 532, "84": 543, "One": 541, "With": 478, "abil": 495, "accept": 489, "accord": [494, 495], "accuraci": [473, 478, 487, 534, 537, 544, 552], "activ": 5, "ad": 493, "adaptor": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 493, 494, 496], "add": 494, "addit": 492, "advanc": 469, "ai": 532, "algorithm": [146, 147, 148, 149, 150, 282, 283, 284, 285, 286, 287, 288, 289, 392, 393, 394, 395, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413, 414, 415, 416, 417, 418, 419, 420, 421, 422, 423, 424, 425, 426, 427, 428, 429, 430, 431, 432, 433, 519, 547, 550, 552], "algorithm_entri": [301, 437], "alpha": [474, 479, 550], "an": 494, "annot": 520, "api": [469, 472, 473, 477, 480, 493, 494, 499, 500, 501, 502, 512, 515, 518, 521, 523, 524, 530, 535, 537, 539, 540, 541, 542], "api_doc_exampl": 281, "appendix": 526, "approach": [480, 544], "architectur": [484, 522, 531, 532], "argmax": 6, "argument": 476, "ask": 527, "asymmetr": 487, "attent": 7, "attribut": [211, 281, 488], "auto": [263, 479, 546, 550, 552], "auto_acceler": 443, "auto_mixed_precis": 264, "auto_slim": 171, "autoround": [418, 476], "autotun": [302, 438, 473, 477, 481, 511, 514], "awar": [478, 487, 490, 536, 542, 544], "awq": [419, 476], "backend": [475, 480, 493, 544], "background": [493, 520], "base": [175, 180, 469, 512, 515, 532], "base_algorithm": 392, "base_config": 152, "base_dataload": 200, "base_model": 236, "base_tun": 153, "basic": [181, 265, 552], "bayesian": [266, 552], "benchmark": [151, 154, 482, 503, 518, 536], "benefit": 549, "bert_dataset": 209, "between": [485, 530], "bf16": [35, 36, 37, 307, 308, 309, 473, 537], "bf16_convert": [35, 134, 307], "bias_correct": [128, 380], "binari": 532, "binary_op": 8, "bitpack": 421, "bleu": 227, "bleu_util": 228, "block": 550, "block_mask": 182, "build": [521, 527, 535], "built": [530, 532, 535], "calcul": 494, "calibr": [2, 3, 283, 494, 519], "callback": 162, "capabl": [493, 547], "case": 482, "chang": [495, 530, 548], "channel": [487, 550], "check": 489, "checklist": 489, "citat": 533, "class": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 73, 74, 75, 76, 77, 78, 79, 81, 82, 83, 84, 85, 87, 88, 89, 90, 92, 93, 94, 95, 98, 100, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 131, 132, 134, 135, 139, 142, 143, 146, 147, 149, 150, 152, 153, 156, 157, 159, 161, 162, 163, 165, 169, 173, 174, 175, 177, 178, 179, 180, 181, 182, 184, 185, 186, 187, 188, 189, 190, 191, 195, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 216, 217, 218, 221, 223, 224, 225, 227, 230, 234, 236, 238, 239, 240, 241, 242, 243, 244, 245, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 258, 259, 260, 263, 264, 265, 266, 267, 268, 269, 271, 272, 273, 274, 277, 278, 279, 280, 281, 283, 284, 286, 288, 289, 292, 293, 294, 297, 298, 299, 303, 306, 307, 308, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 345, 346, 347, 348, 349, 350, 352, 353, 354, 355, 357, 358, 359, 360, 363, 364, 365, 366, 367, 368, 369, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 383, 384, 387, 389, 390, 391, 392, 398, 399, 401, 403, 404, 405, 406, 412, 413, 416, 417, 418, 419, 420, 421, 422, 423, 426, 427, 429, 430, 431, 432, 433, 439, 443, 444, 448, 451, 452, 460, 461, 462, 463, 465, 466, 493], "client": [476, 483], "coco_dataset": 210, "coco_filt": 217, "coco_label_map": 229, "coco_tool": 230, "code": [488, 489, 520, 536, 547], "collect_layer_histogram": 452, "comment": 520, "common": [152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 476, 477, 490, 527], "commun": 492, "comparison": 549, "compat": 532, "compress": [162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 504, 547], "compressor": [468, 485, 490, 492, 521, 531, 532, 535, 536, 549, 554], "comput": 532, "concat": 9, "conduct": [488, 489], "config": [195, 299, 303, 422, 439, 505, 513, 516, 540], "configur": [495, 524, 528, 549], "conserv": [267, 552], "constant": [157, 275, 386, 444, 453], "content": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 73, 74, 75, 76, 77, 78, 79, 81, 82, 83, 84, 85, 87, 88, 89, 90, 92, 93, 94, 95, 98, 100, 101, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 131, 132, 133, 134, 135, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 149, 150, 151, 152, 153, 154, 156, 157, 159, 160, 161, 162, 163, 165, 166, 169, 170, 171, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 194, 195, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 216, 217, 218, 221, 223, 224, 225, 227, 228, 230, 231, 232, 234, 235, 236, 238, 239, 240, 241, 242, 243, 244, 245, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 271, 272, 273, 274, 277, 278, 279, 280, 281, 283, 284, 286, 288, 289, 292, 293, 294, 297, 298, 299, 301, 302, 303, 305, 306, 307, 308, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 345, 346, 347, 348, 349, 350, 352, 353, 354, 355, 357, 358, 359, 360, 363, 364, 365, 366, 367, 368, 369, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 383, 384, 385, 387, 389, 390, 391, 392, 396, 397, 398, 399, 401, 403, 404, 405, 406, 408, 409, 411, 412, 413, 415, 416, 417, 418, 419, 420, 421, 422, 423, 425, 426, 427, 429, 430, 431, 432, 433, 435, 437, 438, 439, 441, 442, 443, 444, 445, 447, 448, 451, 452, 454, 456, 457, 458, 460, 461, 462, 463, 464, 465, 466, 492], "contrib": [196, 197, 198, 199], "contribut": 489, "contributor": [488, 489], "conv": 10, "conv2d": 292, "convent": 520, "convert_add_to_biasadd": [38, 310], "convert_layout": [39, 311], "convert_leakyrelu": [40, 312], "convert_nan_to_random": [41, 313], "convert_placeholder_to_const": [42, 314], "core": [284, 405, 423], "coven": [488, 489], "cpu": [492, 532, 553], "creat": 489, "create_obj_from_config": 454, "criteria": [169, 489, 542, 552], "criterion": 163, "custom": [521, 535, 552], "data": [200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 387, 494, 495, 525], "dataload": [200, 201, 202, 203, 204, 205, 206, 207, 208, 521], "dataset": [209, 210, 211, 212, 213, 214, 215, 216, 530], "decai": 542, "default_dataload": 202, "defin": [495, 524], "demo": [471, 482], "dens": 293, "deploy": 542, "depthwise_conv2d": 294, "dequantize_cast_optim": [36, 308], "design": [484, 494, 522, 552], "detail": 490, "determin": [479, 550], "devic": [480, 544], "differ": 549, "dilated_contract": [43, 315], "direct_q8": 11, "distil": [163, 164, 165, 166, 523, 536, 553], "distribut": [524, 552], "docker": [492, 532], "document": [468, 492, 501, 554], "driven": [473, 537], "dummy_biasadd": [44, 316], "dummy_dataset": 212, "dummy_dataset_v2": 213, "dump": 482, "dure": [537, 546], "dynam": [470, 487, 490, 544], "each": 550, "effici": 476, "embed_layernorm": 12, "enforc": 488, "engin": [532, 550], "enhanc": 550, "entir": 550, "environ": [445, 532], "evalu": 524, "evaluate_squad": 231, "event": [492, 543], "exampl": [470, 471, 472, 473, 475, 476, 478, 479, 487, 490, 493, 501, 518, 521, 523, 524, 525, 526, 535, 536, 537, 538, 539, 540, 541, 542, 544, 545, 547, 550, 553], "except": [138, 397], "execut": 524, "exhaust": [268, 552], "exit": 552, "expanddims_optim": [45, 317], "export": [434, 435, 455, 456, 457, 458, 526, 547], "f1": 232, "face": 530, "factori": [247, 248, 252, 254, 255, 259], "fake_quant": 98, "fast_bias_correct": 147, "featur": [524, 528, 529, 531, 544], "fetch_weight_from_reshap": [46, 318], "fetcher": 203, "few": 495, "file": 528, "filter": [217, 218, 219], "fix": [474, 479, 550], "flow": [493, 544], "fold_batch_norm": [47, 319], "fold_const": [48, 320], "folder": 520, "fp16": [473, 537], "fp32": [494, 526], "fp8": [471, 492], "fp8_quant": 393, "framework": [474, 492, 494, 521, 526, 528, 532, 538, 539, 545, 547, 550], "free": 542, "freeze_fake_qu": [73, 345], "freeze_valu": [74, 346], "freeze_value_without_calib": 75, "frequent": 527, "from": [492, 494, 532, 536], "full": 543, "function": [1, 3, 21, 29, 30, 31, 52, 53, 55, 89, 90, 101, 103, 133, 134, 135, 140, 141, 144, 145, 146, 151, 152, 153, 154, 160, 161, 163, 165, 166, 169, 170, 171, 173, 175, 176, 180, 183, 188, 189, 190, 191, 192, 194, 201, 202, 209, 211, 218, 224, 225, 227, 228, 230, 231, 232, 234, 235, 239, 243, 245, 257, 261, 262, 266, 274, 278, 280, 281, 292, 293, 294, 297, 298, 299, 301, 302, 303, 305, 324, 325, 327, 385, 387, 390, 391, 396, 398, 404, 406, 408, 409, 411, 412, 413, 415, 417, 418, 420, 425, 427, 431, 433, 435, 437, 438, 439, 441, 442, 443, 445, 447, 448, 454, 456, 457, 458, 461, 462, 464, 465, 524], "fundament": [487, 544, 550], "fuse_biasadd_add": [49, 321], "fuse_column_wise_mul": [50, 322], "fuse_conv_redundant_dequant": [76, 347], "fuse_conv_requant": [77, 348], "fuse_conv_with_math": [51, 323], "fuse_decomposed_bn": [52, 324], "fuse_decomposed_in": [53, 325], "fuse_gelu": [54, 326], "fuse_layer_norm": [55, 327], "fuse_matmul_redundant_dequant": [78, 349], "fuse_matmul_requant": [79, 350], "fuse_pad_with_conv": [56, 328], "fuse_pad_with_fp32_conv": [57, 329], "fuse_qdq_bn": [108, 363], "fuse_qdq_concatv2": [109, 364], "fuse_qdq_conv": [110, 365], "fuse_qdq_deconv": [111, 366], "fuse_qdq_in": [112, 367], "fuse_qdq_matmul": [113, 368], "fuse_qdq_pool": [114, 369], "fuse_reshape_transpos": [58, 330], "fx": 490, "gather": 13, "gaudi": 485, "gavgpool": 14, "gemm": 15, "gener": [38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 482, 494], "get": [470, 471, 472, 473, 475, 476, 478, 483, 490, 492, 493, 518, 521, 523, 524, 528, 529, 535, 537, 539, 540, 541, 542, 544], "gptq": [420, 476], "gpu": [492, 532], "graph": 494, "graph_bas": [71, 343], "graph_convert": [33, 306], "graph_converter_without_calib": 34, "graph_cse_optim": [59, 331], "graph_rewrit": [35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359], "graph_transform_bas": [129, 381], "graph_util": [95, 360], "grappler_pass": [60, 332], "guid": 469, "guidelin": 489, "half_precision_convert": 399, "half_precision_rewrit": 406, "hardwar": [473, 532, 537, 553], "hawq_metr": 135, "hawq_v2": [269, 552], "heterogen": 532, "horovodrun": 524, "how": [481, 494, 495], "hpo": [167, 168], "hpu": [492, 532], "hqq": [421, 422, 423, 424, 425, 426, 427, 476], "hyperparamet": 542, "imag": [492, 532], "imagenet_dataset": 214, "imagenet_transform": 221, "implement": [493, 494], "import": 520, "inc": 520, "incompat": [530, 548], "infer": 524, "inform": 533, "infrastructur": 531, "insert_log": [131, 383], "insert_print_nod": [62, 334], "insert_qdq_pattern": [92, 357], "instal": [492, 532], "int4": 495, "int8": [73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 526, 553], "intel": [468, 485, 492, 521, 531, 532, 535, 536, 554], "intel_extension_for_pytorch": [492, 532], "interfac": 520, "intern": 520, "introduct": [470, 471, 472, 473, 474, 475, 476, 477, 478, 479, 480, 482, 483, 487, 490, 493, 494, 495, 518, 519, 521, 523, 524, 526, 528, 531, 535, 537, 538, 539, 540, 541, 542, 544, 545, 547, 549, 550, 551, 552], "invok": 495, "ipex": [475, 487, 544], "issu": [527, 548], "iter": 494, "json": 520, "kera": [288, 291, 292, 293, 294, 295, 296, 297, 298, 299, 300], "keras_model": 238, "kernel": 495, "kit": 532, "kl_diverg": 460, "knowledg": 553, "known": 548, "languag": [492, 534, 542], "larg": [492, 534, 542], "latenc": 482, "layer": [292, 293, 294, 295, 296, 297, 298, 476, 545, 550], "layer_initi": 296, "layer_wis": [395, 396, 397, 398], "layer_wise_qu": [137, 138, 139, 140, 141], "legal": 533, "licens": 533, "like": [477, 495], "limit": [487, 550], "line": 495, "list": [494, 525, 551], "llm": [492, 534], "load": [396, 476, 477, 492], "load_entri": 441, "load_huggingfac": 461, "logger": [159, 393, 462, 520], "lstm": 17, "lwq": 545, "map": 485, "matmul": [18, 487, 550], "matrix": [473, 474, 476, 477, 480, 482, 490, 493, 518, 519, 521, 523, 524, 526, 528, 529, 531, 535, 537, 538, 539, 540, 541, 542, 544, 545, 547, 550], "maxpool": 19, "merge_duplicated_qdq": [93, 358], "meta_op_optim": [81, 352], "metric": [227, 228, 229, 230, 231, 232, 233, 234, 530, 535], "mha": [177, 184], "microsc": [472, 539], "migrat": 536, "mix": [473, 480, 506, 536, 537, 546], "mix_precis": 235, "mixed_precis": [399, 400, 401], "mme": 532, "mode": [490, 553], "model": [236, 237, 238, 239, 240, 241, 242, 243, 244, 389, 474, 475, 481, 492, 494, 507, 526, 532, 534, 536, 538, 539, 542, 545, 547, 550, 553], "model_slim": [171, 172, 173, 174], "model_wrapp": [142, 390], "modified_pickl": [138, 397], "modul": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 73, 74, 75, 76, 77, 78, 79, 81, 82, 83, 84, 85, 87, 88, 89, 90, 92, 93, 94, 95, 98, 100, 101, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 131, 132, 133, 134, 135, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 149, 150, 151, 152, 153, 154, 156, 157, 159, 160, 161, 162, 163, 165, 166, 169, 171, 173, 174, 175, 177, 178, 179, 180, 181, 182, 184, 185, 186, 187, 188, 189, 190, 191, 192, 194, 195, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 216, 217, 218, 221, 223, 224, 225, 227, 228, 230, 231, 232, 234, 235, 236, 238, 239, 240, 241, 242, 243, 244, 245, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 271, 272, 273, 274, 277, 278, 279, 280, 281, 283, 284, 286, 288, 289, 292, 293, 294, 297, 298, 299, 301, 302, 303, 305, 306, 307, 308, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 345, 346, 347, 348, 349, 350, 352, 353, 354, 355, 357, 358, 359, 360, 363, 364, 365, 366, 367, 368, 369, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 383, 384, 385, 387, 389, 390, 391, 392, 396, 397, 398, 399, 401, 403, 404, 405, 406, 408, 409, 411, 412, 413, 415, 416, 417, 418, 419, 420, 421, 422, 423, 425, 426, 427, 429, 430, 431, 432, 433, 435, 437, 438, 439, 441, 442, 443, 444, 445, 447, 448, 451, 452, 454, 456, 457, 458, 460, 461, 462, 463, 464, 465, 466], "module_wrapp": 401, "move_squeeze_after_relu": [63, 335], "mse": [271, 552], "mse_v2": [272, 552], "multipl": [532, 540, 553], "mx": 403, "mx_quant": [402, 403, 404], "mxnet": [535, 544, 551], "mxnet_dataload": 204, "mxnet_model": 240, "mxnet_util": [0, 1], "need": 494, "nets_factori": 241, "network": 542, "neural": [468, 485, 490, 492, 521, 531, 532, 535, 536, 542, 549, 554], "neural_compressor": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227, 228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 270, 271, 272, 273, 274, 275, 276, 277, 278, 279, 280, 281, 282, 283, 284, 285, 286, 287, 288, 289, 290, 291, 292, 293, 294, 295, 296, 297, 298, 299, 300, 301, 302, 303, 304, 305, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 360, 361, 362, 363, 364, 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 382, 383, 384, 385, 386, 387, 388, 389, 390, 391, 392, 393, 394, 395, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413, 414, 415, 416, 417, 418, 419, 420, 421, 422, 423, 424, 425, 426, 427, 428, 429, 430, 431, 432, 433, 434, 435, 436, 437, 438, 439, 440, 441, 442, 443, 444, 445, 446, 447, 448, 449, 450, 451, 452, 453, 454, 455, 456, 457, 458, 459, 460, 461, 462, 463, 464, 465, 466, 467], "new": [492, 493, 495, 552], "ninm": 178, "norm": 20, "note": [490, 548], "nxm": 179, "object": [245, 508, 540], "off": 546, "onli": [476, 487, 492, 547], "onnx": [86, 87, 88, 89, 90, 497, 532, 544, 545, 553], "onnx_graph": 87, "onnx_model": 242, "onnx_nod": 88, "onnx_pars": [248, 249], "onnx_schema": 89, "onnxrt": [535, 551], "onnxrt_dataload": 205, "onnxrt_profil": [255, 256, 257], "onnxrtadaptor": 493, "op": [21, 526], "oper": [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 494, 495], "optim": [165, 425, 541, 542], "optimize_lay": 103, "optimize_qdq": [116, 371], "option": [463, 524], "orchestr": [536, 541], "other": [492, 532], "our": [488, 550], "overview": [469, 481, 489], "ox_util": [2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31], "packag": [170, 176, 183], "pad": 22, "paramet": 471, "parser": [247, 248, 249, 250, 251, 252, 253], "pattern": [175, 176, 177, 178, 179, 542], "pattern_analyz": 173, "pattern_detector": 143, "pattern_lock": 185, "per": [487, 550], "perform": 549, "platform": [492, 532, 549], "pledg": 488, "polici": [491, 552], "pool": 23, "pool2d": 297, "post": [480, 490, 536, 544], "post_hostconst_convert": [82, 353], "post_quantized_op_cs": [83, 354], "postprocess": 223, "pre_optim": [64, 336], "precis": [473, 480, 506, 536, 537, 546], "prepar": [494, 549], "prerequisit": 532, "problem": [477, 490], "process": 552, "processor": 532, "profil": [246, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261], "progress": 186, "prune": [188, 536, 542, 553], "pruner": [169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194], "pt2e": 475, "pt2e_export": 435, "pt2e_quant": [405, 406, 407, 408, 409], "ptq": 553, "public": [492, 520, 543], "pull": 489, "pure": 524, "pypi": 492, "python": [469, 521, 535], "pytorch": [464, 473, 474, 475, 476, 481, 487, 514, 515, 516, 524, 526, 535, 544, 545, 546, 551, 553], "pytorch_dataload": 206, "qat": [98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 553], "qdq": [91, 92, 93, 94, 108, 109, 110, 111, 112, 113, 114, 115, 116, 356, 357, 358, 359, 363, 364, 365, 366, 367, 368, 369, 370, 371, 553], "qlinear2qdq": 456, "qtensor": 426, "quant": [479, 550], "quantiz": [28, 139, 262, 299, 300, 301, 302, 303, 304, 305, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 360, 361, 362, 363, 364, 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 382, 383, 384, 385, 427, 437, 438, 439, 440, 441, 442, 449, 470, 471, 472, 474, 475, 476, 477, 478, 480, 483, 487, 490, 492, 494, 495, 509, 511, 512, 513, 514, 515, 516, 519, 523, 526, 532, 534, 536, 537, 539, 544, 545, 546, 547, 550, 553], "quantization_config": 451, "quantize_config": 100, "quantize_graph": [97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 362, 363, 364, 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377, 378], "quantize_graph_bas": [117, 372], "quantize_graph_bn": [118, 373], "quantize_graph_common": [124, 379], "quantize_graph_concatv2": [119, 374], "quantize_graph_conv": [120, 375], "quantize_graph_for_intel_cpu": [121, 376], "quantize_graph_matmul": [122, 377], "quantize_graph_pool": [123, 378], "quantize_help": 101, "quantize_lay": [102, 103, 104, 105, 106], "quantize_layer_add": 104, "quantize_layer_bas": 105, "quantize_layer_bn": 106, "quantize_wrapp": 107, "queri": 493, "query_fw_cap": 494, "question": 527, "quick": 529, "random": [273, 552], "rang": 494, "recip": [534, 544], "recommend": 520, "reduc": 24, "refer": [472, 476, 487, 519, 520, 539, 542, 544, 547, 550], "reg": 189, "regular": 542, "releas": [525, 548], "remove_training_nod": [65, 337], "rename_batch_norm": [66, 338], "report": 491, "request": [473, 489, 537], "requir": 532, "rerange_quantized_concat": [132, 384], "resiz": 25, "respons": 488, "result": 251, "retrain": 542, "retrain_fre": 187, "rnn_convert": 84, "rtn": [430, 476], "rule": [474, 475, 476, 478, 520, 544], "run": 494, "runtim": [497, 532, 544, 545, 553], "sa_optim": 168, "sampl": [475, 494, 529], "sampler": 207, "save": 476, "save_load": [160, 408, 411, 415, 431], "scale_propag": [85, 355], "scaler": 286, "schedul": [190, 542], "scheme": [480, 487, 544], "scope": [488, 542], "section": [468, 554], "secur": [491, 524], "select": 492, "separable_conv2d": 298, "set": 520, "share_qdq_y_pattern": [94, 359], "shot": 541, "side": 476, "sigopt": [198, 549, 552], "singl": 540, "smooth": [474, 479, 480, 487, 550], "smooth_quant": [29, 149, 410, 411, 412, 413], "smooth_quant_calibr": 125, "smooth_quant_scal": 126, "smoother": [283, 284, 285, 286], "smoothquant": 550, "softwar": [473, 485, 532, 537], "sourc": 532, "space": 552, "spars": 542, "sparsiti": 542, "specif": 495, "specifi": [474, 475, 476, 478, 544], "split": 26, "split_shared_input": [67, 339], "stack": 485, "standard": 488, "start": [470, 471, 472, 473, 475, 476, 478, 483, 490, 492, 493, 518, 521, 523, 524, 528, 529, 535, 537, 539, 540, 541, 542, 544], "static": [475, 480, 487, 490, 544], "static_qu": [287, 288, 289, 414, 415, 416, 417], "statu": 489, "step": 489, "strategi": [197, 198, 199, 263, 264, 265, 266, 267, 268, 269, 270, 271, 272, 273, 274, 275, 276, 277, 278, 279, 280, 510, 549, 552], "string": 520, "strip_equivalent_nod": [68, 340], "strip_unused_nod": [69, 341], "structur": 520, "style_transfer_dataset": 216, "submodul": [0, 4, 16, 37, 61, 72, 80, 86, 91, 96, 97, 99, 102, 115, 130, 136, 137, 148, 155, 158, 164, 167, 170, 172, 176, 183, 193, 197, 215, 219, 222, 226, 233, 237, 270, 276, 285, 287, 295, 300, 304, 309, 333, 344, 351, 356, 361, 362, 370, 382, 388, 394, 395, 400, 402, 407, 410, 414, 424, 428, 434, 440, 446, 450, 455, 459], "subpackag": [4, 72, 96, 97, 99, 136, 155, 170, 196, 220, 226, 270, 282, 290, 291, 304, 344, 361, 362, 394, 428, 436, 459], "summari": [482, 495], "support": [471, 473, 474, 476, 477, 480, 482, 489, 490, 493, 495, 518, 519, 521, 523, 524, 526, 528, 531, 532, 535, 537, 538, 539, 540, 541, 542, 544, 545, 547, 550, 551], "switch_optim": [70, 342], "symbolic_trac": 144, "symmetr": 487, "system": 532, "templat": [281, 489], "tensor": [487, 550], "tensorflow": [32, 282, 283, 284, 285, 286, 287, 288, 289, 290, 291, 292, 293, 294, 295, 296, 297, 298, 299, 300, 301, 302, 303, 304, 305, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 360, 361, 362, 363, 364, 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 382, 383, 384, 385, 386, 387, 388, 389, 390, 391, 478, 480, 481, 487, 492, 511, 512, 513, 524, 526, 532, 535, 544, 546, 551, 553], "tensorflow_dataload": 208, "tensorflow_model": 243, "tensorflow_pars": [252, 253], "tensorflow_profil": [259, 260, 261], "teq": [432, 476], "tf2onnx": 457, "tf2onnx_convert": 127, "tf2onnx_util": 90, "tf_criteria": 191, "tf_util": [33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133], "through": [479, 532, 550, 553], "throughput": 482, "todo": 520, "token": 224, "topic": 469, "torch": [392, 393, 394, 395, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413, 414, 415, 416, 417, 418, 419, 420, 421, 422, 423, 424, 425, 426, 427, 428, 429, 430, 431, 432, 433, 434, 435, 436, 437, 438, 439, 440, 441, 442, 443, 444, 445, 446, 447, 477, 492, 498, 532, 553], "torch2onnx": 458, "torch_load": 140, "torch_model": 244, "torch_util": [134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145], "tpc": 532, "tpe": [199, 552], "trademark": 533, "train": [448, 480, 487, 490, 517, 524, 536, 542, 544], "transform": [221, 222, 223, 224, 225, 449, 450, 451, 530, 551], "transform_graph": [128, 129, 130, 131, 132, 380, 381, 382, 383, 384], "tune": [478, 479, 487, 495, 544, 547, 550, 552], "tune_cfg": 494, "tuning_param": 156, "tuning_sampl": 277, "tuning_spac": 278, "tuning_struct": 279, "turn": 546, "two": 532, "type": [495, 520, 542], "unary_op": 27, "us": [479, 482, 492, 495, 521, 532, 535, 550], "usag": [471, 474, 475, 476, 479, 482, 550, 552], "user": [469, 524, 530, 547], "util": [1, 30, 133, 141, 145, 157, 158, 159, 160, 161, 166, 192, 194, 257, 261, 275, 276, 277, 278, 279, 280, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 360, 361, 362, 363, 364, 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 382, 383, 384, 385, 386, 387, 388, 389, 390, 391, 393, 398, 404, 409, 413, 417, 433, 443, 444, 445, 446, 447, 449, 450, 451, 452, 453, 454, 455, 456, 457, 458, 459, 460, 461, 462, 463, 464, 465, 466, 498], "v": 520, "v1": 530, "valid": [474, 532, 550, 553], "vendor": 532, "version": [467, 485], "vulner": 491, "wanda": [193, 194], "weight": [476, 487, 492, 547], "weight_correct": 150, "weight_onli": [31, 418, 419, 420, 421, 422, 423, 424, 425, 426, 427, 428, 429, 430, 431, 432, 433], "weight_slim": 174, "weights_detail": 466, "what": 492, "wise": [476, 545], "without": 478, "woq": [547, 553], "work": [481, 493, 544], "workflow": [484, 522], "x": [469, 536], "xe": 532, "yaml": [494, 524, 528]}}) \ No newline at end of file +Search.setIndex({"alltitles": {"2.0 API": [[499, "api"]], "2.X API User Guide": [[469, "x-api-user-guide"]], "2018 - 2020 (4)": [[543, "id5"]], "2021 (15)": [[543, "id4"]], "2022 (35)": [[543, "id3"]], "2023 (25)": [[543, "id2"]], "2024 (5)": [[543, "id1"]], "3.0 API": [[500, "api"]], "API Document Example": [[501, "api-document-example"]], "API List that Need to Implement": [[494, "api-list-that-need-to-implement"]], "API for TensorFlow": [[480, "api-for-tensorflow"]], "APIs": [[502, "apis"]], "AWQ": [[476, "awq"]], "Accuracy Aware Tuning": [[487, "accuracy-aware-tuning"], [544, "accuracy-aware-tuning"]], "Accuracy Criteria": [[552, "accuracy-criteria"]], "Accuracy-driven mixed precision": [[473, "accuracy-driven-mixed-precision"], [537, "accuracy-driven-mixed-precision"]], "Adaptor": [[493, "adaptor"], [496, "adaptor"]], "Adaptor Support Matrix": [[493, "adaptor-support-matrix"]], "Add quantize API according to tune_cfg": [[494, "add-quantize-api-according-to-tune-cfg"]], "Add query_fw_capability to Adaptor": [[494, "add-query-fw-capability-to-adaptor"]], "Additional Content": [[492, "additional-content"]], "Advanced Topics": [[469, "advanced-topics"]], "Algorithm: Auto-tuning of $\\alpha$.": [[550, "algorithm-auto-tuning-of-alpha"]], "Appendix": [[526, "appendix"]], "Architecture": [[484, "architecture"], [522, "architecture"], [531, "architecture"]], "Attributes": [[211, "attributes"], [281, "attributes"]], "Attribution": [[488, "attribution"]], "Auto": [[552, "auto"]], "Auto-tune the alpha for each layer/block": [[550, "auto-tune-the-alpha-for-each-layer-block"]], "Auto-tune the alpha for the entire model": [[550, "auto-tune-the-alpha-for-the-entire-model"]], "AutoRound": [[476, "autoround"]], "AutoTune": [[481, "autotune"]], "Autotune API": [[477, "autotune-api"]], "Backend and Device": [[480, "backend-and-device"]], "Background": [[493, "background"], [520, "background"]], "Basic": [[552, "basic"]], "Bayesian": [[552, "bayesian"]], "Benchmark": [[482, "benchmark"], [503, "benchmark"], [536, "benchmark"]], "Benchmark Support Matrix": [[518, "benchmark-support-matrix"]], "Benchmarking": [[518, "benchmarking"]], "Benefit of SigOpt Strategy": [[549, "benefit-of-sigopt-strategy"]], "Build Custom Dataloader with Python API": [[521, "build-custom-dataloader-with-python-api"]], "Build Custom Metric with Python API": [[535, "build-custom-metric-with-python-api"]], "Built-in transform/dataset/metric APIs": [[530, "built-in-transform-dataset-metric-apis"]], "Calculate the data range and generate quantized model": [[494, "calculate-the-data-range-and-generate-quantized-model"]], "Calibration Algorithms": [[519, "calibration-algorithms"]], "Calibration Algorithms in Quantization": [[519, "calibration-algorithms-in-quantization"]], "Capability": [[493, "capability"]], "Citation": [[533, "citation"]], "Classes": [[1, "classes"], [2, "classes"], [3, "classes"], [5, "classes"], [6, "classes"], [7, "classes"], [8, "classes"], [9, "classes"], [10, "classes"], [11, "classes"], [12, "classes"], [13, "classes"], [14, "classes"], [15, "classes"], [17, "classes"], [18, "classes"], [19, "classes"], [20, "classes"], [21, "classes"], [22, "classes"], [23, "classes"], [24, "classes"], [25, "classes"], [26, "classes"], [27, "classes"], [28, "classes"], [29, "classes"], [30, "classes"], [32, "classes"], [33, "classes"], [34, "classes"], [35, "classes"], [36, "classes"], [38, "classes"], [39, "classes"], [40, "classes"], [41, "classes"], [42, "classes"], [43, "classes"], [44, "classes"], [45, "classes"], [46, "classes"], [47, "classes"], [48, "classes"], [49, "classes"], [50, "classes"], [51, "classes"], [52, "classes"], [53, "classes"], [54, "classes"], [55, "classes"], [56, "classes"], [57, "classes"], [58, "classes"], [59, "classes"], [60, "classes"], [62, "classes"], [63, "classes"], [64, "classes"], [65, "classes"], [66, "classes"], [67, "classes"], [68, "classes"], [69, "classes"], [70, "classes"], [71, "classes"], [73, "classes"], [74, "classes"], [75, "classes"], [76, "classes"], [77, "classes"], [78, "classes"], [79, "classes"], [81, "classes"], [82, "classes"], [83, "classes"], [84, "classes"], [85, "classes"], [87, "classes"], [88, "classes"], [89, "classes"], [90, "classes"], [92, "classes"], [93, "classes"], [94, "classes"], [95, "classes"], [98, "classes"], [100, "classes"], [104, "classes"], [105, "classes"], [106, "classes"], [107, "classes"], [108, "classes"], [109, "classes"], [110, "classes"], [111, "classes"], [112, "classes"], [113, "classes"], [114, "classes"], [116, "classes"], [117, "classes"], [118, "classes"], [119, "classes"], [120, "classes"], [121, "classes"], [122, "classes"], [123, "classes"], [124, "classes"], [125, "classes"], [126, "classes"], [127, "classes"], [128, "classes"], [129, "classes"], [131, "classes"], [132, "classes"], [134, "classes"], [135, "classes"], [139, "classes"], [142, "classes"], [143, "classes"], [146, "classes"], [147, "classes"], [149, "classes"], [150, "classes"], [152, "classes"], [153, "classes"], [156, "classes"], [157, "classes"], [159, "classes"], [161, "classes"], [162, "classes"], [163, "classes"], [165, "classes"], [169, "classes"], [173, "classes"], [174, "classes"], [175, "classes"], [177, "classes"], [178, "classes"], [179, "classes"], [180, "classes"], [181, "classes"], [182, "classes"], [184, "classes"], [185, "classes"], [186, "classes"], [187, "classes"], [188, "classes"], [189, "classes"], [190, "classes"], [191, "classes"], [195, "classes"], [198, "classes"], [199, "classes"], [200, "classes"], [201, "classes"], [202, "classes"], [203, "classes"], [204, "classes"], [205, "classes"], [206, "classes"], [207, "classes"], [208, "classes"], [209, "classes"], [210, "classes"], [211, "classes"], [212, "classes"], [213, "classes"], [214, "classes"], [216, "classes"], [217, "classes"], [218, "classes"], [221, "classes"], [223, "classes"], [224, "classes"], [225, "classes"], [227, "classes"], [230, "classes"], [234, "classes"], [236, "classes"], [238, "classes"], [239, "classes"], [240, "classes"], [241, "classes"], [242, "classes"], [243, "classes"], [244, "classes"], [245, "classes"], [247, "classes"], [248, "classes"], [249, "classes"], [250, "classes"], [251, "classes"], [252, "classes"], [253, "classes"], [254, "classes"], [255, "classes"], [256, "classes"], [258, "classes"], [259, "classes"], [260, "classes"], [263, "classes"], [264, "classes"], [265, "classes"], [266, "classes"], [267, "classes"], [268, "classes"], [269, "classes"], [271, "classes"], [272, "classes"], [273, "classes"], [274, "classes"], [277, "classes"], [278, "classes"], [279, "classes"], [280, "classes"], [281, "classes"], [283, "classes"], [284, "classes"], [286, "classes"], [288, "classes"], [289, "classes"], [292, "classes"], [293, "classes"], [294, "classes"], [297, "classes"], [298, "classes"], [299, "classes"], [303, "classes"], [306, "classes"], [307, "classes"], [308, "classes"], [310, "classes"], [311, "classes"], [312, "classes"], [313, "classes"], [314, "classes"], [315, "classes"], [316, "classes"], [317, "classes"], [318, "classes"], [319, "classes"], [320, "classes"], [321, "classes"], [322, "classes"], [323, "classes"], [324, "classes"], [325, "classes"], [326, "classes"], [327, "classes"], [328, "classes"], [329, "classes"], [330, "classes"], [331, "classes"], [332, "classes"], [334, "classes"], [335, "classes"], [336, "classes"], [337, "classes"], [338, "classes"], [339, "classes"], [340, "classes"], [341, "classes"], [342, "classes"], [343, "classes"], [345, "classes"], [346, "classes"], [347, "classes"], [348, "classes"], [349, "classes"], [350, "classes"], [352, "classes"], [353, "classes"], [354, "classes"], [355, "classes"], [357, "classes"], [358, "classes"], [359, "classes"], [360, "classes"], [363, "classes"], [364, "classes"], [365, "classes"], [366, "classes"], [367, "classes"], [368, "classes"], [369, "classes"], [371, "classes"], [372, "classes"], [373, "classes"], [374, "classes"], [375, "classes"], [376, "classes"], [377, "classes"], [378, "classes"], [379, "classes"], [380, "classes"], [381, "classes"], [383, "classes"], [384, "classes"], [387, "classes"], [389, "classes"], [390, "classes"], [391, "classes"], [392, "classes"], [398, "classes"], [399, "classes"], [401, "classes"], [403, "classes"], [404, "classes"], [405, "classes"], [406, "classes"], [412, "classes"], [413, "classes"], [416, "classes"], [417, "classes"], [418, "classes"], [419, "classes"], [420, "classes"], [421, "classes"], [422, "classes"], [423, "classes"], [426, "classes"], [427, "classes"], [429, "classes"], [430, "classes"], [431, "classes"], [432, "classes"], [433, "classes"], [439, "classes"], [443, "classes"], [444, "classes"], [448, "classes"], [451, "classes"], [452, "classes"], [460, "classes"], [461, "classes"], [462, "classes"], [463, "classes"], [465, "classes"], [466, "classes"]], "Code Migration from Intel Neural Compressor 1.X to Intel Neural Compressor 2.X": [[536, "code-migration-from-intel-neural-compressor-1-x-to-intel-neural-compressor-2-x"]], "Comments": [[520, "comments"]], "Common Build Issues": [[527, "common-build-issues"]], "Common Problem": [[490, "common-problem"]], "Common Problems": [[477, "common-problems"]], "Common arguments": [[476, "common-arguments"]], "Communication": [[492, "communication"]], "Compression": [[504, "compression"]], "Config": [[505, "config"]], "Config Multiple Objectives": [[540, "config-multiple-objectives"]], "Config Single Objective": [[540, "config-single-objective"]], "Conservative Tuning": [[552, "conservative-tuning"]], "Contribution Guidelines": [[489, "contribution-guidelines"]], "Contributor Covenant Code of Conduct": [[488, "contributor-covenant-code-of-conduct"], [489, "contributor-covenant-code-of-conduct"]], "Create Pull Request": [[489, "create-pull-request"]], "Customize a New Tuning Strategy": [[552, "customize-a-new-tuning-strategy"]], "DataLoader": [[521, "dataloader"]], "Define the Quantization Ability of the Specific Operator": [[495, "define-the-quantization-ability-of-the-specific-operator"]], "Demo Usage": [[471, "demo-usage"]], "Demo usage": [[482, "demo-usage"]], "Design": [[484, "design"], [522, "design"], [552, "design"], [552, "id1"], [552, "id3"], [552, "id5"], [552, "id7"], [552, "id9"], [552, "id11"], [552, "id13"], [552, "id15"], [552, "id17"], [552, "id19"], [552, "id21"]], "Design the framework YAML": [[494, "design-the-framework-yaml"]], "Details": [[490, "details"]], "Determining the alpha through auto-tuning": [[479, "determining-the-alpha-through-auto-tuning"], [550, "determining-the-alpha-through-auto-tuning"]], "Distillation": [[536, "distillation"]], "Distillation for Quantization": [[523, "distillation-for-quantization"]], "Distillation for Quantization Support Matrix": [[523, "distillation-for-quantization-support-matrix"]], "Distributed Training and Inference (Evaluation)": [[524, "distributed-training-and-inference-evaluation"]], "Distributed Tuning": [[552, "distributed-tuning"]], "Documentation": [[492, "documentation"]], "Dump Throughput and Latency Summary": [[482, "dump-throughput-and-latency-summary"]], "During quantization mixed precision": [[537, "during-quantization-mixed-precision"]], "Dynamic Quantization": [[470, "dynamic-quantization"], [487, "dynamic-quantization"], [490, "dynamic-quantization"]], "Efficient Usage on Client-Side": [[476, "efficient-usage-on-client-side"]], "Enforcement": [[488, "enforcement"]], "Engineering": [[550, "engineering"]], "Example": [[535, "example"], [540, "example"]], "Example List": [[525, "example-list"]], "Example of Adding a New Backend Support": [[493, "example-of-adding-a-new-backend-support"]], "Examples": [[470, "examples"], [471, "examples"], [472, "examples"], [473, "examples"], [476, "examples"], [478, "examples"], [479, "examples"], [490, "examples"], [518, "examples"], [521, "examples"], [523, "examples"], [524, "examples"], [525, "examples"], [526, "examples"], [536, "examples"], [537, "examples"], [538, "examples"], [539, "examples"], [541, "examples"], [542, "examples"], [544, "examples"], [545, "examples"], [547, "examples"]], "Exceptions": [[138, "exceptions"], [397, "exceptions"]], "Exhaustive": [[552, "exhaustive"]], "Exit Policy": [[552, "exit-policy"]], "Export": [[526, "export"]], "Export Compressed Model": [[547, "export-compressed-model"]], "FP32 Model Export": [[526, "fp32-model-export"], [526, "id1"]], "FP8 Quantization": [[471, "fp8-quantization"], [492, "fp8-quantization"]], "FX": [[490, "fx"]], "FX Mode Support Matrix in Neural Compressor": [[490, "fx-mode-support-matrix-in-neural-compressor"]], "Feature Matrix": [[529, "feature-matrix"]], "Fixed Alpha": [[474, "fixed-alpha"]], "Folder structure": [[520, "folder-structure"]], "Framework YAML Configuration Files": [[528, "framework-yaml-configuration-files"]], "Frequently Asked Questions": [[527, "frequently-asked-questions"]], "Full Publications/Events (84)": [[543, "full-publications-events-84"]], "Functions": [[1, "functions"], [3, "functions"], [21, "functions"], [29, "functions"], [30, "functions"], [31, "functions"], [52, "functions"], [53, "functions"], [55, "functions"], [89, "functions"], [90, "functions"], [101, "functions"], [103, "functions"], [133, "functions"], [134, "functions"], [135, "functions"], [140, "functions"], [141, "functions"], [144, "functions"], [145, "functions"], [146, "functions"], [151, "functions"], [152, "functions"], [153, "functions"], [154, "functions"], [160, "functions"], [161, "functions"], [163, "functions"], [165, "functions"], [166, "functions"], [169, "functions"], [170, "functions"], [171, "functions"], [173, "functions"], [175, "functions"], [176, "functions"], [180, "functions"], [183, "functions"], [188, "functions"], [189, "functions"], [190, "functions"], [191, "functions"], [192, "functions"], [194, "functions"], [201, "functions"], [202, "functions"], [209, "functions"], [211, "functions"], [218, "functions"], [224, "functions"], [225, "functions"], [227, "functions"], [228, "functions"], [230, "functions"], [231, "functions"], [232, "functions"], [234, "functions"], [235, "functions"], [239, "functions"], [243, "functions"], [245, "functions"], [257, "functions"], [261, "functions"], [262, "functions"], [266, "functions"], [274, "functions"], [278, "functions"], [280, "functions"], [281, "functions"], [292, "functions"], [293, "functions"], [294, "functions"], [297, "functions"], [298, "functions"], [299, "functions"], [301, "functions"], [302, "functions"], [303, "functions"], [305, "functions"], [324, "functions"], [325, "functions"], [327, "functions"], [385, "functions"], [387, "functions"], [390, "functions"], [391, "functions"], [396, "functions"], [398, "functions"], [404, "functions"], [406, "functions"], [408, "functions"], [409, "functions"], [411, "functions"], [412, "functions"], [413, "functions"], [415, "functions"], [417, "functions"], [418, "functions"], [420, "functions"], [425, "functions"], [427, "functions"], [431, "functions"], [433, "functions"], [435, "functions"], [437, "functions"], [438, "functions"], [439, "functions"], [441, "functions"], [442, "functions"], [443, "functions"], [445, "functions"], [447, "functions"], [448, "functions"], [454, "functions"], [456, "functions"], [457, "functions"], [458, "functions"], [461, "functions"], [462, "functions"], [464, "functions"], [465, "functions"]], "GPTQ": [[476, "gptq"]], "General Use Cases": [[482, "general-use-cases"]], "Get Start with FP8 Quantization": [[471, "get-start-with-fp8-quantization"]], "Get Started": [[475, "get-started"], [476, "get-started"], [478, "get-started"], [483, "get-started"], [490, "get-started"], [544, "get-started"]], "Get Started with Adaptor API": [[493, "get-started-with-adaptor-api"]], "Get Started with Benchmark API": [[518, "get-started-with-benchmark-api"]], "Get Started with DataLoader": [[521, "get-started-with-dataloader"]], "Get Started with Distillation for Quantization API": [[523, "get-started-with-distillation-for-quantization-api"]], "Get Started with Distributed Training and Inference API": [[524, "get-started-with-distributed-training-and-inference-api"]], "Get Started with Metric": [[535, "get-started-with-metric"]], "Get Started with Microscaling Quantization API": [[472, "get-started-with-microscaling-quantization-api"], [539, "get-started-with-microscaling-quantization-api"]], "Get Started with Mixed Precision API": [[537, "get-started-with-mixed-precision-api"]], "Get Started with Objective API": [[540, "get-started-with-objective-api"]], "Get Started with Orchestration API": [[541, "get-started-with-orchestration-api"]], "Get Started with Pruning API": [[542, "get-started-with-pruning-api"]], "Get Started with autotune API": [[473, "get-started-with-autotune-api"]], "Get started with Framework YAML Files": [[528, "get-started-with-framework-yaml-files"]], "Getting Started": [[492, "getting-started"], [529, "getting-started"]], "Getting Started with Dynamic Quantization": [[470, "getting-started-with-dynamic-quantization"]], "HAWQ_V2": [[552, "hawq-v2"]], "HQQ": [[476, "hqq"]], "Hardware and Software requests for BF16": [[473, "hardware-and-software-requests-for-bf16"], [537, "hardware-and-software-requests-for-bf16"]], "Hardware and Software requests for FP16": [[473, "hardware-and-software-requests-for-fp16"], [537, "hardware-and-software-requests-for-fp16"]], "Horovodrun Execution": [[524, "horovodrun-execution"]], "How it Works": [[481, "how-it-works"]], "How to Add An Adaptor": [[494, "how-to-add-an-adaptor"]], "How to Support New Data Type, Like Int4, with a Few Line Changes": [[495, "how-to-support-new-data-type-like-int4-with-a-few-line-changes"]], "INC Coding Conventions": [[520, "inc-coding-conventions"]], "INT8 Model Export": [[526, "int8-model-export"], [526, "id2"]], "Implement ONNXRTAdaptor Class": [[493, "implement-onnxrtadaptor-class"]], "Imports": [[520, "imports"]], "Incompatible Changes": [[548, "incompatible-changes"]], "Incompatible changes between v1.2 and v1.1": [[530, "incompatible-changes-between-v1-2-and-v1-1"]], "Infrastructure of Intel\u00ae Neural Compressor": [[531, "infrastructure-of-intel-neural-compressor"]], "Install Framework": [[492, "install-framework"], [532, "install-framework"]], "Install from AI Kit": [[532, "install-from-ai-kit"]], "Install from Binary": [[532, "install-from-binary"]], "Install from Source": [[532, "install-from-source"]], "Install from pypi": [[492, "install-from-pypi"]], "Install tensorflow": [[492, "install-tensorflow"], [532, "install-tensorflow"]], "Install torch for CPU": [[492, "install-torch-for-cpu"], [532, "install-torch-for-cpu"]], "Install torch for other platform": [[492, "install-torch-for-other-platform"], [532, "install-torch-for-other-platform"]], "Install torch/intel_extension_for_pytorch for Intel GPU": [[492, "install-torch-intel-extension-for-pytorch-for-intel-gpu"], [532, "install-torch-intel-extension-for-pytorch-for-intel-gpu"]], "Installation": [[492, "installation"], [532, "installation"], [532, "id1"]], "Intel\u00ae Neural Compressor": [[492, "intel-neural-compressor"]], "Intel\u00ae Neural Compressor Documentation": [[468, "intel-neural-compressor-documentation"], [554, "intel-neural-compressor-documentation"]], "Intel\u00ae Neural Compressor quantized ONNX models support multiple hardware vendors through ONNX Runtime:": [[532, "intel-neural-compressor-quantized-onnx-models-support-multiple-hardware-vendors-through-onnx-runtime"]], "Intel\u00ae Neural Compressor supports CPUs based on Intel 64 architecture or compatible processors:": [[532, "intel-neural-compressor-supports-cpus-based-on-intel-64-architecture-or-compatible-processors"]], "Intel\u00ae Neural Compressor supports GPUs built on Intel\u2019s Xe architecture:": [[532, "intel-neural-compressor-supports-gpus-built-on-intel-s-xe-architecture"]], "Intel\u00ae Neural Compressor supports HPUs based on heterogeneous architecture with two compute engines (MME and TPC):": [[532, "intel-neural-compressor-supports-hpus-based-on-heterogeneous-architecture-with-two-compute-engines-mme-and-tpc"]], "Introduction": [[470, "introduction"], [471, "introduction"], [472, "introduction"], [473, "introduction"], [474, "introduction"], [475, "introduction"], [476, "introduction"], [477, "introduction"], [478, "introduction"], [479, "introduction"], [480, "introduction"], [482, "introduction"], [483, "introduction"], [487, "introduction"], [490, "introduction"], [493, "introduction"], [494, "introduction"], [495, "introduction"], [518, "introduction"], [519, "introduction"], [521, "introduction"], [523, "introduction"], [524, "introduction"], [526, "introduction"], [528, "introduction"], [531, "introduction"], [535, "introduction"], [537, "introduction"], [538, "introduction"], [539, "introduction"], [540, "introduction"], [541, "introduction"], [542, "introduction"], [545, "introduction"], [547, "introduction"], [549, "introduction"], [550, "introduction"], [551, "introduction"], [552, "introduction"]], "Invoke the Operator Kernel According to the Tuning Configuration": [[495, "invoke-the-operator-kernel-according-to-the-tuning-configuration"]], "Issue 1:": [[527, "issue-1"]], "Issue 2:": [[527, "issue-2"]], "Issue 3:": [[527, "issue-3"]], "Issue 4:": [[527, "issue-4"]], "Issue 5:": [[527, "issue-5"]], "Known Issues": [[548, "known-issues"]], "LLMs Quantization Recipes": [[534, "llms-quantization-recipes"]], "Large Language Model Pruning": [[542, "large-language-model-pruning"]], "Large Language Models Accuracy": [[534, "large-language-models-accuracy"]], "Large Language Models Recipes": [[534, "large-language-models-recipes"]], "Layer Wise Quantization": [[476, "layer-wise-quantization"]], "Layer Wise Quantization (LWQ)": [[545, "layer-wise-quantization-lwq"]], "Legal Information": [[533, "legal-information"]], "License": [[533, "license"]], "Load API": [[477, "load-api"]], "Logger": [[520, "logger"]], "MSE": [[552, "mse"]], "MSE_V2": [[552, "mse-v2"]], "MXNet": [[535, "mxnet"], [551, "mxnet"]], "Matmul quantization example": [[487, "matmul-quantization-example"], [550, "matmul-quantization-example"]], "Metrics": [[535, "metrics"]], "Microscaling Quantization": [[472, "microscaling-quantization"], [539, "microscaling-quantization"]], "Mix Precision": [[506, "mix-precision"], [536, "mix-precision"]], "Mixed Precision": [[480, "mixed-precision"], [537, "mixed-precision"]], "Mixed Precision Support Matrix": [[473, "mixed-precision-support-matrix"], [537, "mixed-precision-support-matrix"]], "Model": [[507, "model"], [538, "model"]], "Model Examples": [[475, "model-examples"]], "Model Examples with PT2E": [[475, "model-examples-with-pt2e"]], "Model Quantization": [[536, "model-quantization"]], "Module Contents": [[1, "module-contents"], [2, "module-contents"], [3, "module-contents"], [5, "module-contents"], [6, "module-contents"], [7, "module-contents"], [8, "module-contents"], [9, "module-contents"], [10, "module-contents"], [11, "module-contents"], [12, "module-contents"], [13, "module-contents"], [14, "module-contents"], [15, "module-contents"], [17, "module-contents"], [18, "module-contents"], [19, "module-contents"], [20, "module-contents"], [21, "module-contents"], [22, "module-contents"], [23, "module-contents"], [24, "module-contents"], [25, "module-contents"], [26, "module-contents"], [27, "module-contents"], [28, "module-contents"], [29, "module-contents"], [30, "module-contents"], [31, "module-contents"], [32, "module-contents"], [33, "module-contents"], [34, "module-contents"], [35, "module-contents"], [36, "module-contents"], [38, "module-contents"], [39, "module-contents"], [40, "module-contents"], [41, "module-contents"], [42, "module-contents"], [43, "module-contents"], [44, "module-contents"], [45, "module-contents"], [46, "module-contents"], [47, "module-contents"], [48, "module-contents"], [49, "module-contents"], [50, "module-contents"], [51, "module-contents"], [52, "module-contents"], [53, "module-contents"], [54, "module-contents"], [55, "module-contents"], [56, "module-contents"], [57, "module-contents"], [58, "module-contents"], [59, "module-contents"], [60, "module-contents"], [62, "module-contents"], [63, "module-contents"], [64, "module-contents"], [65, "module-contents"], [66, "module-contents"], [67, "module-contents"], [68, "module-contents"], [69, "module-contents"], [70, "module-contents"], [71, "module-contents"], [73, "module-contents"], [74, "module-contents"], [75, "module-contents"], [76, "module-contents"], [77, "module-contents"], [78, "module-contents"], [79, "module-contents"], [81, "module-contents"], [82, "module-contents"], [83, "module-contents"], [84, "module-contents"], [85, "module-contents"], [87, "module-contents"], [88, "module-contents"], [89, "module-contents"], [90, "module-contents"], [92, "module-contents"], [93, "module-contents"], [94, "module-contents"], [95, "module-contents"], [98, "module-contents"], [100, "module-contents"], [101, "module-contents"], [103, "module-contents"], [104, "module-contents"], [105, "module-contents"], [106, "module-contents"], [107, "module-contents"], [108, "module-contents"], [109, "module-contents"], [110, "module-contents"], [111, "module-contents"], [112, "module-contents"], [113, "module-contents"], [114, "module-contents"], [116, "module-contents"], [117, "module-contents"], [118, "module-contents"], [119, "module-contents"], [120, "module-contents"], [121, "module-contents"], [122, "module-contents"], [123, "module-contents"], [124, "module-contents"], [125, "module-contents"], [126, "module-contents"], [127, "module-contents"], [128, "module-contents"], [129, "module-contents"], [131, "module-contents"], [132, "module-contents"], [133, "module-contents"], [134, "module-contents"], [135, "module-contents"], [138, "module-contents"], [139, "module-contents"], [140, "module-contents"], [141, "module-contents"], [142, "module-contents"], [143, "module-contents"], [144, "module-contents"], [145, "module-contents"], [146, "module-contents"], [147, "module-contents"], [149, "module-contents"], [150, "module-contents"], [151, "module-contents"], [152, "module-contents"], [153, "module-contents"], [154, "module-contents"], [156, "module-contents"], [157, "module-contents"], [159, "module-contents"], [160, "module-contents"], [161, "module-contents"], [162, "module-contents"], [163, "module-contents"], [165, "module-contents"], [166, "module-contents"], [169, "module-contents"], [171, "module-contents"], [173, "module-contents"], [174, "module-contents"], [175, "module-contents"], [177, "module-contents"], [178, "module-contents"], [179, "module-contents"], [180, "module-contents"], [181, "module-contents"], [182, "module-contents"], [184, "module-contents"], [185, "module-contents"], [186, "module-contents"], [187, "module-contents"], [188, "module-contents"], [189, "module-contents"], [190, "module-contents"], [191, "module-contents"], [192, "module-contents"], [194, "module-contents"], [195, "module-contents"], [198, "module-contents"], [199, "module-contents"], [200, "module-contents"], [201, "module-contents"], [202, "module-contents"], [203, "module-contents"], [204, "module-contents"], [205, "module-contents"], [206, "module-contents"], [207, "module-contents"], [208, "module-contents"], [209, "module-contents"], [210, "module-contents"], [211, "module-contents"], [212, "module-contents"], [213, "module-contents"], [214, "module-contents"], [216, "module-contents"], [217, "module-contents"], [218, "module-contents"], [221, "module-contents"], [223, "module-contents"], [224, "module-contents"], [225, "module-contents"], [227, "module-contents"], [228, "module-contents"], [230, "module-contents"], [231, "module-contents"], [232, "module-contents"], [234, "module-contents"], [235, "module-contents"], [236, "module-contents"], [238, "module-contents"], [239, "module-contents"], [240, "module-contents"], [241, "module-contents"], [242, "module-contents"], [243, "module-contents"], [244, "module-contents"], [245, "module-contents"], [247, "module-contents"], [248, "module-contents"], [249, "module-contents"], [250, "module-contents"], [251, "module-contents"], [252, "module-contents"], [253, "module-contents"], [254, "module-contents"], [255, "module-contents"], [256, "module-contents"], [257, "module-contents"], [258, "module-contents"], [259, "module-contents"], [260, "module-contents"], [261, "module-contents"], [262, "module-contents"], [263, "module-contents"], [264, "module-contents"], [265, "module-contents"], [266, "module-contents"], [267, "module-contents"], [268, "module-contents"], [269, "module-contents"], [271, "module-contents"], [272, "module-contents"], [273, "module-contents"], [274, "module-contents"], [277, "module-contents"], [278, "module-contents"], [279, "module-contents"], [280, "module-contents"], [281, "module-contents"], [283, "module-contents"], [284, "module-contents"], [286, "module-contents"], [288, "module-contents"], [289, "module-contents"], [292, "module-contents"], [293, "module-contents"], [294, "module-contents"], [297, "module-contents"], [298, "module-contents"], [299, "module-contents"], [301, "module-contents"], [302, "module-contents"], [303, "module-contents"], [305, "module-contents"], [306, "module-contents"], [307, "module-contents"], [308, "module-contents"], [310, "module-contents"], [311, "module-contents"], [312, "module-contents"], [313, "module-contents"], [314, "module-contents"], [315, "module-contents"], [316, "module-contents"], [317, "module-contents"], [318, "module-contents"], [319, "module-contents"], [320, "module-contents"], [321, "module-contents"], [322, "module-contents"], [323, "module-contents"], [324, "module-contents"], [325, "module-contents"], [326, "module-contents"], [327, "module-contents"], [328, "module-contents"], [329, "module-contents"], [330, "module-contents"], [331, "module-contents"], [332, "module-contents"], [334, "module-contents"], [335, "module-contents"], [336, "module-contents"], [337, "module-contents"], [338, "module-contents"], [339, "module-contents"], [340, "module-contents"], [341, "module-contents"], [342, "module-contents"], [343, "module-contents"], [345, "module-contents"], [346, "module-contents"], [347, "module-contents"], [348, "module-contents"], [349, "module-contents"], [350, "module-contents"], [352, "module-contents"], [353, "module-contents"], [354, "module-contents"], [355, "module-contents"], [357, "module-contents"], [358, "module-contents"], [359, "module-contents"], [360, "module-contents"], [363, "module-contents"], [364, "module-contents"], [365, "module-contents"], [366, "module-contents"], [367, "module-contents"], [368, "module-contents"], [369, "module-contents"], [371, "module-contents"], [372, "module-contents"], [373, "module-contents"], [374, "module-contents"], [375, "module-contents"], [376, "module-contents"], [377, "module-contents"], [378, "module-contents"], [379, "module-contents"], [380, "module-contents"], [381, "module-contents"], [383, "module-contents"], [384, "module-contents"], [385, "module-contents"], [387, "module-contents"], [389, "module-contents"], [390, "module-contents"], [391, "module-contents"], [392, "module-contents"], [396, "module-contents"], [397, "module-contents"], [398, "module-contents"], [399, "module-contents"], [401, "module-contents"], [403, "module-contents"], [404, "module-contents"], [405, "module-contents"], [406, "module-contents"], [408, "module-contents"], [409, "module-contents"], [411, "module-contents"], [412, "module-contents"], [413, "module-contents"], [415, "module-contents"], [416, "module-contents"], [417, "module-contents"], [418, "module-contents"], [419, "module-contents"], [420, "module-contents"], [421, "module-contents"], [422, "module-contents"], [423, "module-contents"], [425, "module-contents"], [426, "module-contents"], [427, "module-contents"], [429, "module-contents"], [430, "module-contents"], [431, "module-contents"], [432, "module-contents"], [433, "module-contents"], [435, "module-contents"], [437, "module-contents"], [438, "module-contents"], [439, "module-contents"], [441, "module-contents"], [442, "module-contents"], [443, "module-contents"], [444, "module-contents"], [445, "module-contents"], [447, "module-contents"], [448, "module-contents"], [451, "module-contents"], [452, "module-contents"], [454, "module-contents"], [456, "module-contents"], [457, "module-contents"], [458, "module-contents"], [460, "module-contents"], [461, "module-contents"], [462, "module-contents"], [463, "module-contents"], [464, "module-contents"], [465, "module-contents"], [466, "module-contents"]], "Multiple Objectives": [[540, "multiple-objectives"]], "Neural Compressor Configuration": [[549, "neural-compressor-configuration"]], "Neural Network Pruning": [[542, "neural-network-pruning"]], "Note": [[490, "note"]], "ONNX Models with ONNX Runtime 1.15.0 in WOQ Mode": [[553, "onnx-models-with-onnx-runtime-1-15-0-in-woq-mode"]], "ONNX Models with ONNX Runtime 1.17.1": [[553, "onnx-models-with-onnx-runtime-1-17-1"]], "ONNX Runtime": [[497, "onnx-runtime"]], "ONNX Runtime framework example": [[545, "onnx-runtime-framework-example"]], "ONNXRT": [[535, "onnxrt"], [551, "onnxrt"]], "Objective": [[508, "objective"], [540, "objective"]], "Objective Support Matrix": [[540, "objective-support-matrix"]], "One-shot": [[541, "one-shot"]], "Optimization Orchestration": [[541, "optimization-orchestration"]], "Option 1: Pure Yaml Configuration": [[524, "option-1-pure-yaml-configuration"]], "Option 2: User Defined Training Function": [[524, "option-2-user-defined-training-function"]], "Orchestration": [[536, "orchestration"]], "Orchestration Support Matrix": [[541, "orchestration-support-matrix"]], "Our Pledge": [[488, "our-pledge"]], "Our Responsibilities": [[488, "our-responsibilities"]], "Our Standards": [[488, "our-standards"]], "Our enhancement:": [[550, "our-enhancement"]], "Overview": [[469, "overview"], [481, "overview"]], "Package Contents": [[170, "package-contents"], [176, "package-contents"], [183, "package-contents"]], "Per-channel example": [[487, "per-channel-example"], [550, "per-channel-example"]], "Per-channel limitation": [[487, "per-channel-limitation"], [550, "per-channel-limitation"]], "Per-tensor & Per-channel": [[487, "per-tensor-per-channel"], [550, "per-tensor-per-channel"]], "Per-tensor example": [[487, "per-tensor-example"], [550, "per-tensor-example"]], "Performance": [[549, "performance"]], "Performance Comparison of Different Strategies": [[549, "performance-comparison-of-different-strategies"]], "Post Training Dynamic Quantization": [[490, "post-training-dynamic-quantization"], [544, "post-training-dynamic-quantization"]], "Post Training Quantization": [[544, "post-training-quantization"]], "Post Training Static Quantization": [[480, "post-training-static-quantization"], [490, "post-training-static-quantization"], [544, "post-training-static-quantization"]], "Post-training Quantization": [[536, "post-training-quantization"]], "Preparation": [[549, "preparation"]], "Prepare calibration model from fp32 graph": [[494, "prepare-calibration-model-from-fp32-graph"]], "Prerequisites": [[532, "prerequisites"]], "Pruning": [[536, "pruning"], [542, "pruning"]], "Pruning Criteria": [[542, "pruning-criteria"]], "Pruning Patterns": [[542, "pruning-patterns"]], "Pruning Schedules": [[542, "pruning-schedules"]], "Pruning Scope": [[542, "pruning-scope"]], "Pruning Support Matrix": [[542, "pruning-support-matrix"]], "Pruning Types": [[542, "pruning-types"]], "Pruning with Hyperparameter Optimization": [[542, "pruning-with-hyperparameter-optimization"]], "Public and Internal Interfaces": [[520, "public-and-internal-interfaces"]], "Pull Request Acceptance Criteria": [[489, "pull-request-acceptance-criteria"]], "Pull Request Checklist": [[489, "pull-request-checklist"]], "Pull Request Status Checks Overview": [[489, "pull-request-status-checks-overview"]], "Pull Request Template": [[489, "pull-request-template"]], "PyTorch": [[535, "pytorch"], [546, "pytorch"]], "PyTorch Examples:": [[524, "pytorch-examples"]], "PyTorch Mixed Precision": [[473, "pytorch-mixed-precision"]], "PyTorch Model": [[526, "pytorch-model"]], "PyTorch Models with Torch 2.0.1+cpu in WOQ Mode": [[553, "pytorch-models-with-torch-2-0-1-cpu-in-woq-mode"]], "PyTorch Models with Torch 2.2.1+cpu in PTQ Mode": [[553, "pytorch-models-with-torch-2-2-1-cpu-in-ptq-mode"]], "PyTorch Models with Torch 2.2.1+cpu in QAT Mode": [[553, "pytorch-models-with-torch-2-2-1-cpu-in-qat-mode"]], "PyTorch Smooth Quantization": [[474, "pytorch-smooth-quantization"]], "PyTorch Static Quantization": [[475, "pytorch-static-quantization"]], "PyTorch Weight Only Quantization": [[476, "pytorch-weight-only-quantization"]], "PyTorch framework example": [[545, "pytorch-framework-example"]], "Python-based APIs": [[469, "python-based-apis"]], "Pytorch": [[551, "pytorch"]], "Pytorch Quantization AutoTune": [[514, "pytorch-quantization-autotune"]], "Pytorch Quantization Base API": [[515, "pytorch-quantization-base-api"]], "Pytorch Quantization Config": [[516, "pytorch-quantization-config"]], "Quantization": [[487, "quantization"], [509, "quantization"], [544, "quantization"]], "Quantization APIs": [[477, "quantization-apis"]], "Quantization Approaches": [[480, "quantization-approaches"], [544, "quantization-approaches"]], "Quantization Aware Training": [[487, "quantization-aware-training"], [536, "quantization-aware-training"], [544, "quantization-aware-training"], [544, "id1"]], "Quantization Capability": [[547, "quantization-capability"]], "Quantization Fundamentals": [[487, "quantization-fundamentals"], [544, "quantization-fundamentals"], [550, "quantization-fundamentals"]], "Quantization Introduction": [[544, "quantization-introduction"]], "Quantization Scheme": [[480, "quantization-scheme"]], "Quantization Scheme in IPEX": [[487, "quantization-scheme-in-ipex"], [544, "quantization-scheme-in-ipex"]], "Quantization Scheme in MXNet": [[544, "quantization-scheme-in-mxnet"]], "Quantization Scheme in ONNX Runtime": [[544, "quantization-scheme-in-onnx-runtime"]], "Quantization Scheme in PyTorch": [[487, "quantization-scheme-in-pytorch"], [544, "quantization-scheme-in-pytorch"]], "Quantization Scheme in TensorFlow": [[487, "quantization-scheme-in-tensorflow"], [544, "quantization-scheme-in-tensorflow"]], "Quantization Support Matrix": [[544, "quantization-support-matrix"]], "Quantization on Client": [[483, "quantization-on-client"]], "Quantization-Aware Training": [[490, "quantization-aware-training"]], "Query API": [[493, "query-api"]], "Query API Introduction": [[493, "query-api-introduction"]], "Quick Samples": [[529, "quick-samples"]], "RTN": [[476, "rtn"]], "Random": [[552, "random"]], "Recommend VS Code settings.json": [[520, "recommend-vs-code-settings-json"]], "Reference": [[472, "reference"], [476, "reference"], [487, "reference"], [519, "reference"], [520, "reference"], [539, "reference"], [542, "reference"], [544, "reference"], [547, "reference"], [550, "reference"]], "Regularization": [[542, "regularization"]], "Release": [[548, "release"]], "Release Data": [[525, "release-data"]], "Release Notes": [[548, "release-notes"]], "Report a Vulnerability": [[491, "report-a-vulnerability"]], "Retrain-free Pruning API": [[542, "retrain-free-pruning-api"]], "Rules": [[520, "rules"]], "Run sampling iterations of the fp32 graph to calibrate quantizable operators.": [[494, "run-sampling-iterations-of-the-fp32-graph-to-calibrate-quantizable-operators"]], "Saving and Loading": [[476, "saving-and-loading"]], "Scope": [[488, "scope"]], "Sections": [[468, "sections"], [554, "sections"]], "Security": [[524, "security"]], "Security Policy": [[491, "security-policy"]], "Selected Publications/Events": [[492, "selected-publications-events"]], "SigOpt": [[552, "sigopt"]], "SigOpt Platform": [[549, "sigopt-platform"]], "SigOpt Strategy": [[549, "sigopt-strategy"]], "Single Objective": [[540, "single-objective"]], "Smooth Quant": [[479, "smooth-quant"], [550, "smooth-quant"]], "Smooth Quantization": [[480, "smooth-quantization"], [487, "smooth-quantization"]], "SmoothQuant": [[550, "smoothquant"]], "SmoothQuant and Our Enhancement": [[550, "smoothquant-and-our-enhancement"]], "Sparse Model Deployment": [[542, "sparse-model-deployment"]], "Sparsity Decay Types": [[542, "sparsity-decay-types"]], "Specify Quantization Backend and Device": [[544, "specify-quantization-backend-and-device"]], "Specify Quantization Recipes": [[544, "specify-quantization-recipes"]], "Specify Quantization Rules": [[474, "specify-quantization-rules"], [475, "specify-quantization-rules"], [476, "specify-quantization-rules"], [478, "specify-quantization-rules"], [544, "specify-quantization-rules"]], "Static Quantization": [[487, "static-quantization"]], "Static Quantization & Quantization Aware Training": [[490, "static-quantization-quantization-aware-training"]], "Static Quantization with IPEX Backend": [[475, "static-quantization-with-ipex-backend"]], "Static Quantization with PT2E Backend": [[475, "static-quantization-with-pt2e-backend"]], "Step-by-Step guidelines": [[489, "step-by-step-guidelines"]], "Strategy": [[510, "strategy"]], "Strategy Design": [[552, "strategy-design"]], "Strings": [[520, "strings"]], "Submodules": [[0, "submodules"], [4, "submodules"], [16, "submodules"], [37, "submodules"], [61, "submodules"], [72, "submodules"], [80, "submodules"], [86, "submodules"], [91, "submodules"], [96, "submodules"], [97, "submodules"], [99, "submodules"], [102, "submodules"], [115, "submodules"], [130, "submodules"], [136, "submodules"], [137, "submodules"], [148, "submodules"], [155, "submodules"], [158, "submodules"], [164, "submodules"], [167, "submodules"], [170, "submodules"], [172, "submodules"], [176, "submodules"], [183, "submodules"], [193, "submodules"], [197, "submodules"], [215, "submodules"], [219, "submodules"], [222, "submodules"], [226, "submodules"], [233, "submodules"], [237, "submodules"], [270, "submodules"], [276, "submodules"], [285, "submodules"], [287, "submodules"], [295, "submodules"], [300, "submodules"], [304, "submodules"], [309, "submodules"], [333, "submodules"], [344, "submodules"], [351, "submodules"], [356, "submodules"], [361, "submodules"], [362, "submodules"], [370, "submodules"], [382, "submodules"], [388, "submodules"], [394, "submodules"], [395, "submodules"], [400, "submodules"], [402, "submodules"], [407, "submodules"], [410, "submodules"], [414, "submodules"], [424, "submodules"], [428, "submodules"], [434, "submodules"], [440, "submodules"], [446, "submodules"], [450, "submodules"], [455, "submodules"], [459, "submodules"]], "Subpackages": [[4, "subpackages"], [72, "subpackages"], [96, "subpackages"], [97, "subpackages"], [99, "subpackages"], [136, "subpackages"], [155, "subpackages"], [170, "subpackages"], [196, "subpackages"], [220, "subpackages"], [226, "subpackages"], [270, "subpackages"], [282, "subpackages"], [290, "subpackages"], [291, "subpackages"], [304, "subpackages"], [344, "subpackages"], [361, "subpackages"], [362, "subpackages"], [394, "subpackages"], [428, "subpackages"], [436, "subpackages"], [459, "subpackages"]], "Summary": [[495, "summary"]], "Support": [[489, "support"]], "Support Matrix": [[480, "support-matrix"], [519, "support-matrix"]], "Supported Built-in Metric Matrix": [[535, "supported-built-in-metric-matrix"]], "Supported Feature Matrix": [[524, "supported-feature-matrix"], [528, "supported-feature-matrix"], [531, "supported-feature-matrix"], [544, "supported-feature-matrix"]], "Supported Framework Dataloader Matrix": [[521, "supported-framework-dataloader-matrix"]], "Supported Framework Matrix": [[474, "supported-framework-matrix"], [550, "supported-framework-matrix"]], "Supported Framework Model Matrix": [[526, "supported-framework-model-matrix"], [538, "supported-framework-model-matrix"], [539, "supported-framework-model-matrix"], [545, "supported-framework-model-matrix"], [547, "supported-framework-model-matrix"]], "Supported Matrix": [[476, "supported-matrix"], [477, "supported-matrix"], [482, "supported-matrix"]], "Supported Parameters": [[471, "supported-parameters"]], "Supported quantized ops": [[526, "supported-quantized-ops"]], "Symmetric & Asymmetric": [[487, "symmetric-asymmetric"]], "System Requirements": [[532, "system-requirements"]], "TEQ": [[476, "teq"]], "TODO Comments": [[520, "todo-comments"]], "TPE": [[552, "tpe"]], "TensorFlow": [[480, "tensorflow"], [535, "tensorflow"], [551, "tensorflow"]], "TensorFlow Examples:": [[524, "tensorflow-examples"]], "TensorFlow Models with TensorFlow 2.15.0": [[553, "tensorflow-models-with-tensorflow-2-15-0"]], "TensorFlow Quantization": [[478, "tensorflow-quantization"]], "Tensorflow": [[546, "tensorflow"]], "Tensorflow Model": [[526, "tensorflow-model"]], "Tensorflow Quantization AutoTune": [[511, "tensorflow-quantization-autotune"]], "Tensorflow Quantization Base API": [[512, "tensorflow-quantization-base-api"]], "Tensorflow Quantization Config": [[513, "tensorflow-quantization-config"]], "Torch": [[477, "torch"]], "Torch Utils": [[498, "torch-utils"]], "Torch-like APIs": [[477, "torch-like-apis"]], "Trademarks": [[533, "trademarks"]], "Training": [[517, "training"]], "Training-aware pruning API": [[542, "training-aware-pruning-api"]], "Transform": [[551, "transform"]], "Transform Support List": [[551, "transform-support-list"]], "Tuning Algorithms": [[552, "tuning-algorithms"]], "Tuning Process": [[552, "tuning-process"]], "Tuning Space": [[552, "tuning-space"]], "Tuning Strategies": [[552, "tuning-strategies"]], "Turn OFF Auto Mixed Precision during Quantization": [[546, "turn-off-auto-mixed-precision-during-quantization"]], "Type Annotations": [[520, "type-annotations"]], "Usage": [[474, "usage"], [476, "usage"], [479, "usage"], [482, "usage"], [550, "usage"], [552, "usage"], [552, "id2"], [552, "id4"], [552, "id6"], [552, "id8"], [552, "id10"], [552, "id12"], [552, "id14"], [552, "id16"], [552, "id18"], [552, "id20"], [552, "id22"]], "Usage Sample with IPEX": [[475, "usage-sample-with-ipex"]], "Usage Sample with PT2E": [[475, "usage-sample-with-pt2e"]], "Use Docker Image with torch installed for HPU": [[492, "use-docker-image-with-torch-installed-for-hpu"], [532, "use-docker-image-with-torch-installed-for-hpu"]], "Use Intel\u00ae Neural Compressor DataLoader API": [[521, "use-intel-neural-compressor-dataloader-api"]], "Use Intel\u00ae Neural Compressor Metric API": [[535, "use-intel-neural-compressor-metric-api"]], "Use the New Data Type": [[495, "use-the-new-data-type"]], "User Code Example": [[547, "user-code-example"]], "User code example": [[547, "id1"]], "User-facing APIs": [[530, "user-facing-apis"]], "Using a Fixed alpha": [[479, "using-a-fixed-alpha"]], "Using a fixed alpha": [[550, "using-a-fixed-alpha"]], "Validated Hardware Environment": [[532, "validated-hardware-environment"]], "Validated Knowledge Distillation Examples": [[553, "validated-knowledge-distillation-examples"]], "Validated Models": [[474, "validated-models"], [550, "validated-models"], [553, "validated-models"]], "Validated ONNX QDQ INT8 Models on Multiple Hardware through ONNX Runtime": [[553, "validated-onnx-qdq-int8-models-on-multiple-hardware-through-onnx-runtime"]], "Validated Pruning Examples": [[553, "validated-pruning-examples"]], "Validated Quantization Examples": [[553, "validated-quantization-examples"]], "Validated Software Environment": [[532, "validated-software-environment"]], "Version mapping between Intel Neural Compressor to Gaudi Software Stack": [[485, "version-mapping-between-intel-neural-compressor-to-gaudi-software-stack"]], "WOQ Algorithms Tuning": [[547, "woq-algorithms-tuning"]], "Weight Only Quantization": [[487, "weight-only-quantization"]], "Weight Only Quantization (WOQ)": [[547, "weight-only-quantization-woq"]], "Weight-Only Large Language Model Loading (LLMs)": [[492, "weight-only-large-language-model-loading-llms"]], "What\u2019s New": [[492, "what-s-new"]], "With Accuracy Aware Tuning": [[478, "with-accuracy-aware-tuning"]], "Without Accuracy Aware Tuning": [[478, "without-accuracy-aware-tuning"]], "Workflow": [[522, "workflow"]], "Workflows": [[484, "workflows"]], "Working Flow": [[493, "working-flow"], [544, "working-flow"]], "Working with Autotune": [[481, "working-with-autotune"]], "Working with PyTorch Model": [[481, "working-with-pytorch-model"]], "Working with Tensorflow Model": [[481, "working-with-tensorflow-model"]], "neural_compressor": [[226, "module-neural_compressor"]], "neural_compressor.adaptor.mxnet_utils": [[0, "module-neural_compressor.adaptor.mxnet_utils"]], "neural_compressor.adaptor.mxnet_utils.util": [[1, "module-neural_compressor.adaptor.mxnet_utils.util"]], "neural_compressor.adaptor.ox_utils": [[4, "module-neural_compressor.adaptor.ox_utils"]], "neural_compressor.adaptor.ox_utils.calibration": [[2, "module-neural_compressor.adaptor.ox_utils.calibration"]], "neural_compressor.adaptor.ox_utils.calibrator": [[3, "module-neural_compressor.adaptor.ox_utils.calibrator"]], "neural_compressor.adaptor.ox_utils.operators": [[16, "module-neural_compressor.adaptor.ox_utils.operators"]], "neural_compressor.adaptor.ox_utils.operators.activation": [[5, "module-neural_compressor.adaptor.ox_utils.operators.activation"]], "neural_compressor.adaptor.ox_utils.operators.argmax": [[6, "module-neural_compressor.adaptor.ox_utils.operators.argmax"]], "neural_compressor.adaptor.ox_utils.operators.attention": [[7, "module-neural_compressor.adaptor.ox_utils.operators.attention"]], "neural_compressor.adaptor.ox_utils.operators.binary_op": [[8, "module-neural_compressor.adaptor.ox_utils.operators.binary_op"]], "neural_compressor.adaptor.ox_utils.operators.concat": [[9, "module-neural_compressor.adaptor.ox_utils.operators.concat"]], "neural_compressor.adaptor.ox_utils.operators.conv": [[10, "module-neural_compressor.adaptor.ox_utils.operators.conv"]], "neural_compressor.adaptor.ox_utils.operators.direct_q8": [[11, "module-neural_compressor.adaptor.ox_utils.operators.direct_q8"]], "neural_compressor.adaptor.ox_utils.operators.embed_layernorm": [[12, "module-neural_compressor.adaptor.ox_utils.operators.embed_layernorm"]], "neural_compressor.adaptor.ox_utils.operators.gather": [[13, "module-neural_compressor.adaptor.ox_utils.operators.gather"]], "neural_compressor.adaptor.ox_utils.operators.gavgpool": [[14, "module-neural_compressor.adaptor.ox_utils.operators.gavgpool"]], "neural_compressor.adaptor.ox_utils.operators.gemm": [[15, "module-neural_compressor.adaptor.ox_utils.operators.gemm"]], "neural_compressor.adaptor.ox_utils.operators.lstm": [[17, "module-neural_compressor.adaptor.ox_utils.operators.lstm"]], "neural_compressor.adaptor.ox_utils.operators.matmul": [[18, "module-neural_compressor.adaptor.ox_utils.operators.matmul"]], "neural_compressor.adaptor.ox_utils.operators.maxpool": [[19, "module-neural_compressor.adaptor.ox_utils.operators.maxpool"]], "neural_compressor.adaptor.ox_utils.operators.norm": [[20, "module-neural_compressor.adaptor.ox_utils.operators.norm"]], "neural_compressor.adaptor.ox_utils.operators.ops": [[21, "module-neural_compressor.adaptor.ox_utils.operators.ops"]], "neural_compressor.adaptor.ox_utils.operators.pad": [[22, "module-neural_compressor.adaptor.ox_utils.operators.pad"]], "neural_compressor.adaptor.ox_utils.operators.pooling": [[23, "module-neural_compressor.adaptor.ox_utils.operators.pooling"]], "neural_compressor.adaptor.ox_utils.operators.reduce": [[24, "module-neural_compressor.adaptor.ox_utils.operators.reduce"]], "neural_compressor.adaptor.ox_utils.operators.resize": [[25, "module-neural_compressor.adaptor.ox_utils.operators.resize"]], "neural_compressor.adaptor.ox_utils.operators.split": [[26, "module-neural_compressor.adaptor.ox_utils.operators.split"]], "neural_compressor.adaptor.ox_utils.operators.unary_op": [[27, "module-neural_compressor.adaptor.ox_utils.operators.unary_op"]], "neural_compressor.adaptor.ox_utils.quantizer": [[28, "module-neural_compressor.adaptor.ox_utils.quantizer"]], "neural_compressor.adaptor.ox_utils.smooth_quant": [[29, "module-neural_compressor.adaptor.ox_utils.smooth_quant"]], "neural_compressor.adaptor.ox_utils.util": [[30, "module-neural_compressor.adaptor.ox_utils.util"]], "neural_compressor.adaptor.ox_utils.weight_only": [[31, "module-neural_compressor.adaptor.ox_utils.weight_only"]], "neural_compressor.adaptor.tensorflow": [[32, "module-neural_compressor.adaptor.tensorflow"]], "neural_compressor.adaptor.tf_utils": [[96, "module-neural_compressor.adaptor.tf_utils"]], "neural_compressor.adaptor.tf_utils.graph_converter": [[33, "module-neural_compressor.adaptor.tf_utils.graph_converter"]], "neural_compressor.adaptor.tf_utils.graph_converter_without_calib": [[34, "module-neural_compressor.adaptor.tf_utils.graph_converter_without_calib"]], "neural_compressor.adaptor.tf_utils.graph_rewriter": [[72, "module-neural_compressor.adaptor.tf_utils.graph_rewriter"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16": [[37, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert": [[35, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer": [[36, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic": [[61, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd": [[38, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout": [[39, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu": [[40, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random": [[41, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const": [[42, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction": [[43, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd": [[44, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer": [[45, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape": [[46, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm": [[47, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant": [[48, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add": [[49, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul": [[50, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math": [[51, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn": [[52, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in": [[53, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu": [[54, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm": [[55, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv": [[56, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv": [[57, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose": [[58, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer": [[59, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass": [[60, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node": [[62, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu": [[63, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize": [[64, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes": [[65, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm": [[66, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input": [[67, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes": [[68, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes": [[69, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer": [[70, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base": [[71, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8": [[80, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant": [[73, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value": [[74, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib": [[75, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize": [[76, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize": [[77, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize": [[78, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize": [[79, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer": [[81, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter": [[82, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse": [[83, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert": [[84, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation": [[85, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx": [[86, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph": [[87, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node": [[88, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema": [[89, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils": [[90, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq": [[91, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern": [[92, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq": [[93, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern": [[94, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern"]], "neural_compressor.adaptor.tf_utils.graph_util": [[95, "module-neural_compressor.adaptor.tf_utils.graph_util"]], "neural_compressor.adaptor.tf_utils.quantize_graph": [[97, "module-neural_compressor.adaptor.tf_utils.quantize_graph"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat": [[99, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize": [[98, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config": [[100, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper": [[101, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers": [[102, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer": [[103, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add": [[104, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base": [[105, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn": [[106, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper": [[107, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq": [[115, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn": [[108, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2": [[109, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv": [[110, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv": [[111, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in": [[112, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul": [[113, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling": [[114, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq": [[116, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base": [[117, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn": [[118, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2": [[119, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv": [[120, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu": [[121, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul": [[122, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling": [[123, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling"]], "neural_compressor.adaptor.tf_utils.quantize_graph_common": [[124, "module-neural_compressor.adaptor.tf_utils.quantize_graph_common"]], "neural_compressor.adaptor.tf_utils.smooth_quant_calibration": [[125, "module-neural_compressor.adaptor.tf_utils.smooth_quant_calibration"]], "neural_compressor.adaptor.tf_utils.smooth_quant_scaler": [[126, "module-neural_compressor.adaptor.tf_utils.smooth_quant_scaler"]], "neural_compressor.adaptor.tf_utils.tf2onnx_converter": [[127, "module-neural_compressor.adaptor.tf_utils.tf2onnx_converter"]], "neural_compressor.adaptor.tf_utils.transform_graph": [[130, "module-neural_compressor.adaptor.tf_utils.transform_graph"]], "neural_compressor.adaptor.tf_utils.transform_graph.bias_correction": [[128, "module-neural_compressor.adaptor.tf_utils.transform_graph.bias_correction"]], "neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base": [[129, "module-neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base"]], "neural_compressor.adaptor.tf_utils.transform_graph.insert_logging": [[131, "module-neural_compressor.adaptor.tf_utils.transform_graph.insert_logging"]], "neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat": [[132, "module-neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat"]], "neural_compressor.adaptor.tf_utils.util": [[133, "module-neural_compressor.adaptor.tf_utils.util"]], "neural_compressor.adaptor.torch_utils": [[136, "module-neural_compressor.adaptor.torch_utils"]], "neural_compressor.adaptor.torch_utils.bf16_convert": [[134, "module-neural_compressor.adaptor.torch_utils.bf16_convert"]], "neural_compressor.adaptor.torch_utils.hawq_metric": [[135, "module-neural_compressor.adaptor.torch_utils.hawq_metric"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant": [[137, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle": [[138, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize": [[139, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load": [[140, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils": [[141, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.utils"]], "neural_compressor.adaptor.torch_utils.model_wrapper": [[142, "module-neural_compressor.adaptor.torch_utils.model_wrapper"]], "neural_compressor.adaptor.torch_utils.pattern_detector": [[143, "module-neural_compressor.adaptor.torch_utils.pattern_detector"]], "neural_compressor.adaptor.torch_utils.symbolic_trace": [[144, "module-neural_compressor.adaptor.torch_utils.symbolic_trace"]], "neural_compressor.adaptor.torch_utils.util": [[145, "module-neural_compressor.adaptor.torch_utils.util"]], "neural_compressor.algorithm": [[148, "module-neural_compressor.algorithm"]], "neural_compressor.algorithm.algorithm": [[146, "module-neural_compressor.algorithm.algorithm"]], "neural_compressor.algorithm.fast_bias_correction": [[147, "module-neural_compressor.algorithm.fast_bias_correction"]], "neural_compressor.algorithm.smooth_quant": [[149, "module-neural_compressor.algorithm.smooth_quant"]], "neural_compressor.algorithm.weight_correction": [[150, "module-neural_compressor.algorithm.weight_correction"]], "neural_compressor.benchmark": [[151, "module-neural_compressor.benchmark"]], "neural_compressor.common": [[155, "module-neural_compressor.common"]], "neural_compressor.common.base_config": [[152, "module-neural_compressor.common.base_config"]], "neural_compressor.common.base_tuning": [[153, "module-neural_compressor.common.base_tuning"]], "neural_compressor.common.benchmark": [[154, "module-neural_compressor.common.benchmark"]], "neural_compressor.common.tuning_param": [[156, "module-neural_compressor.common.tuning_param"]], "neural_compressor.common.utils": [[158, "module-neural_compressor.common.utils"]], "neural_compressor.common.utils.constants": [[157, "module-neural_compressor.common.utils.constants"]], "neural_compressor.common.utils.logger": [[159, "module-neural_compressor.common.utils.logger"]], "neural_compressor.common.utils.save_load": [[160, "module-neural_compressor.common.utils.save_load"]], "neural_compressor.common.utils.utility": [[161, "module-neural_compressor.common.utils.utility"]], "neural_compressor.compression.callbacks": [[162, "module-neural_compressor.compression.callbacks"]], "neural_compressor.compression.distillation": [[164, "module-neural_compressor.compression.distillation"]], "neural_compressor.compression.distillation.criterions": [[163, "module-neural_compressor.compression.distillation.criterions"]], "neural_compressor.compression.distillation.optimizers": [[165, "module-neural_compressor.compression.distillation.optimizers"]], "neural_compressor.compression.distillation.utility": [[166, "module-neural_compressor.compression.distillation.utility"]], "neural_compressor.compression.hpo": [[167, "module-neural_compressor.compression.hpo"]], "neural_compressor.compression.hpo.sa_optimizer": [[168, "module-neural_compressor.compression.hpo.sa_optimizer"]], "neural_compressor.compression.pruner": [[170, "module-neural_compressor.compression.pruner"]], "neural_compressor.compression.pruner.criteria": [[169, "module-neural_compressor.compression.pruner.criteria"]], "neural_compressor.compression.pruner.model_slim": [[172, "module-neural_compressor.compression.pruner.model_slim"]], "neural_compressor.compression.pruner.model_slim.auto_slim": [[171, "module-neural_compressor.compression.pruner.model_slim.auto_slim"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer": [[173, "module-neural_compressor.compression.pruner.model_slim.pattern_analyzer"]], "neural_compressor.compression.pruner.model_slim.weight_slim": [[174, "module-neural_compressor.compression.pruner.model_slim.weight_slim"]], "neural_compressor.compression.pruner.patterns": [[176, "module-neural_compressor.compression.pruner.patterns"]], "neural_compressor.compression.pruner.patterns.base": [[175, "module-neural_compressor.compression.pruner.patterns.base"]], "neural_compressor.compression.pruner.patterns.mha": [[177, "module-neural_compressor.compression.pruner.patterns.mha"]], "neural_compressor.compression.pruner.patterns.ninm": [[178, "module-neural_compressor.compression.pruner.patterns.ninm"]], "neural_compressor.compression.pruner.patterns.nxm": [[179, "module-neural_compressor.compression.pruner.patterns.nxm"]], "neural_compressor.compression.pruner.pruners": [[183, "module-neural_compressor.compression.pruner.pruners"]], "neural_compressor.compression.pruner.pruners.base": [[180, "module-neural_compressor.compression.pruner.pruners.base"]], "neural_compressor.compression.pruner.pruners.basic": [[181, "module-neural_compressor.compression.pruner.pruners.basic"]], "neural_compressor.compression.pruner.pruners.block_mask": [[182, "module-neural_compressor.compression.pruner.pruners.block_mask"]], "neural_compressor.compression.pruner.pruners.mha": [[184, "module-neural_compressor.compression.pruner.pruners.mha"]], "neural_compressor.compression.pruner.pruners.pattern_lock": [[185, "module-neural_compressor.compression.pruner.pruners.pattern_lock"]], "neural_compressor.compression.pruner.pruners.progressive": [[186, "module-neural_compressor.compression.pruner.pruners.progressive"]], "neural_compressor.compression.pruner.pruners.retrain_free": [[187, "module-neural_compressor.compression.pruner.pruners.retrain_free"]], "neural_compressor.compression.pruner.pruning": [[188, "module-neural_compressor.compression.pruner.pruning"]], "neural_compressor.compression.pruner.regs": [[189, "module-neural_compressor.compression.pruner.regs"]], "neural_compressor.compression.pruner.schedulers": [[190, "module-neural_compressor.compression.pruner.schedulers"]], "neural_compressor.compression.pruner.tf_criteria": [[191, "module-neural_compressor.compression.pruner.tf_criteria"]], "neural_compressor.compression.pruner.utils": [[192, "module-neural_compressor.compression.pruner.utils"]], "neural_compressor.compression.pruner.wanda": [[193, "module-neural_compressor.compression.pruner.wanda"]], "neural_compressor.compression.pruner.wanda.utils": [[194, "module-neural_compressor.compression.pruner.wanda.utils"]], "neural_compressor.config": [[195, "module-neural_compressor.config"]], "neural_compressor.contrib": [[196, "module-neural_compressor.contrib"]], "neural_compressor.contrib.strategy": [[197, "module-neural_compressor.contrib.strategy"]], "neural_compressor.contrib.strategy.sigopt": [[198, "module-neural_compressor.contrib.strategy.sigopt"]], "neural_compressor.contrib.strategy.tpe": [[199, "module-neural_compressor.contrib.strategy.tpe"]], "neural_compressor.data": [[220, "module-neural_compressor.data"]], "neural_compressor.data.dataloaders.base_dataloader": [[200, "module-neural_compressor.data.dataloaders.base_dataloader"]], "neural_compressor.data.dataloaders.dataloader": [[201, "module-neural_compressor.data.dataloaders.dataloader"]], "neural_compressor.data.dataloaders.default_dataloader": [[202, "module-neural_compressor.data.dataloaders.default_dataloader"]], "neural_compressor.data.dataloaders.fetcher": [[203, "module-neural_compressor.data.dataloaders.fetcher"]], "neural_compressor.data.dataloaders.mxnet_dataloader": [[204, "module-neural_compressor.data.dataloaders.mxnet_dataloader"]], "neural_compressor.data.dataloaders.onnxrt_dataloader": [[205, "module-neural_compressor.data.dataloaders.onnxrt_dataloader"]], "neural_compressor.data.dataloaders.pytorch_dataloader": [[206, "module-neural_compressor.data.dataloaders.pytorch_dataloader"]], "neural_compressor.data.dataloaders.sampler": [[207, "module-neural_compressor.data.dataloaders.sampler"]], "neural_compressor.data.dataloaders.tensorflow_dataloader": [[208, "module-neural_compressor.data.dataloaders.tensorflow_dataloader"]], "neural_compressor.data.datasets": [[215, "module-neural_compressor.data.datasets"]], "neural_compressor.data.datasets.bert_dataset": [[209, "module-neural_compressor.data.datasets.bert_dataset"]], "neural_compressor.data.datasets.coco_dataset": [[210, "module-neural_compressor.data.datasets.coco_dataset"]], "neural_compressor.data.datasets.dataset": [[211, "module-neural_compressor.data.datasets.dataset"]], "neural_compressor.data.datasets.dummy_dataset": [[212, "module-neural_compressor.data.datasets.dummy_dataset"]], "neural_compressor.data.datasets.dummy_dataset_v2": [[213, "module-neural_compressor.data.datasets.dummy_dataset_v2"]], "neural_compressor.data.datasets.imagenet_dataset": [[214, "module-neural_compressor.data.datasets.imagenet_dataset"]], "neural_compressor.data.datasets.style_transfer_dataset": [[216, "module-neural_compressor.data.datasets.style_transfer_dataset"]], "neural_compressor.data.filters": [[219, "module-neural_compressor.data.filters"]], "neural_compressor.data.filters.coco_filter": [[217, "module-neural_compressor.data.filters.coco_filter"]], "neural_compressor.data.filters.filter": [[218, "module-neural_compressor.data.filters.filter"]], "neural_compressor.data.transforms": [[222, "module-neural_compressor.data.transforms"]], "neural_compressor.data.transforms.imagenet_transform": [[221, "module-neural_compressor.data.transforms.imagenet_transform"]], "neural_compressor.data.transforms.postprocess": [[223, "module-neural_compressor.data.transforms.postprocess"]], "neural_compressor.data.transforms.tokenization": [[224, "module-neural_compressor.data.transforms.tokenization"]], "neural_compressor.data.transforms.transform": [[225, "module-neural_compressor.data.transforms.transform"]], "neural_compressor.metric": [[233, "module-neural_compressor.metric"]], "neural_compressor.metric.bleu": [[227, "module-neural_compressor.metric.bleu"]], "neural_compressor.metric.bleu_util": [[228, "module-neural_compressor.metric.bleu_util"]], "neural_compressor.metric.coco_label_map": [[229, "module-neural_compressor.metric.coco_label_map"]], "neural_compressor.metric.coco_tools": [[230, "module-neural_compressor.metric.coco_tools"]], "neural_compressor.metric.evaluate_squad": [[231, "module-neural_compressor.metric.evaluate_squad"]], "neural_compressor.metric.f1": [[232, "module-neural_compressor.metric.f1"]], "neural_compressor.metric.metric": [[234, "module-neural_compressor.metric.metric"]], "neural_compressor.mix_precision": [[235, "module-neural_compressor.mix_precision"]], "neural_compressor.model": [[237, "module-neural_compressor.model"]], "neural_compressor.model.base_model": [[236, "module-neural_compressor.model.base_model"]], "neural_compressor.model.keras_model": [[238, "module-neural_compressor.model.keras_model"]], "neural_compressor.model.model": [[239, "module-neural_compressor.model.model"]], "neural_compressor.model.mxnet_model": [[240, "module-neural_compressor.model.mxnet_model"]], "neural_compressor.model.nets_factory": [[241, "module-neural_compressor.model.nets_factory"]], "neural_compressor.model.onnx_model": [[242, "module-neural_compressor.model.onnx_model"]], "neural_compressor.model.tensorflow_model": [[243, "module-neural_compressor.model.tensorflow_model"]], "neural_compressor.model.torch_model": [[244, "module-neural_compressor.model.torch_model"]], "neural_compressor.objective": [[245, "module-neural_compressor.objective"]], "neural_compressor.profiling": [[246, "module-neural_compressor.profiling"]], "neural_compressor.profiling.parser.factory": [[247, "module-neural_compressor.profiling.parser.factory"]], "neural_compressor.profiling.parser.onnx_parser.factory": [[248, "module-neural_compressor.profiling.parser.onnx_parser.factory"]], "neural_compressor.profiling.parser.onnx_parser.parser": [[249, "module-neural_compressor.profiling.parser.onnx_parser.parser"]], "neural_compressor.profiling.parser.parser": [[250, "module-neural_compressor.profiling.parser.parser"]], "neural_compressor.profiling.parser.result": [[251, "module-neural_compressor.profiling.parser.result"]], "neural_compressor.profiling.parser.tensorflow_parser.factory": [[252, "module-neural_compressor.profiling.parser.tensorflow_parser.factory"]], "neural_compressor.profiling.parser.tensorflow_parser.parser": [[253, "module-neural_compressor.profiling.parser.tensorflow_parser.parser"]], "neural_compressor.profiling.profiler.factory": [[254, "module-neural_compressor.profiling.profiler.factory"]], "neural_compressor.profiling.profiler.onnxrt_profiler.factory": [[255, "module-neural_compressor.profiling.profiler.onnxrt_profiler.factory"]], "neural_compressor.profiling.profiler.onnxrt_profiler.profiler": [[256, "module-neural_compressor.profiling.profiler.onnxrt_profiler.profiler"]], "neural_compressor.profiling.profiler.onnxrt_profiler.utils": [[257, "module-neural_compressor.profiling.profiler.onnxrt_profiler.utils"]], "neural_compressor.profiling.profiler.profiler": [[258, "module-neural_compressor.profiling.profiler.profiler"]], "neural_compressor.profiling.profiler.tensorflow_profiler.factory": [[259, "module-neural_compressor.profiling.profiler.tensorflow_profiler.factory"]], "neural_compressor.profiling.profiler.tensorflow_profiler.profiler": [[260, "module-neural_compressor.profiling.profiler.tensorflow_profiler.profiler"]], "neural_compressor.profiling.profiler.tensorflow_profiler.utils": [[261, "module-neural_compressor.profiling.profiler.tensorflow_profiler.utils"]], "neural_compressor.quantization": [[262, "module-neural_compressor.quantization"]], "neural_compressor.strategy": [[270, "module-neural_compressor.strategy"]], "neural_compressor.strategy.auto": [[263, "module-neural_compressor.strategy.auto"]], "neural_compressor.strategy.auto_mixed_precision": [[264, "module-neural_compressor.strategy.auto_mixed_precision"]], "neural_compressor.strategy.basic": [[265, "module-neural_compressor.strategy.basic"]], "neural_compressor.strategy.bayesian": [[266, "module-neural_compressor.strategy.bayesian"]], "neural_compressor.strategy.conservative": [[267, "module-neural_compressor.strategy.conservative"]], "neural_compressor.strategy.exhaustive": [[268, "module-neural_compressor.strategy.exhaustive"]], "neural_compressor.strategy.hawq_v2": [[269, "module-neural_compressor.strategy.hawq_v2"]], "neural_compressor.strategy.mse": [[271, "module-neural_compressor.strategy.mse"]], "neural_compressor.strategy.mse_v2": [[272, "module-neural_compressor.strategy.mse_v2"]], "neural_compressor.strategy.random": [[273, "module-neural_compressor.strategy.random"]], "neural_compressor.strategy.strategy": [[274, "module-neural_compressor.strategy.strategy"]], "neural_compressor.strategy.utils": [[276, "module-neural_compressor.strategy.utils"]], "neural_compressor.strategy.utils.constant": [[275, "module-neural_compressor.strategy.utils.constant"]], "neural_compressor.strategy.utils.tuning_sampler": [[277, "module-neural_compressor.strategy.utils.tuning_sampler"]], "neural_compressor.strategy.utils.tuning_space": [[278, "module-neural_compressor.strategy.utils.tuning_space"]], "neural_compressor.strategy.utils.tuning_structs": [[279, "module-neural_compressor.strategy.utils.tuning_structs"]], "neural_compressor.strategy.utils.utility": [[280, "module-neural_compressor.strategy.utils.utility"]], "neural_compressor.template.api_doc_example": [[281, "module-neural_compressor.template.api_doc_example"]], "neural_compressor.tensorflow": [[290, "module-neural_compressor.tensorflow"]], "neural_compressor.tensorflow.algorithms": [[282, "module-neural_compressor.tensorflow.algorithms"]], "neural_compressor.tensorflow.algorithms.smoother": [[285, "module-neural_compressor.tensorflow.algorithms.smoother"]], "neural_compressor.tensorflow.algorithms.smoother.calibration": [[283, "module-neural_compressor.tensorflow.algorithms.smoother.calibration"]], "neural_compressor.tensorflow.algorithms.smoother.core": [[284, "module-neural_compressor.tensorflow.algorithms.smoother.core"]], "neural_compressor.tensorflow.algorithms.smoother.scaler": [[286, "module-neural_compressor.tensorflow.algorithms.smoother.scaler"]], "neural_compressor.tensorflow.algorithms.static_quant": [[287, "module-neural_compressor.tensorflow.algorithms.static_quant"]], "neural_compressor.tensorflow.algorithms.static_quant.keras": [[288, "module-neural_compressor.tensorflow.algorithms.static_quant.keras"]], "neural_compressor.tensorflow.algorithms.static_quant.tensorflow": [[289, "module-neural_compressor.tensorflow.algorithms.static_quant.tensorflow"]], "neural_compressor.tensorflow.keras": [[291, "module-neural_compressor.tensorflow.keras"]], "neural_compressor.tensorflow.keras.layers": [[295, "module-neural_compressor.tensorflow.keras.layers"]], "neural_compressor.tensorflow.keras.layers.conv2d": [[292, "module-neural_compressor.tensorflow.keras.layers.conv2d"]], "neural_compressor.tensorflow.keras.layers.dense": [[293, "module-neural_compressor.tensorflow.keras.layers.dense"]], "neural_compressor.tensorflow.keras.layers.depthwise_conv2d": [[294, "module-neural_compressor.tensorflow.keras.layers.depthwise_conv2d"]], "neural_compressor.tensorflow.keras.layers.layer_initializer": [[296, "module-neural_compressor.tensorflow.keras.layers.layer_initializer"]], "neural_compressor.tensorflow.keras.layers.pool2d": [[297, "module-neural_compressor.tensorflow.keras.layers.pool2d"]], "neural_compressor.tensorflow.keras.layers.separable_conv2d": [[298, "module-neural_compressor.tensorflow.keras.layers.separable_conv2d"]], "neural_compressor.tensorflow.keras.quantization": [[300, "module-neural_compressor.tensorflow.keras.quantization"]], "neural_compressor.tensorflow.keras.quantization.config": [[299, "module-neural_compressor.tensorflow.keras.quantization.config"]], "neural_compressor.tensorflow.quantization": [[304, "module-neural_compressor.tensorflow.quantization"]], "neural_compressor.tensorflow.quantization.algorithm_entry": [[301, "module-neural_compressor.tensorflow.quantization.algorithm_entry"]], "neural_compressor.tensorflow.quantization.autotune": [[302, "module-neural_compressor.tensorflow.quantization.autotune"]], "neural_compressor.tensorflow.quantization.config": [[303, "module-neural_compressor.tensorflow.quantization.config"]], "neural_compressor.tensorflow.quantization.quantize": [[305, "module-neural_compressor.tensorflow.quantization.quantize"]], "neural_compressor.tensorflow.quantization.utils": [[361, "module-neural_compressor.tensorflow.quantization.utils"]], "neural_compressor.tensorflow.quantization.utils.graph_converter": [[306, "module-neural_compressor.tensorflow.quantization.utils.graph_converter"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter": [[344, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16": [[309, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert": [[307, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer": [[308, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic": [[333, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd": [[310, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout": [[311, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu": [[312, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random": [[313, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const": [[314, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction": [[315, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd": [[316, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer": [[317, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape": [[318, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm": [[319, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant": [[320, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add": [[321, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul": [[322, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math": [[323, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn": [[324, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in": [[325, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu": [[326, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm": [[327, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv": [[328, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv": [[329, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose": [[330, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer": [[331, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass": [[332, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node": [[334, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu": [[335, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize": [[336, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes": [[337, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm": [[338, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input": [[339, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes": [[340, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes": [[341, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer": [[342, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base": [[343, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8": [[351, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant": [[345, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value": [[346, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize": [[347, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize": [[348, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize": [[349, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize": [[350, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer": [[352, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter": [[353, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse": [[354, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation": [[355, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq": [[356, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern": [[357, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq": [[358, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern": [[359, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern"]], "neural_compressor.tensorflow.quantization.utils.graph_util": [[360, "module-neural_compressor.tensorflow.quantization.utils.graph_util"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph": [[362, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq": [[370, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn": [[363, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2": [[364, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv": [[365, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv": [[366, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in": [[367, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul": [[368, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling": [[369, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq": [[371, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base": [[372, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn": [[373, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2": [[374, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv": [[375, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu": [[376, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul": [[377, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling": [[378, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph_common": [[379, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph_common"]], "neural_compressor.tensorflow.quantization.utils.transform_graph": [[382, "module-neural_compressor.tensorflow.quantization.utils.transform_graph"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction": [[380, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base": [[381, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging": [[383, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat": [[384, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat"]], "neural_compressor.tensorflow.quantization.utils.utility": [[385, "module-neural_compressor.tensorflow.quantization.utils.utility"]], "neural_compressor.tensorflow.utils": [[388, "module-neural_compressor.tensorflow.utils"]], "neural_compressor.tensorflow.utils.constants": [[386, "module-neural_compressor.tensorflow.utils.constants"]], "neural_compressor.tensorflow.utils.data": [[387, "module-neural_compressor.tensorflow.utils.data"]], "neural_compressor.tensorflow.utils.model": [[389, "module-neural_compressor.tensorflow.utils.model"]], "neural_compressor.tensorflow.utils.model_wrappers": [[390, "module-neural_compressor.tensorflow.utils.model_wrappers"]], "neural_compressor.tensorflow.utils.utility": [[391, "module-neural_compressor.tensorflow.utils.utility"]], "neural_compressor.torch": [[436, "module-neural_compressor.torch"]], "neural_compressor.torch.algorithms": [[394, "module-neural_compressor.torch.algorithms"]], "neural_compressor.torch.algorithms.base_algorithm": [[392, "module-neural_compressor.torch.algorithms.base_algorithm"]], "neural_compressor.torch.algorithms.fp8_quant.utils.logger": [[393, "module-neural_compressor.torch.algorithms.fp8_quant.utils.logger"]], "neural_compressor.torch.algorithms.layer_wise": [[395, "module-neural_compressor.torch.algorithms.layer_wise"]], "neural_compressor.torch.algorithms.layer_wise.load": [[396, "module-neural_compressor.torch.algorithms.layer_wise.load"]], "neural_compressor.torch.algorithms.layer_wise.modified_pickle": [[397, "module-neural_compressor.torch.algorithms.layer_wise.modified_pickle"]], "neural_compressor.torch.algorithms.layer_wise.utils": [[398, "module-neural_compressor.torch.algorithms.layer_wise.utils"]], "neural_compressor.torch.algorithms.mixed_precision": [[400, "module-neural_compressor.torch.algorithms.mixed_precision"]], "neural_compressor.torch.algorithms.mixed_precision.half_precision_convert": [[399, "module-neural_compressor.torch.algorithms.mixed_precision.half_precision_convert"]], "neural_compressor.torch.algorithms.mixed_precision.module_wrappers": [[401, "module-neural_compressor.torch.algorithms.mixed_precision.module_wrappers"]], "neural_compressor.torch.algorithms.mx_quant": [[402, "module-neural_compressor.torch.algorithms.mx_quant"]], "neural_compressor.torch.algorithms.mx_quant.mx": [[403, "module-neural_compressor.torch.algorithms.mx_quant.mx"]], "neural_compressor.torch.algorithms.mx_quant.utils": [[404, "module-neural_compressor.torch.algorithms.mx_quant.utils"]], "neural_compressor.torch.algorithms.pt2e_quant": [[407, "module-neural_compressor.torch.algorithms.pt2e_quant"]], "neural_compressor.torch.algorithms.pt2e_quant.core": [[405, "module-neural_compressor.torch.algorithms.pt2e_quant.core"]], "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter": [[406, "module-neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter"]], "neural_compressor.torch.algorithms.pt2e_quant.save_load": [[408, "module-neural_compressor.torch.algorithms.pt2e_quant.save_load"]], "neural_compressor.torch.algorithms.pt2e_quant.utility": [[409, "module-neural_compressor.torch.algorithms.pt2e_quant.utility"]], "neural_compressor.torch.algorithms.smooth_quant": [[410, "module-neural_compressor.torch.algorithms.smooth_quant"]], "neural_compressor.torch.algorithms.smooth_quant.save_load": [[411, "module-neural_compressor.torch.algorithms.smooth_quant.save_load"]], "neural_compressor.torch.algorithms.smooth_quant.smooth_quant": [[412, "module-neural_compressor.torch.algorithms.smooth_quant.smooth_quant"]], "neural_compressor.torch.algorithms.smooth_quant.utility": [[413, "module-neural_compressor.torch.algorithms.smooth_quant.utility"]], "neural_compressor.torch.algorithms.static_quant": [[414, "module-neural_compressor.torch.algorithms.static_quant"]], "neural_compressor.torch.algorithms.static_quant.save_load": [[415, "module-neural_compressor.torch.algorithms.static_quant.save_load"]], "neural_compressor.torch.algorithms.static_quant.static_quant": [[416, "module-neural_compressor.torch.algorithms.static_quant.static_quant"]], "neural_compressor.torch.algorithms.static_quant.utility": [[417, "module-neural_compressor.torch.algorithms.static_quant.utility"]], "neural_compressor.torch.algorithms.weight_only": [[428, "module-neural_compressor.torch.algorithms.weight_only"]], "neural_compressor.torch.algorithms.weight_only.autoround": [[418, "module-neural_compressor.torch.algorithms.weight_only.autoround"]], "neural_compressor.torch.algorithms.weight_only.awq": [[419, "module-neural_compressor.torch.algorithms.weight_only.awq"]], "neural_compressor.torch.algorithms.weight_only.gptq": [[420, "module-neural_compressor.torch.algorithms.weight_only.gptq"]], "neural_compressor.torch.algorithms.weight_only.hqq": [[424, "module-neural_compressor.torch.algorithms.weight_only.hqq"]], "neural_compressor.torch.algorithms.weight_only.hqq.bitpack": [[421, "module-neural_compressor.torch.algorithms.weight_only.hqq.bitpack"]], "neural_compressor.torch.algorithms.weight_only.hqq.config": [[422, "module-neural_compressor.torch.algorithms.weight_only.hqq.config"]], "neural_compressor.torch.algorithms.weight_only.hqq.core": [[423, "module-neural_compressor.torch.algorithms.weight_only.hqq.core"]], "neural_compressor.torch.algorithms.weight_only.hqq.optimizer": [[425, "module-neural_compressor.torch.algorithms.weight_only.hqq.optimizer"]], "neural_compressor.torch.algorithms.weight_only.hqq.qtensor": [[426, "module-neural_compressor.torch.algorithms.weight_only.hqq.qtensor"]], "neural_compressor.torch.algorithms.weight_only.hqq.quantizer": [[427, "module-neural_compressor.torch.algorithms.weight_only.hqq.quantizer"]], "neural_compressor.torch.algorithms.weight_only.modules": [[429, "module-neural_compressor.torch.algorithms.weight_only.modules"]], "neural_compressor.torch.algorithms.weight_only.rtn": [[430, "module-neural_compressor.torch.algorithms.weight_only.rtn"]], "neural_compressor.torch.algorithms.weight_only.save_load": [[431, "module-neural_compressor.torch.algorithms.weight_only.save_load"]], "neural_compressor.torch.algorithms.weight_only.teq": [[432, "module-neural_compressor.torch.algorithms.weight_only.teq"]], "neural_compressor.torch.algorithms.weight_only.utility": [[433, "module-neural_compressor.torch.algorithms.weight_only.utility"]], "neural_compressor.torch.export": [[434, "module-neural_compressor.torch.export"]], "neural_compressor.torch.export.pt2e_export": [[435, "module-neural_compressor.torch.export.pt2e_export"]], "neural_compressor.torch.quantization": [[440, "module-neural_compressor.torch.quantization"]], "neural_compressor.torch.quantization.algorithm_entry": [[437, "module-neural_compressor.torch.quantization.algorithm_entry"]], "neural_compressor.torch.quantization.autotune": [[438, "module-neural_compressor.torch.quantization.autotune"]], "neural_compressor.torch.quantization.config": [[439, "module-neural_compressor.torch.quantization.config"]], "neural_compressor.torch.quantization.load_entry": [[441, "module-neural_compressor.torch.quantization.load_entry"]], "neural_compressor.torch.quantization.quantize": [[442, "module-neural_compressor.torch.quantization.quantize"]], "neural_compressor.torch.utils": [[446, "module-neural_compressor.torch.utils"]], "neural_compressor.torch.utils.auto_accelerator": [[443, "module-neural_compressor.torch.utils.auto_accelerator"]], "neural_compressor.torch.utils.constants": [[444, "module-neural_compressor.torch.utils.constants"]], "neural_compressor.torch.utils.environ": [[445, "module-neural_compressor.torch.utils.environ"]], "neural_compressor.torch.utils.utility": [[447, "module-neural_compressor.torch.utils.utility"]], "neural_compressor.training": [[448, "module-neural_compressor.training"]], "neural_compressor.transformers.quantization.utils": [[449, "module-neural_compressor.transformers.quantization.utils"]], "neural_compressor.transformers.utils": [[450, "module-neural_compressor.transformers.utils"]], "neural_compressor.transformers.utils.quantization_config": [[451, "module-neural_compressor.transformers.utils.quantization_config"]], "neural_compressor.utils": [[459, "module-neural_compressor.utils"]], "neural_compressor.utils.collect_layer_histogram": [[452, "module-neural_compressor.utils.collect_layer_histogram"]], "neural_compressor.utils.constant": [[453, "module-neural_compressor.utils.constant"]], "neural_compressor.utils.create_obj_from_config": [[454, "module-neural_compressor.utils.create_obj_from_config"]], "neural_compressor.utils.export": [[455, "module-neural_compressor.utils.export"]], "neural_compressor.utils.export.qlinear2qdq": [[456, "module-neural_compressor.utils.export.qlinear2qdq"]], "neural_compressor.utils.export.tf2onnx": [[457, "module-neural_compressor.utils.export.tf2onnx"]], "neural_compressor.utils.export.torch2onnx": [[458, "module-neural_compressor.utils.export.torch2onnx"]], "neural_compressor.utils.kl_divergence": [[460, "module-neural_compressor.utils.kl_divergence"]], "neural_compressor.utils.load_huggingface": [[461, "module-neural_compressor.utils.load_huggingface"]], "neural_compressor.utils.logger": [[462, "module-neural_compressor.utils.logger"]], "neural_compressor.utils.options": [[463, "module-neural_compressor.utils.options"]], "neural_compressor.utils.pytorch": [[464, "module-neural_compressor.utils.pytorch"]], "neural_compressor.utils.utility": [[465, "module-neural_compressor.utils.utility"]], "neural_compressor.utils.weights_details": [[466, "module-neural_compressor.utils.weights_details"]], "neural_compressor.version": [[467, "module-neural_compressor.version"]], "}": [[145, "id3"]]}, "docnames": ["autoapi/neural_compressor/adaptor/mxnet_utils/index", "autoapi/neural_compressor/adaptor/mxnet_utils/util/index", "autoapi/neural_compressor/adaptor/ox_utils/calibration/index", "autoapi/neural_compressor/adaptor/ox_utils/calibrator/index", "autoapi/neural_compressor/adaptor/ox_utils/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/activation/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/argmax/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/attention/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/binary_op/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/concat/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/conv/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/direct_q8/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/embed_layernorm/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/gather/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/gavgpool/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/gemm/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/lstm/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/matmul/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/maxpool/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/norm/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/ops/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/pad/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/pooling/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/reduce/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/resize/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/split/index", "autoapi/neural_compressor/adaptor/ox_utils/operators/unary_op/index", "autoapi/neural_compressor/adaptor/ox_utils/quantizer/index", "autoapi/neural_compressor/adaptor/ox_utils/smooth_quant/index", "autoapi/neural_compressor/adaptor/ox_utils/util/index", "autoapi/neural_compressor/adaptor/ox_utils/weight_only/index", "autoapi/neural_compressor/adaptor/tensorflow/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_converter/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_converter_without_calib/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/bf16_convert/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/dequantize_cast_optimizer/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_add_to_biasadd/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_layout/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_leakyrelu/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_nan_to_random/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_placeholder_to_const/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dilated_contraction/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dummy_biasadd/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/expanddims_optimizer/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fetch_weight_from_reshape/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_batch_norm/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_constant/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_biasadd_add/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_column_wise_mul/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_conv_with_math/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_bn/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_in/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_gelu/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_layer_norm/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_conv/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_reshape_transpose/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/graph_cse_optimizer/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/grappler_pass/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/insert_print_node/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/move_squeeze_after_relu/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/pre_optimize/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/remove_training_nodes/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/rename_batch_norm/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/split_shared_input/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_equivalent_nodes/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_unused_nodes/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/switch_optimizer/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/graph_base/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_fake_quant/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value_without_calib/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_requantize/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_requantize/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/meta_op_optimizer/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_hostconst_converter/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_quantized_op_cse/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/rnn_convert/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/scale_propagation/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_graph/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_node/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_schema/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/tf2onnx_utils/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/insert_qdq_pattern/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/merge_duplicated_qdq/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/share_qdq_y_pattern/index", "autoapi/neural_compressor/adaptor/tf_utils/graph_util/index", "autoapi/neural_compressor/adaptor/tf_utils/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/fake_quantize/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_config/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_helper/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/optimize_layer/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_add/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_base/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_bn/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_wrapper/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_bn/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_concatv2/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_conv/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_deconv/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_in/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_matmul/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_pooling/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/optimize_qdq/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_base/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_bn/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_concatv2/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_conv/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_for_intel_cpu/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_matmul/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_pooling/index", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph_common/index", "autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_calibration/index", "autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_scaler/index", "autoapi/neural_compressor/adaptor/tf_utils/tf2onnx_converter/index", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/bias_correction/index", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/graph_transform_base/index", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/index", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/insert_logging/index", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/rerange_quantized_concat/index", "autoapi/neural_compressor/adaptor/tf_utils/util/index", "autoapi/neural_compressor/adaptor/torch_utils/bf16_convert/index", "autoapi/neural_compressor/adaptor/torch_utils/hawq_metric/index", "autoapi/neural_compressor/adaptor/torch_utils/index", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/index", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/modified_pickle/index", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/quantize/index", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/torch_load/index", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/utils/index", "autoapi/neural_compressor/adaptor/torch_utils/model_wrapper/index", "autoapi/neural_compressor/adaptor/torch_utils/pattern_detector/index", "autoapi/neural_compressor/adaptor/torch_utils/symbolic_trace/index", "autoapi/neural_compressor/adaptor/torch_utils/util/index", "autoapi/neural_compressor/algorithm/algorithm/index", "autoapi/neural_compressor/algorithm/fast_bias_correction/index", "autoapi/neural_compressor/algorithm/index", "autoapi/neural_compressor/algorithm/smooth_quant/index", "autoapi/neural_compressor/algorithm/weight_correction/index", "autoapi/neural_compressor/benchmark/index", "autoapi/neural_compressor/common/base_config/index", "autoapi/neural_compressor/common/base_tuning/index", "autoapi/neural_compressor/common/benchmark/index", "autoapi/neural_compressor/common/index", "autoapi/neural_compressor/common/tuning_param/index", "autoapi/neural_compressor/common/utils/constants/index", "autoapi/neural_compressor/common/utils/index", "autoapi/neural_compressor/common/utils/logger/index", "autoapi/neural_compressor/common/utils/save_load/index", "autoapi/neural_compressor/common/utils/utility/index", "autoapi/neural_compressor/compression/callbacks/index", "autoapi/neural_compressor/compression/distillation/criterions/index", "autoapi/neural_compressor/compression/distillation/index", "autoapi/neural_compressor/compression/distillation/optimizers/index", "autoapi/neural_compressor/compression/distillation/utility/index", "autoapi/neural_compressor/compression/hpo/index", "autoapi/neural_compressor/compression/hpo/sa_optimizer/index", "autoapi/neural_compressor/compression/pruner/criteria/index", "autoapi/neural_compressor/compression/pruner/index", "autoapi/neural_compressor/compression/pruner/model_slim/auto_slim/index", "autoapi/neural_compressor/compression/pruner/model_slim/index", "autoapi/neural_compressor/compression/pruner/model_slim/pattern_analyzer/index", "autoapi/neural_compressor/compression/pruner/model_slim/weight_slim/index", "autoapi/neural_compressor/compression/pruner/patterns/base/index", "autoapi/neural_compressor/compression/pruner/patterns/index", "autoapi/neural_compressor/compression/pruner/patterns/mha/index", "autoapi/neural_compressor/compression/pruner/patterns/ninm/index", "autoapi/neural_compressor/compression/pruner/patterns/nxm/index", "autoapi/neural_compressor/compression/pruner/pruners/base/index", "autoapi/neural_compressor/compression/pruner/pruners/basic/index", "autoapi/neural_compressor/compression/pruner/pruners/block_mask/index", "autoapi/neural_compressor/compression/pruner/pruners/index", "autoapi/neural_compressor/compression/pruner/pruners/mha/index", "autoapi/neural_compressor/compression/pruner/pruners/pattern_lock/index", "autoapi/neural_compressor/compression/pruner/pruners/progressive/index", "autoapi/neural_compressor/compression/pruner/pruners/retrain_free/index", "autoapi/neural_compressor/compression/pruner/pruning/index", "autoapi/neural_compressor/compression/pruner/regs/index", "autoapi/neural_compressor/compression/pruner/schedulers/index", "autoapi/neural_compressor/compression/pruner/tf_criteria/index", "autoapi/neural_compressor/compression/pruner/utils/index", "autoapi/neural_compressor/compression/pruner/wanda/index", "autoapi/neural_compressor/compression/pruner/wanda/utils/index", "autoapi/neural_compressor/config/index", "autoapi/neural_compressor/contrib/index", "autoapi/neural_compressor/contrib/strategy/index", "autoapi/neural_compressor/contrib/strategy/sigopt/index", "autoapi/neural_compressor/contrib/strategy/tpe/index", "autoapi/neural_compressor/data/dataloaders/base_dataloader/index", "autoapi/neural_compressor/data/dataloaders/dataloader/index", "autoapi/neural_compressor/data/dataloaders/default_dataloader/index", "autoapi/neural_compressor/data/dataloaders/fetcher/index", "autoapi/neural_compressor/data/dataloaders/mxnet_dataloader/index", "autoapi/neural_compressor/data/dataloaders/onnxrt_dataloader/index", "autoapi/neural_compressor/data/dataloaders/pytorch_dataloader/index", "autoapi/neural_compressor/data/dataloaders/sampler/index", "autoapi/neural_compressor/data/dataloaders/tensorflow_dataloader/index", "autoapi/neural_compressor/data/datasets/bert_dataset/index", "autoapi/neural_compressor/data/datasets/coco_dataset/index", "autoapi/neural_compressor/data/datasets/dataset/index", "autoapi/neural_compressor/data/datasets/dummy_dataset/index", "autoapi/neural_compressor/data/datasets/dummy_dataset_v2/index", "autoapi/neural_compressor/data/datasets/imagenet_dataset/index", "autoapi/neural_compressor/data/datasets/index", "autoapi/neural_compressor/data/datasets/style_transfer_dataset/index", "autoapi/neural_compressor/data/filters/coco_filter/index", "autoapi/neural_compressor/data/filters/filter/index", "autoapi/neural_compressor/data/filters/index", "autoapi/neural_compressor/data/index", "autoapi/neural_compressor/data/transforms/imagenet_transform/index", "autoapi/neural_compressor/data/transforms/index", "autoapi/neural_compressor/data/transforms/postprocess/index", "autoapi/neural_compressor/data/transforms/tokenization/index", "autoapi/neural_compressor/data/transforms/transform/index", "autoapi/neural_compressor/index", "autoapi/neural_compressor/metric/bleu/index", "autoapi/neural_compressor/metric/bleu_util/index", "autoapi/neural_compressor/metric/coco_label_map/index", "autoapi/neural_compressor/metric/coco_tools/index", "autoapi/neural_compressor/metric/evaluate_squad/index", "autoapi/neural_compressor/metric/f1/index", "autoapi/neural_compressor/metric/index", "autoapi/neural_compressor/metric/metric/index", "autoapi/neural_compressor/mix_precision/index", "autoapi/neural_compressor/model/base_model/index", "autoapi/neural_compressor/model/index", "autoapi/neural_compressor/model/keras_model/index", "autoapi/neural_compressor/model/model/index", "autoapi/neural_compressor/model/mxnet_model/index", "autoapi/neural_compressor/model/nets_factory/index", "autoapi/neural_compressor/model/onnx_model/index", "autoapi/neural_compressor/model/tensorflow_model/index", "autoapi/neural_compressor/model/torch_model/index", "autoapi/neural_compressor/objective/index", "autoapi/neural_compressor/profiling/index", "autoapi/neural_compressor/profiling/parser/factory/index", "autoapi/neural_compressor/profiling/parser/onnx_parser/factory/index", "autoapi/neural_compressor/profiling/parser/onnx_parser/parser/index", "autoapi/neural_compressor/profiling/parser/parser/index", "autoapi/neural_compressor/profiling/parser/result/index", "autoapi/neural_compressor/profiling/parser/tensorflow_parser/factory/index", "autoapi/neural_compressor/profiling/parser/tensorflow_parser/parser/index", "autoapi/neural_compressor/profiling/profiler/factory/index", "autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/factory/index", "autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/profiler/index", "autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/utils/index", "autoapi/neural_compressor/profiling/profiler/profiler/index", "autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/factory/index", "autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/profiler/index", "autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/utils/index", "autoapi/neural_compressor/quantization/index", "autoapi/neural_compressor/strategy/auto/index", "autoapi/neural_compressor/strategy/auto_mixed_precision/index", "autoapi/neural_compressor/strategy/basic/index", "autoapi/neural_compressor/strategy/bayesian/index", "autoapi/neural_compressor/strategy/conservative/index", "autoapi/neural_compressor/strategy/exhaustive/index", "autoapi/neural_compressor/strategy/hawq_v2/index", "autoapi/neural_compressor/strategy/index", "autoapi/neural_compressor/strategy/mse/index", "autoapi/neural_compressor/strategy/mse_v2/index", "autoapi/neural_compressor/strategy/random/index", "autoapi/neural_compressor/strategy/strategy/index", "autoapi/neural_compressor/strategy/utils/constant/index", "autoapi/neural_compressor/strategy/utils/index", "autoapi/neural_compressor/strategy/utils/tuning_sampler/index", "autoapi/neural_compressor/strategy/utils/tuning_space/index", "autoapi/neural_compressor/strategy/utils/tuning_structs/index", "autoapi/neural_compressor/strategy/utils/utility/index", "autoapi/neural_compressor/template/api_doc_example/index", "autoapi/neural_compressor/tensorflow/algorithms/index", "autoapi/neural_compressor/tensorflow/algorithms/smoother/calibration/index", "autoapi/neural_compressor/tensorflow/algorithms/smoother/core/index", "autoapi/neural_compressor/tensorflow/algorithms/smoother/index", "autoapi/neural_compressor/tensorflow/algorithms/smoother/scaler/index", "autoapi/neural_compressor/tensorflow/algorithms/static_quant/index", "autoapi/neural_compressor/tensorflow/algorithms/static_quant/keras/index", "autoapi/neural_compressor/tensorflow/algorithms/static_quant/tensorflow/index", "autoapi/neural_compressor/tensorflow/index", "autoapi/neural_compressor/tensorflow/keras/index", "autoapi/neural_compressor/tensorflow/keras/layers/conv2d/index", "autoapi/neural_compressor/tensorflow/keras/layers/dense/index", "autoapi/neural_compressor/tensorflow/keras/layers/depthwise_conv2d/index", "autoapi/neural_compressor/tensorflow/keras/layers/index", "autoapi/neural_compressor/tensorflow/keras/layers/layer_initializer/index", "autoapi/neural_compressor/tensorflow/keras/layers/pool2d/index", "autoapi/neural_compressor/tensorflow/keras/layers/separable_conv2d/index", "autoapi/neural_compressor/tensorflow/keras/quantization/config/index", "autoapi/neural_compressor/tensorflow/keras/quantization/index", "autoapi/neural_compressor/tensorflow/quantization/algorithm_entry/index", "autoapi/neural_compressor/tensorflow/quantization/autotune/index", "autoapi/neural_compressor/tensorflow/quantization/config/index", "autoapi/neural_compressor/tensorflow/quantization/index", "autoapi/neural_compressor/tensorflow/quantization/quantize/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_converter/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/bf16_convert/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/dequantize_cast_optimizer/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_add_to_biasadd/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_layout/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_leakyrelu/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_nan_to_random/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_placeholder_to_const/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dilated_contraction/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dummy_biasadd/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/expanddims_optimizer/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fetch_weight_from_reshape/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_batch_norm/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_constant/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_biasadd_add/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_column_wise_mul/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_conv_with_math/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_bn/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_in/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_gelu/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_layer_norm/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_conv/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_reshape_transpose/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/graph_cse_optimizer/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/grappler_pass/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/insert_print_node/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/move_squeeze_after_relu/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/pre_optimize/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/remove_training_nodes/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/rename_batch_norm/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/split_shared_input/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_equivalent_nodes/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_unused_nodes/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/switch_optimizer/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/graph_base/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_fake_quant/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_value/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_requantize/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_requantize/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/meta_op_optimizer/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_hostconst_converter/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_quantized_op_cse/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/scale_propagation/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/insert_qdq_pattern/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/merge_duplicated_qdq/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/share_qdq_y_pattern/index", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_util/index", "autoapi/neural_compressor/tensorflow/quantization/utils/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_bn/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_concatv2/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_conv/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_deconv/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_in/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_matmul/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_pooling/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/optimize_qdq/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_base/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_bn/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_concatv2/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_conv/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_for_intel_cpu/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_matmul/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_pooling/index", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph_common/index", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/bias_correction/index", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/graph_transform_base/index", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/index", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/insert_logging/index", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/rerange_quantized_concat/index", "autoapi/neural_compressor/tensorflow/quantization/utils/utility/index", "autoapi/neural_compressor/tensorflow/utils/constants/index", "autoapi/neural_compressor/tensorflow/utils/data/index", "autoapi/neural_compressor/tensorflow/utils/index", "autoapi/neural_compressor/tensorflow/utils/model/index", "autoapi/neural_compressor/tensorflow/utils/model_wrappers/index", "autoapi/neural_compressor/tensorflow/utils/utility/index", "autoapi/neural_compressor/torch/algorithms/base_algorithm/index", "autoapi/neural_compressor/torch/algorithms/fp8_quant/utils/logger/index", "autoapi/neural_compressor/torch/algorithms/index", "autoapi/neural_compressor/torch/algorithms/layer_wise/index", "autoapi/neural_compressor/torch/algorithms/layer_wise/load/index", "autoapi/neural_compressor/torch/algorithms/layer_wise/modified_pickle/index", "autoapi/neural_compressor/torch/algorithms/layer_wise/utils/index", "autoapi/neural_compressor/torch/algorithms/mixed_precision/half_precision_convert/index", "autoapi/neural_compressor/torch/algorithms/mixed_precision/index", "autoapi/neural_compressor/torch/algorithms/mixed_precision/module_wrappers/index", "autoapi/neural_compressor/torch/algorithms/mx_quant/index", "autoapi/neural_compressor/torch/algorithms/mx_quant/mx/index", "autoapi/neural_compressor/torch/algorithms/mx_quant/utils/index", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/core/index", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/half_precision_rewriter/index", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/index", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/save_load/index", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/utility/index", "autoapi/neural_compressor/torch/algorithms/smooth_quant/index", "autoapi/neural_compressor/torch/algorithms/smooth_quant/save_load/index", "autoapi/neural_compressor/torch/algorithms/smooth_quant/smooth_quant/index", "autoapi/neural_compressor/torch/algorithms/smooth_quant/utility/index", "autoapi/neural_compressor/torch/algorithms/static_quant/index", "autoapi/neural_compressor/torch/algorithms/static_quant/save_load/index", "autoapi/neural_compressor/torch/algorithms/static_quant/static_quant/index", "autoapi/neural_compressor/torch/algorithms/static_quant/utility/index", "autoapi/neural_compressor/torch/algorithms/weight_only/autoround/index", "autoapi/neural_compressor/torch/algorithms/weight_only/awq/index", "autoapi/neural_compressor/torch/algorithms/weight_only/gptq/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/bitpack/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/config/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/core/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/optimizer/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/qtensor/index", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/quantizer/index", "autoapi/neural_compressor/torch/algorithms/weight_only/index", "autoapi/neural_compressor/torch/algorithms/weight_only/modules/index", "autoapi/neural_compressor/torch/algorithms/weight_only/rtn/index", "autoapi/neural_compressor/torch/algorithms/weight_only/save_load/index", "autoapi/neural_compressor/torch/algorithms/weight_only/teq/index", "autoapi/neural_compressor/torch/algorithms/weight_only/utility/index", "autoapi/neural_compressor/torch/export/index", "autoapi/neural_compressor/torch/export/pt2e_export/index", "autoapi/neural_compressor/torch/index", "autoapi/neural_compressor/torch/quantization/algorithm_entry/index", "autoapi/neural_compressor/torch/quantization/autotune/index", "autoapi/neural_compressor/torch/quantization/config/index", "autoapi/neural_compressor/torch/quantization/index", "autoapi/neural_compressor/torch/quantization/load_entry/index", "autoapi/neural_compressor/torch/quantization/quantize/index", "autoapi/neural_compressor/torch/utils/auto_accelerator/index", "autoapi/neural_compressor/torch/utils/constants/index", "autoapi/neural_compressor/torch/utils/environ/index", "autoapi/neural_compressor/torch/utils/index", "autoapi/neural_compressor/torch/utils/utility/index", "autoapi/neural_compressor/training/index", "autoapi/neural_compressor/transformers/quantization/utils/index", "autoapi/neural_compressor/transformers/utils/index", "autoapi/neural_compressor/transformers/utils/quantization_config/index", "autoapi/neural_compressor/utils/collect_layer_histogram/index", "autoapi/neural_compressor/utils/constant/index", "autoapi/neural_compressor/utils/create_obj_from_config/index", "autoapi/neural_compressor/utils/export/index", "autoapi/neural_compressor/utils/export/qlinear2qdq/index", "autoapi/neural_compressor/utils/export/tf2onnx/index", "autoapi/neural_compressor/utils/export/torch2onnx/index", "autoapi/neural_compressor/utils/index", "autoapi/neural_compressor/utils/kl_divergence/index", "autoapi/neural_compressor/utils/load_huggingface/index", "autoapi/neural_compressor/utils/logger/index", "autoapi/neural_compressor/utils/options/index", "autoapi/neural_compressor/utils/pytorch/index", "autoapi/neural_compressor/utils/utility/index", "autoapi/neural_compressor/utils/weights_details/index", "autoapi/neural_compressor/version/index", "docs/build_docs/source/index", "docs/source/2x_user_guide", "docs/source/3x/PT_DynamicQuant", "docs/source/3x/PT_FP8Quant", "docs/source/3x/PT_MXQuant", "docs/source/3x/PT_MixedPrecision", "docs/source/3x/PT_SmoothQuant", "docs/source/3x/PT_StaticQuant", "docs/source/3x/PT_WeightOnlyQuant", "docs/source/3x/PyTorch", "docs/source/3x/TF_Quant", "docs/source/3x/TF_SQ", "docs/source/3x/TensorFlow", "docs/source/3x/autotune", "docs/source/3x/benchmark", "docs/source/3x/client_quant", "docs/source/3x/design", "docs/source/3x/gaudi_version_map", "docs/source/3x/llm_recipes", "docs/source/3x/quantization", "docs/source/CODE_OF_CONDUCT", "docs/source/CONTRIBUTING", "docs/source/FX", "docs/source/SECURITY", "docs/source/Welcome", "docs/source/adaptor", "docs/source/add_new_adaptor", "docs/source/add_new_data_type", "docs/source/api-doc/adaptor", "docs/source/api-doc/adaptor/onnxrt", "docs/source/api-doc/adaptor/torch_utils", "docs/source/api-doc/api_2", "docs/source/api-doc/api_3", "docs/source/api-doc/api_doc_example", "docs/source/api-doc/apis", "docs/source/api-doc/benchmark", "docs/source/api-doc/compression", "docs/source/api-doc/config", "docs/source/api-doc/mix_precision", "docs/source/api-doc/model", "docs/source/api-doc/objective", "docs/source/api-doc/quantization", "docs/source/api-doc/strategy", "docs/source/api-doc/tf_quantization_autotune", "docs/source/api-doc/tf_quantization_common", "docs/source/api-doc/tf_quantization_config", "docs/source/api-doc/torch_quantization_autotune", "docs/source/api-doc/torch_quantization_common", "docs/source/api-doc/torch_quantization_config", "docs/source/api-doc/training", "docs/source/benchmark", "docs/source/calibration", "docs/source/coding_style", "docs/source/dataloader", "docs/source/design", "docs/source/distillation_quantization", "docs/source/distributed", "docs/source/examples_readme", "docs/source/export", "docs/source/faq", "docs/source/framework_yaml", "docs/source/get_started", "docs/source/incompatible_changes", "docs/source/infrastructure", "docs/source/installation_guide", "docs/source/legal_information", "docs/source/llm_recipes", "docs/source/metric", "docs/source/migration", "docs/source/mixed_precision", "docs/source/model", "docs/source/mx_quantization", "docs/source/objective", "docs/source/orchestration", "docs/source/pruning", "docs/source/publication_list", "docs/source/quantization", "docs/source/quantization_layer_wise", "docs/source/quantization_mixed_precision", "docs/source/quantization_weight_only", "docs/source/releases_info", "docs/source/sigopt_strategy", "docs/source/smooth_quant", "docs/source/transform", "docs/source/tuning_strategies", "docs/source/validated_model_list", "index"], "envversion": {"sphinx": 61, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2}, "filenames": ["autoapi/neural_compressor/adaptor/mxnet_utils/index.rst", "autoapi/neural_compressor/adaptor/mxnet_utils/util/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/calibration/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/calibrator/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/activation/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/argmax/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/attention/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/binary_op/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/concat/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/conv/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/direct_q8/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/embed_layernorm/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/gather/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/gavgpool/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/gemm/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/lstm/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/matmul/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/maxpool/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/norm/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/ops/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/pad/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/pooling/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/reduce/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/resize/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/split/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/operators/unary_op/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/quantizer/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/smooth_quant/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/util/index.rst", "autoapi/neural_compressor/adaptor/ox_utils/weight_only/index.rst", "autoapi/neural_compressor/adaptor/tensorflow/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_converter/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_converter_without_calib/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/bf16_convert/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/dequantize_cast_optimizer/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_add_to_biasadd/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_layout/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_leakyrelu/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_nan_to_random/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_placeholder_to_const/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dilated_contraction/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dummy_biasadd/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/expanddims_optimizer/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fetch_weight_from_reshape/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_batch_norm/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_constant/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_biasadd_add/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_column_wise_mul/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_conv_with_math/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_bn/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_in/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_gelu/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_layer_norm/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_conv/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_reshape_transpose/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/graph_cse_optimizer/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/grappler_pass/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/insert_print_node/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/move_squeeze_after_relu/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/pre_optimize/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/remove_training_nodes/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/rename_batch_norm/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/split_shared_input/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_equivalent_nodes/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_unused_nodes/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/generic/switch_optimizer/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/graph_base/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_fake_quant/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value_without_calib/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_requantize/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_requantize/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/meta_op_optimizer/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_hostconst_converter/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_quantized_op_cse/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/rnn_convert/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/int8/scale_propagation/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_graph/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_node/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_schema/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/tf2onnx_utils/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/insert_qdq_pattern/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/merge_duplicated_qdq/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/share_qdq_y_pattern/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/graph_util/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/fake_quantize/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_config/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_helper/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/optimize_layer/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_add/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_base/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_bn/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_wrapper/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_bn/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_concatv2/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_conv/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_deconv/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_in/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_matmul/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_pooling/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/qdq/optimize_qdq/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_base/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_bn/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_concatv2/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_conv/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_for_intel_cpu/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_matmul/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_pooling/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/quantize_graph_common/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_calibration/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/smooth_quant_scaler/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/tf2onnx_converter/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/bias_correction/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/graph_transform_base/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/insert_logging/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/transform_graph/rerange_quantized_concat/index.rst", "autoapi/neural_compressor/adaptor/tf_utils/util/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/bf16_convert/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/hawq_metric/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/modified_pickle/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/quantize/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/torch_load/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/layer_wise_quant/utils/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/model_wrapper/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/pattern_detector/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/symbolic_trace/index.rst", "autoapi/neural_compressor/adaptor/torch_utils/util/index.rst", "autoapi/neural_compressor/algorithm/algorithm/index.rst", "autoapi/neural_compressor/algorithm/fast_bias_correction/index.rst", "autoapi/neural_compressor/algorithm/index.rst", "autoapi/neural_compressor/algorithm/smooth_quant/index.rst", "autoapi/neural_compressor/algorithm/weight_correction/index.rst", "autoapi/neural_compressor/benchmark/index.rst", "autoapi/neural_compressor/common/base_config/index.rst", "autoapi/neural_compressor/common/base_tuning/index.rst", "autoapi/neural_compressor/common/benchmark/index.rst", "autoapi/neural_compressor/common/index.rst", "autoapi/neural_compressor/common/tuning_param/index.rst", "autoapi/neural_compressor/common/utils/constants/index.rst", "autoapi/neural_compressor/common/utils/index.rst", "autoapi/neural_compressor/common/utils/logger/index.rst", "autoapi/neural_compressor/common/utils/save_load/index.rst", "autoapi/neural_compressor/common/utils/utility/index.rst", "autoapi/neural_compressor/compression/callbacks/index.rst", "autoapi/neural_compressor/compression/distillation/criterions/index.rst", "autoapi/neural_compressor/compression/distillation/index.rst", "autoapi/neural_compressor/compression/distillation/optimizers/index.rst", "autoapi/neural_compressor/compression/distillation/utility/index.rst", "autoapi/neural_compressor/compression/hpo/index.rst", "autoapi/neural_compressor/compression/hpo/sa_optimizer/index.rst", "autoapi/neural_compressor/compression/pruner/criteria/index.rst", "autoapi/neural_compressor/compression/pruner/index.rst", "autoapi/neural_compressor/compression/pruner/model_slim/auto_slim/index.rst", "autoapi/neural_compressor/compression/pruner/model_slim/index.rst", "autoapi/neural_compressor/compression/pruner/model_slim/pattern_analyzer/index.rst", "autoapi/neural_compressor/compression/pruner/model_slim/weight_slim/index.rst", "autoapi/neural_compressor/compression/pruner/patterns/base/index.rst", "autoapi/neural_compressor/compression/pruner/patterns/index.rst", "autoapi/neural_compressor/compression/pruner/patterns/mha/index.rst", "autoapi/neural_compressor/compression/pruner/patterns/ninm/index.rst", "autoapi/neural_compressor/compression/pruner/patterns/nxm/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/base/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/basic/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/block_mask/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/mha/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/pattern_lock/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/progressive/index.rst", "autoapi/neural_compressor/compression/pruner/pruners/retrain_free/index.rst", "autoapi/neural_compressor/compression/pruner/pruning/index.rst", "autoapi/neural_compressor/compression/pruner/regs/index.rst", "autoapi/neural_compressor/compression/pruner/schedulers/index.rst", "autoapi/neural_compressor/compression/pruner/tf_criteria/index.rst", "autoapi/neural_compressor/compression/pruner/utils/index.rst", "autoapi/neural_compressor/compression/pruner/wanda/index.rst", "autoapi/neural_compressor/compression/pruner/wanda/utils/index.rst", "autoapi/neural_compressor/config/index.rst", "autoapi/neural_compressor/contrib/index.rst", "autoapi/neural_compressor/contrib/strategy/index.rst", "autoapi/neural_compressor/contrib/strategy/sigopt/index.rst", "autoapi/neural_compressor/contrib/strategy/tpe/index.rst", "autoapi/neural_compressor/data/dataloaders/base_dataloader/index.rst", "autoapi/neural_compressor/data/dataloaders/dataloader/index.rst", "autoapi/neural_compressor/data/dataloaders/default_dataloader/index.rst", "autoapi/neural_compressor/data/dataloaders/fetcher/index.rst", "autoapi/neural_compressor/data/dataloaders/mxnet_dataloader/index.rst", "autoapi/neural_compressor/data/dataloaders/onnxrt_dataloader/index.rst", "autoapi/neural_compressor/data/dataloaders/pytorch_dataloader/index.rst", "autoapi/neural_compressor/data/dataloaders/sampler/index.rst", "autoapi/neural_compressor/data/dataloaders/tensorflow_dataloader/index.rst", "autoapi/neural_compressor/data/datasets/bert_dataset/index.rst", "autoapi/neural_compressor/data/datasets/coco_dataset/index.rst", "autoapi/neural_compressor/data/datasets/dataset/index.rst", "autoapi/neural_compressor/data/datasets/dummy_dataset/index.rst", "autoapi/neural_compressor/data/datasets/dummy_dataset_v2/index.rst", "autoapi/neural_compressor/data/datasets/imagenet_dataset/index.rst", "autoapi/neural_compressor/data/datasets/index.rst", "autoapi/neural_compressor/data/datasets/style_transfer_dataset/index.rst", "autoapi/neural_compressor/data/filters/coco_filter/index.rst", "autoapi/neural_compressor/data/filters/filter/index.rst", "autoapi/neural_compressor/data/filters/index.rst", "autoapi/neural_compressor/data/index.rst", "autoapi/neural_compressor/data/transforms/imagenet_transform/index.rst", "autoapi/neural_compressor/data/transforms/index.rst", "autoapi/neural_compressor/data/transforms/postprocess/index.rst", "autoapi/neural_compressor/data/transforms/tokenization/index.rst", "autoapi/neural_compressor/data/transforms/transform/index.rst", "autoapi/neural_compressor/index.rst", "autoapi/neural_compressor/metric/bleu/index.rst", "autoapi/neural_compressor/metric/bleu_util/index.rst", "autoapi/neural_compressor/metric/coco_label_map/index.rst", "autoapi/neural_compressor/metric/coco_tools/index.rst", "autoapi/neural_compressor/metric/evaluate_squad/index.rst", "autoapi/neural_compressor/metric/f1/index.rst", "autoapi/neural_compressor/metric/index.rst", "autoapi/neural_compressor/metric/metric/index.rst", "autoapi/neural_compressor/mix_precision/index.rst", "autoapi/neural_compressor/model/base_model/index.rst", "autoapi/neural_compressor/model/index.rst", "autoapi/neural_compressor/model/keras_model/index.rst", "autoapi/neural_compressor/model/model/index.rst", "autoapi/neural_compressor/model/mxnet_model/index.rst", "autoapi/neural_compressor/model/nets_factory/index.rst", "autoapi/neural_compressor/model/onnx_model/index.rst", "autoapi/neural_compressor/model/tensorflow_model/index.rst", "autoapi/neural_compressor/model/torch_model/index.rst", "autoapi/neural_compressor/objective/index.rst", "autoapi/neural_compressor/profiling/index.rst", "autoapi/neural_compressor/profiling/parser/factory/index.rst", "autoapi/neural_compressor/profiling/parser/onnx_parser/factory/index.rst", "autoapi/neural_compressor/profiling/parser/onnx_parser/parser/index.rst", "autoapi/neural_compressor/profiling/parser/parser/index.rst", "autoapi/neural_compressor/profiling/parser/result/index.rst", "autoapi/neural_compressor/profiling/parser/tensorflow_parser/factory/index.rst", "autoapi/neural_compressor/profiling/parser/tensorflow_parser/parser/index.rst", "autoapi/neural_compressor/profiling/profiler/factory/index.rst", "autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/factory/index.rst", "autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/profiler/index.rst", "autoapi/neural_compressor/profiling/profiler/onnxrt_profiler/utils/index.rst", "autoapi/neural_compressor/profiling/profiler/profiler/index.rst", "autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/factory/index.rst", "autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/profiler/index.rst", "autoapi/neural_compressor/profiling/profiler/tensorflow_profiler/utils/index.rst", "autoapi/neural_compressor/quantization/index.rst", "autoapi/neural_compressor/strategy/auto/index.rst", "autoapi/neural_compressor/strategy/auto_mixed_precision/index.rst", "autoapi/neural_compressor/strategy/basic/index.rst", "autoapi/neural_compressor/strategy/bayesian/index.rst", "autoapi/neural_compressor/strategy/conservative/index.rst", "autoapi/neural_compressor/strategy/exhaustive/index.rst", "autoapi/neural_compressor/strategy/hawq_v2/index.rst", "autoapi/neural_compressor/strategy/index.rst", "autoapi/neural_compressor/strategy/mse/index.rst", "autoapi/neural_compressor/strategy/mse_v2/index.rst", "autoapi/neural_compressor/strategy/random/index.rst", "autoapi/neural_compressor/strategy/strategy/index.rst", "autoapi/neural_compressor/strategy/utils/constant/index.rst", "autoapi/neural_compressor/strategy/utils/index.rst", "autoapi/neural_compressor/strategy/utils/tuning_sampler/index.rst", "autoapi/neural_compressor/strategy/utils/tuning_space/index.rst", "autoapi/neural_compressor/strategy/utils/tuning_structs/index.rst", "autoapi/neural_compressor/strategy/utils/utility/index.rst", "autoapi/neural_compressor/template/api_doc_example/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/smoother/calibration/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/smoother/core/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/smoother/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/smoother/scaler/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/static_quant/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/static_quant/keras/index.rst", "autoapi/neural_compressor/tensorflow/algorithms/static_quant/tensorflow/index.rst", "autoapi/neural_compressor/tensorflow/index.rst", "autoapi/neural_compressor/tensorflow/keras/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/conv2d/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/dense/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/depthwise_conv2d/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/layer_initializer/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/pool2d/index.rst", "autoapi/neural_compressor/tensorflow/keras/layers/separable_conv2d/index.rst", "autoapi/neural_compressor/tensorflow/keras/quantization/config/index.rst", "autoapi/neural_compressor/tensorflow/keras/quantization/index.rst", "autoapi/neural_compressor/tensorflow/quantization/algorithm_entry/index.rst", "autoapi/neural_compressor/tensorflow/quantization/autotune/index.rst", "autoapi/neural_compressor/tensorflow/quantization/config/index.rst", "autoapi/neural_compressor/tensorflow/quantization/index.rst", "autoapi/neural_compressor/tensorflow/quantization/quantize/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_converter/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/bf16_convert/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/dequantize_cast_optimizer/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_add_to_biasadd/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_layout/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_leakyrelu/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_nan_to_random/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_placeholder_to_const/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dilated_contraction/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dummy_biasadd/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/expanddims_optimizer/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fetch_weight_from_reshape/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_batch_norm/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_constant/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_biasadd_add/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_column_wise_mul/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_conv_with_math/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_bn/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_in/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_gelu/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_layer_norm/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_conv/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_fp32_conv/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_reshape_transpose/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/graph_cse_optimizer/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/grappler_pass/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/insert_print_node/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/move_squeeze_after_relu/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/pre_optimize/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/remove_training_nodes/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/rename_batch_norm/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/split_shared_input/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_equivalent_nodes/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_unused_nodes/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/switch_optimizer/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/graph_base/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_fake_quant/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_value/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_redundant_dequantize/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_requantize/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_requantize/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/meta_op_optimizer/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_hostconst_converter/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_quantized_op_cse/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/scale_propagation/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/insert_qdq_pattern/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/merge_duplicated_qdq/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/share_qdq_y_pattern/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/graph_util/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_bn/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_concatv2/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_conv/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_deconv/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_in/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_matmul/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_pooling/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/optimize_qdq/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_base/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_bn/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_concatv2/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_conv/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_for_intel_cpu/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_matmul/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_pooling/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/quantize_graph_common/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/bias_correction/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/graph_transform_base/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/insert_logging/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/transform_graph/rerange_quantized_concat/index.rst", "autoapi/neural_compressor/tensorflow/quantization/utils/utility/index.rst", "autoapi/neural_compressor/tensorflow/utils/constants/index.rst", "autoapi/neural_compressor/tensorflow/utils/data/index.rst", "autoapi/neural_compressor/tensorflow/utils/index.rst", "autoapi/neural_compressor/tensorflow/utils/model/index.rst", "autoapi/neural_compressor/tensorflow/utils/model_wrappers/index.rst", "autoapi/neural_compressor/tensorflow/utils/utility/index.rst", "autoapi/neural_compressor/torch/algorithms/base_algorithm/index.rst", "autoapi/neural_compressor/torch/algorithms/fp8_quant/utils/logger/index.rst", "autoapi/neural_compressor/torch/algorithms/index.rst", "autoapi/neural_compressor/torch/algorithms/layer_wise/index.rst", "autoapi/neural_compressor/torch/algorithms/layer_wise/load/index.rst", "autoapi/neural_compressor/torch/algorithms/layer_wise/modified_pickle/index.rst", "autoapi/neural_compressor/torch/algorithms/layer_wise/utils/index.rst", "autoapi/neural_compressor/torch/algorithms/mixed_precision/half_precision_convert/index.rst", "autoapi/neural_compressor/torch/algorithms/mixed_precision/index.rst", "autoapi/neural_compressor/torch/algorithms/mixed_precision/module_wrappers/index.rst", "autoapi/neural_compressor/torch/algorithms/mx_quant/index.rst", "autoapi/neural_compressor/torch/algorithms/mx_quant/mx/index.rst", "autoapi/neural_compressor/torch/algorithms/mx_quant/utils/index.rst", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/core/index.rst", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/half_precision_rewriter/index.rst", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/index.rst", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/save_load/index.rst", "autoapi/neural_compressor/torch/algorithms/pt2e_quant/utility/index.rst", "autoapi/neural_compressor/torch/algorithms/smooth_quant/index.rst", "autoapi/neural_compressor/torch/algorithms/smooth_quant/save_load/index.rst", "autoapi/neural_compressor/torch/algorithms/smooth_quant/smooth_quant/index.rst", "autoapi/neural_compressor/torch/algorithms/smooth_quant/utility/index.rst", "autoapi/neural_compressor/torch/algorithms/static_quant/index.rst", "autoapi/neural_compressor/torch/algorithms/static_quant/save_load/index.rst", "autoapi/neural_compressor/torch/algorithms/static_quant/static_quant/index.rst", "autoapi/neural_compressor/torch/algorithms/static_quant/utility/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/autoround/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/awq/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/gptq/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/bitpack/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/config/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/core/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/optimizer/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/qtensor/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/hqq/quantizer/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/modules/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/rtn/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/save_load/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/teq/index.rst", "autoapi/neural_compressor/torch/algorithms/weight_only/utility/index.rst", "autoapi/neural_compressor/torch/export/index.rst", "autoapi/neural_compressor/torch/export/pt2e_export/index.rst", "autoapi/neural_compressor/torch/index.rst", "autoapi/neural_compressor/torch/quantization/algorithm_entry/index.rst", "autoapi/neural_compressor/torch/quantization/autotune/index.rst", "autoapi/neural_compressor/torch/quantization/config/index.rst", "autoapi/neural_compressor/torch/quantization/index.rst", "autoapi/neural_compressor/torch/quantization/load_entry/index.rst", "autoapi/neural_compressor/torch/quantization/quantize/index.rst", "autoapi/neural_compressor/torch/utils/auto_accelerator/index.rst", "autoapi/neural_compressor/torch/utils/constants/index.rst", "autoapi/neural_compressor/torch/utils/environ/index.rst", "autoapi/neural_compressor/torch/utils/index.rst", "autoapi/neural_compressor/torch/utils/utility/index.rst", "autoapi/neural_compressor/training/index.rst", "autoapi/neural_compressor/transformers/quantization/utils/index.rst", "autoapi/neural_compressor/transformers/utils/index.rst", "autoapi/neural_compressor/transformers/utils/quantization_config/index.rst", "autoapi/neural_compressor/utils/collect_layer_histogram/index.rst", "autoapi/neural_compressor/utils/constant/index.rst", "autoapi/neural_compressor/utils/create_obj_from_config/index.rst", "autoapi/neural_compressor/utils/export/index.rst", "autoapi/neural_compressor/utils/export/qlinear2qdq/index.rst", "autoapi/neural_compressor/utils/export/tf2onnx/index.rst", "autoapi/neural_compressor/utils/export/torch2onnx/index.rst", "autoapi/neural_compressor/utils/index.rst", "autoapi/neural_compressor/utils/kl_divergence/index.rst", "autoapi/neural_compressor/utils/load_huggingface/index.rst", "autoapi/neural_compressor/utils/logger/index.rst", "autoapi/neural_compressor/utils/options/index.rst", "autoapi/neural_compressor/utils/pytorch/index.rst", "autoapi/neural_compressor/utils/utility/index.rst", "autoapi/neural_compressor/utils/weights_details/index.rst", "autoapi/neural_compressor/version/index.rst", "docs/build_docs/source/index.rst", "docs/source/2x_user_guide.md", "docs/source/3x/PT_DynamicQuant.md", "docs/source/3x/PT_FP8Quant.md", "docs/source/3x/PT_MXQuant.md", "docs/source/3x/PT_MixedPrecision.md", "docs/source/3x/PT_SmoothQuant.md", "docs/source/3x/PT_StaticQuant.md", "docs/source/3x/PT_WeightOnlyQuant.md", "docs/source/3x/PyTorch.md", "docs/source/3x/TF_Quant.md", "docs/source/3x/TF_SQ.md", "docs/source/3x/TensorFlow.md", "docs/source/3x/autotune.md", "docs/source/3x/benchmark.md", "docs/source/3x/client_quant.md", "docs/source/3x/design.md", "docs/source/3x/gaudi_version_map.md", "docs/source/3x/llm_recipes.md", "docs/source/3x/quantization.md", "docs/source/CODE_OF_CONDUCT.md", "docs/source/CONTRIBUTING.md", "docs/source/FX.md", "docs/source/SECURITY.md", "docs/source/Welcome.md", "docs/source/adaptor.md", "docs/source/add_new_adaptor.md", "docs/source/add_new_data_type.md", "docs/source/api-doc/adaptor.rst", "docs/source/api-doc/adaptor/onnxrt.rst", "docs/source/api-doc/adaptor/torch_utils.rst", "docs/source/api-doc/api_2.rst", "docs/source/api-doc/api_3.rst", "docs/source/api-doc/api_doc_example.rst", "docs/source/api-doc/apis.rst", "docs/source/api-doc/benchmark.rst", "docs/source/api-doc/compression.rst", "docs/source/api-doc/config.rst", "docs/source/api-doc/mix_precision.rst", "docs/source/api-doc/model.rst", "docs/source/api-doc/objective.rst", "docs/source/api-doc/quantization.rst", "docs/source/api-doc/strategy.rst", "docs/source/api-doc/tf_quantization_autotune.rst", "docs/source/api-doc/tf_quantization_common.rst", "docs/source/api-doc/tf_quantization_config.rst", "docs/source/api-doc/torch_quantization_autotune.rst", "docs/source/api-doc/torch_quantization_common.rst", "docs/source/api-doc/torch_quantization_config.rst", "docs/source/api-doc/training.rst", "docs/source/benchmark.md", "docs/source/calibration.md", "docs/source/coding_style.md", "docs/source/dataloader.md", "docs/source/design.md", "docs/source/distillation_quantization.md", "docs/source/distributed.md", "docs/source/examples_readme.md", "docs/source/export.md", "docs/source/faq.md", "docs/source/framework_yaml.md", "docs/source/get_started.md", "docs/source/incompatible_changes.md", "docs/source/infrastructure.md", "docs/source/installation_guide.md", "docs/source/legal_information.md", "docs/source/llm_recipes.md", "docs/source/metric.md", "docs/source/migration.md", "docs/source/mixed_precision.md", "docs/source/model.md", "docs/source/mx_quantization.md", "docs/source/objective.md", "docs/source/orchestration.md", "docs/source/pruning.md", "docs/source/publication_list.md", "docs/source/quantization.md", "docs/source/quantization_layer_wise.md", "docs/source/quantization_mixed_precision.md", "docs/source/quantization_weight_only.md", "docs/source/releases_info.md", "docs/source/sigopt_strategy.md", "docs/source/smooth_quant.md", "docs/source/transform.md", "docs/source/tuning_strategies.md", "docs/source/validated_model_list.md", "index.rst"], "indexentries": {"_epoch_ran (neural_compressor.compression.callbacks.distillationcallbacks attribute)": [[162, "neural_compressor.compression.callbacks.DistillationCallbacks._epoch_ran", false]], "acceleratorregistry (class in neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.AcceleratorRegistry", false]], "accuracy (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.Accuracy", false]], "accuracy (class in neural_compressor.objective)": [[245, "neural_compressor.objective.Accuracy", false]], "accuracycriterion (class in neural_compressor.config)": [[195, "neural_compressor.config.AccuracyCriterion", false]], "acq_max() (in module neural_compressor.strategy.bayesian)": [[266, "neural_compressor.strategy.bayesian.acq_max", false]], "activationoperator (class in neural_compressor.adaptor.ox_utils.operators.activation)": [[5, "neural_compressor.adaptor.ox_utils.operators.activation.ActivationOperator", false]], "add_port_to_name() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.add_port_to_name", false]], "algorithm (class in neural_compressor.algorithm.algorithm)": [[146, "neural_compressor.algorithm.algorithm.Algorithm", false]], "algorithm_registry() (in module neural_compressor.algorithm.algorithm)": [[146, "neural_compressor.algorithm.algorithm.algorithm_registry", false]], "algorithms (class in neural_compressor.algorithm.algorithm)": [[146, "neural_compressor.algorithm.algorithm.ALGORITHMS", false]], "algorithmscheduler (class in neural_compressor.algorithm.algorithm)": [[146, "neural_compressor.algorithm.algorithm.AlgorithmScheduler", false]], "alias_param() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.alias_param", false]], "alignimagechanneltransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.AlignImageChannelTransform", false]], "alpha (neural_compressor.compression.pruner.regs.grouplasso attribute)": [[189, "neural_compressor.compression.pruner.regs.GroupLasso.alpha", false]], "amp_convert() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.amp_convert", false]], "append_attr() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.append_attr", false]], "apply_awq_clip() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.apply_awq_clip", false]], "apply_awq_scale() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.apply_awq_scale", false]], "apply_inlining() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.apply_inlining", false]], "apply_inlining() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.apply_inlining", false]], "apply_single_pattern_pair() (in module neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.apply_single_pattern_pair", false]], "are_shapes_equal() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.are_shapes_equal", false]], "argmaxoperator (class in neural_compressor.adaptor.ox_utils.operators.argmax)": [[6, "neural_compressor.adaptor.ox_utils.operators.argmax.ArgMaxOperator", false]], "assert_error() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.assert_error", false]], "attentionoperator (class in neural_compressor.adaptor.ox_utils.operators.attention)": [[7, "neural_compressor.adaptor.ox_utils.operators.attention.AttentionOperator", false]], "attr1 (neural_compressor.template.api_doc_example.exampleclass attribute)": [[281, "neural_compressor.template.api_doc_example.ExampleClass.attr1", false]], "attr2 (neural_compressor.template.api_doc_example.exampleclass attribute)": [[281, "neural_compressor.template.api_doc_example.ExampleClass.attr2", false]], "attr5 (neural_compressor.template.api_doc_example.exampleclass attribute)": [[281, "neural_compressor.template.api_doc_example.ExampleClass.attr5", false]], "attribute1 (in module neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.attribute1", false]], "attribute_to_kwarg() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.attribute_to_kwarg", false]], "auto_accelerator (class in neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.Auto_Accelerator", false]], "auto_copy() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.auto_copy", false]], "auto_detect_accelerator() (in module neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.auto_detect_accelerator", false]], "autoalpha (class in neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.AutoAlpha", false]], "automixedprecisiontunestrategy (class in neural_compressor.strategy.auto_mixed_precision)": [[264, "neural_compressor.strategy.auto_mixed_precision.AutoMixedPrecisionTuneStrategy", false]], "autoround_quantize_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.autoround_quantize_entry", false]], "autoroundconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.AutoRoundConfig", false]], "autoroundconfig (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.AutoRoundConfig", false]], "autoroundquantizer (class in neural_compressor.torch.algorithms.weight_only.autoround)": [[418, "neural_compressor.torch.algorithms.weight_only.autoround.AutoRoundQuantizer", false]], "autotune() (in module neural_compressor.tensorflow.quantization.autotune)": [[302, "neural_compressor.tensorflow.quantization.autotune.autotune", false]], "autotune() (in module neural_compressor.torch.quantization.autotune)": [[438, "neural_compressor.torch.quantization.autotune.autotune", false]], "autotunestrategy (class in neural_compressor.strategy.auto)": [[263, "neural_compressor.strategy.auto.AutoTuneStrategy", false]], "awq_quantize() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.awq_quantize", false]], "awq_quantize_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.awq_quantize_entry", false]], "awqconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.AWQConfig", false]], "awqconfig (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.AwqConfig", false]], "awqquantizer (class in neural_compressor.torch.algorithms.weight_only.awq)": [[419, "neural_compressor.torch.algorithms.weight_only.awq.AWQQuantizer", false]], "axis (neural_compressor.torch.algorithms.weight_only.hqq.qtensor.qtensormetainfo attribute)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo.axis", false]], "basecallbacks (class in neural_compressor.compression.callbacks)": [[162, "neural_compressor.compression.callbacks.BaseCallbacks", false]], "baseconfig (class in neural_compressor.common.base_config)": [[152, "neural_compressor.common.base_config.BaseConfig", false]], "basedataloader (class in neural_compressor.data.dataloaders.base_dataloader)": [[200, "neural_compressor.data.dataloaders.base_dataloader.BaseDataLoader", false]], "basedataloader (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.BaseDataLoader", false]], "basemetric (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.BaseMetric", false]], "basemodel (class in neural_compressor.model.base_model)": [[236, "neural_compressor.model.base_model.BaseModel", false]], "basemodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.BaseModel", false]], "basepattern (class in neural_compressor.compression.pruner.patterns.base)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern", false]], "basepruner (class in neural_compressor.compression.pruner.pruners.base)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner", false]], "basepruning (class in neural_compressor.compression.pruner.pruning)": [[188, "neural_compressor.compression.pruner.pruning.BasePruning", false]], "basereg (class in neural_compressor.compression.pruner.regs)": [[189, "neural_compressor.compression.pruner.regs.BaseReg", false]], "basetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.BaseTransform", false]], "basicpruning (class in neural_compressor.compression.pruner.pruning)": [[188, "neural_compressor.compression.pruner.pruning.BasicPruning", false]], "basictokenizer (class in neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.BasicTokenizer", false]], "basictunestrategy (class in neural_compressor.strategy.basic)": [[265, "neural_compressor.strategy.basic.BasicTuneStrategy", false]], "batchnormalizationoperator (class in neural_compressor.adaptor.ox_utils.operators.norm)": [[20, "neural_compressor.adaptor.ox_utils.operators.norm.BatchNormalizationOperator", false]], "batchsampler (class in neural_compressor.data.dataloaders.sampler)": [[207, "neural_compressor.data.dataloaders.sampler.BatchSampler", false]], "batchsampler (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.BatchSampler", false]], "bayesianoptimization (class in neural_compressor.strategy.bayesian)": [[266, "neural_compressor.strategy.bayesian.BayesianOptimization", false]], "bayesiantunestrategy (class in neural_compressor.strategy.bayesian)": [[266, "neural_compressor.strategy.bayesian.BayesianTuneStrategy", false]], "benchmark() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.benchmark", false]], "benchmark_with_raw_cmd() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.benchmark_with_raw_cmd", false]], "benchmarkconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.BenchmarkConfig", false]], "best_model (neural_compressor.compression.callbacks.distillationcallbacks attribute)": [[162, "neural_compressor.compression.callbacks.DistillationCallbacks.best_model", false]], "best_score (neural_compressor.compression.callbacks.distillationcallbacks attribute)": [[162, "neural_compressor.compression.callbacks.DistillationCallbacks.best_score", false]], "bf16convert (class in neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert)": [[35, "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert.BF16Convert", false]], "bf16convert (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert)": [[307, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert.BF16Convert", false]], "bf16modulewrapper (class in neural_compressor.adaptor.torch_utils.bf16_convert)": [[134, "neural_compressor.adaptor.torch_utils.bf16_convert.BF16ModuleWrapper", false]], "biascorrection (class in neural_compressor.adaptor.tf_utils.transform_graph.bias_correction)": [[128, "neural_compressor.adaptor.tf_utils.transform_graph.bias_correction.BiasCorrection", false]], "biascorrection (class in neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction)": [[380, "neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction.BiasCorrection", false]], "bilinearimagenettransform (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.BilinearImagenetTransform", false]], "binarydirect8bitoperator (class in neural_compressor.adaptor.ox_utils.operators.binary_op)": [[8, "neural_compressor.adaptor.ox_utils.operators.binary_op.BinaryDirect8BitOperator", false]], "binaryoperator (class in neural_compressor.adaptor.ox_utils.operators.binary_op)": [[8, "neural_compressor.adaptor.ox_utils.operators.binary_op.BinaryOperator", false]], "bleu (class in neural_compressor.metric.bleu)": [[227, "neural_compressor.metric.bleu.BLEU", false]], "bleu_tokenize() (in module neural_compressor.metric.bleu)": [[227, "neural_compressor.metric.bleu.bleu_tokenize", false]], "block_size (neural_compressor.compression.pruner.patterns.nxm.keraspatternnxm attribute)": [[179, "neural_compressor.compression.pruner.patterns.nxm.KerasPatternNxM.block_size", false]], "block_size (neural_compressor.compression.pruner.patterns.nxm.pytorchpatternnxm attribute)": [[179, "neural_compressor.compression.pruner.patterns.nxm.PytorchPatternNxM.block_size", false]], "blockfallbacktuningsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.BlockFallbackTuningSampler", false]], "blockmaskcriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.BlockMaskCriterion", false]], "build_captured_dataloader() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.build_captured_dataloader", false]], "build_slave_faker_model() (in module neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.build_slave_faker_model", false]], "bypass_reshape() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.bypass_reshape", false]], "bypass_reshape() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.bypass_reshape", false]], "bypass_reshape() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.bypass_reshape", false]], "bypass_reshape() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.bypass_reshape", false]], "cal_scale() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.cal_scale", false]], "calculate_md5() (in module neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.calculate_md5", false]], "calculate_mse() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.calculate_mse", false]], "calculate_quant_min_max() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.calculate_quant_min_max", false]], "calculate_scale_zp() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.calculate_scale_zp", false]], "calib_model() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.calib_model", false]], "calib_registry() (in module neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.calib_registry", false]], "calibcollector (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.CalibCollector", false]], "calibdata (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.CalibData", false]], "calibration (class in neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.Calibration", false]], "calibration() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.calibration", false]], "calibratorbase (class in neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.CalibratorBase", false]], "call_counter() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.call_counter", false]], "call_one() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.call_one", false]], "callbacks (class in neural_compressor.training)": [[448, "neural_compressor.training.CallBacks", false]], "captureoutputtofile (class in neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.CaptureOutputToFile", false]], "captureoutputtofile (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.CaptureOutputToFile", false]], "cast_tensor() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.cast_tensor", false]], "castonnxtransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CastONNXTransform", false]], "castpytorchtransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CastPyTorchTransform", false]], "casttftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CastTFTransform", false]], "centercroptftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CenterCropTFTransform", false]], "centercroptransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CenterCropTransform", false]], "cfg_to_qconfig() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.cfg_to_qconfig", false]], "cfg_to_qconfig() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.cfg_to_qconfig", false]], "check_cfg_and_qconfig() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.check_cfg_and_qconfig", false]], "check_cfg_and_qconfig() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.check_cfg_and_qconfig", false]], "check_cfg_and_qconfig() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.check_cfg_and_qconfig", false]], "check_config() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.check_config", false]], "check_dataloader() (in module neural_compressor.data.dataloaders.dataloader)": [[201, "neural_compressor.data.dataloaders.dataloader.check_dataloader", false]], "check_integrity() (in module neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.check_integrity", false]], "check_key_exist() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.check_key_exist", false]], "check_key_validity() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.check_key_validity", false]], "check_model() (in module neural_compressor.utils.export.qlinear2qdq)": [[456, "neural_compressor.utils.export.qlinear2qdq.check_model", false]], "check_mx_version() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.check_mx_version", false]], "checkpoint_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.checkpoint_session", false]], "checkpoint_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.checkpoint_session", false]], "cifar10 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.CIFAR10", false]], "cifar100 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.CIFAR100", false]], "classifierheadsearcher (class in neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcher", false]], "classifierheadsearchertf (class in neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcherTF", false]], "classregister (class in neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.ClassRegister", false]], "clean_module_weight() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.clean_module_weight", false]], "cocoevalwrapper (class in neural_compressor.metric.coco_tools)": [[230, "neural_compressor.metric.coco_tools.COCOEvalWrapper", false]], "cocomapv2 (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.COCOmAPv2", false]], "coconpy (class in neural_compressor.data.datasets.coco_dataset)": [[210, "neural_compressor.data.datasets.coco_dataset.COCONpy", false]], "cocoraw (class in neural_compressor.data.datasets.coco_dataset)": [[210, "neural_compressor.data.datasets.coco_dataset.COCORaw", false]], "cocorecorddataset (class in neural_compressor.data.datasets.coco_dataset)": [[210, "neural_compressor.data.datasets.coco_dataset.COCORecordDataset", false]], "cocowrapper (class in neural_compressor.metric.coco_tools)": [[230, "neural_compressor.metric.coco_tools.COCOWrapper", false]], "collate_preds() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.collate_preds", false]], "collate_tf_preds() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.collate_tf_preds", false]], "collate_tf_preds() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.collate_tf_preds", false]], "collate_torch_preds() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.collate_torch_preds", false]], "collect_layer_inputs() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.collect_layer_inputs", false]], "collect_weight_info() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.collect_weight_info", false]], "collectorbase (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.CollectorBase", false]], "collecttransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CollectTransform", false]], "combine_capabilities() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.combine_capabilities", false]], "combine_histogram() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.combine_histogram", false]], "combine_histogram() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.combine_histogram", false]], "compare_label (neural_compressor.metric.metric.mae attribute)": [[234, "neural_compressor.metric.metric.MAE.compare_label", false]], "compare_label (neural_compressor.metric.metric.mse attribute)": [[234, "neural_compressor.metric.metric.MSE.compare_label", false]], "compare_objects() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.compare_objects", false]], "compare_weights() (in module neural_compressor.adaptor.torch_utils.hawq_metric)": [[135, "neural_compressor.adaptor.torch_utils.hawq_metric.compare_weights", false]], "composableconfig (class in neural_compressor.common.base_config)": [[152, "neural_compressor.common.base_config.ComposableConfig", false]], "composetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ComposeTransform", false]], "compressionmanager (class in neural_compressor.training)": [[448, "neural_compressor.training.CompressionManager", false]], "compute_bleu() (in module neural_compressor.metric.bleu_util)": [[228, "neural_compressor.metric.bleu_util.compute_bleu", false]], "compute_const_folding_using_tf() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.compute_const_folding_using_tf", false]], "compute_sparsity() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.compute_sparsity", false]], "concatoperator (class in neural_compressor.adaptor.ox_utils.operators.concat)": [[9, "neural_compressor.adaptor.ox_utils.operators.concat.ConcatOperator", false]], "config (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.config", false]], "config (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.config", false]], "config (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.config", false]], "config (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.config", false]], "config (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.config", false]], "config (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.config", false]], "config (neural_compressor.compression.pruner.schedulers.pruningscheduler attribute)": [[190, "neural_compressor.compression.pruner.schedulers.PruningScheduler.config", false]], "config_file_path (neural_compressor.compression.pruner.pruning.basepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasePruning.config_file_path", false]], "config_file_path (neural_compressor.compression.pruner.pruning.basicpruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasicPruning.config_file_path", false]], "config_file_path (neural_compressor.compression.pruner.pruning.retrainfreepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.RetrainFreePruning.config_file_path", false]], "config_instance() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.config_instance", false]], "config_list (neural_compressor.common.base_config.composableconfig attribute)": [[152, "neural_compressor.common.base_config.ComposableConfig.config_list", false]], "config_list (neural_compressor.common.base_tuning.configset attribute)": [[153, "neural_compressor.common.base_tuning.ConfigSet.config_list", false]], "config_quantizable_layers() (in module neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer)": [[103, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer.config_quantizable_layers", false]], "configloader (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.ConfigLoader", false]], "configregistry (class in neural_compressor.common.base_config)": [[152, "neural_compressor.common.base_config.ConfigRegistry", false]], "configset (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.ConfigSet", false]], "conservativetunestrategy (class in neural_compressor.strategy.conservative)": [[267, "neural_compressor.strategy.conservative.ConservativeTuneStrategy", false]], "construct_function_from_graph_def() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.construct_function_from_graph_def", false]], "construct_function_from_graph_def() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.construct_function_from_graph_def", false]], "convert() (in module neural_compressor.adaptor.torch_utils.bf16_convert)": [[134, "neural_compressor.adaptor.torch_utils.bf16_convert.Convert", false]], "convert() (in module neural_compressor.torch.quantization.quantize)": [[442, "neural_compressor.torch.quantization.quantize.convert", false]], "convert_by_vocab() (in module neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.convert_by_vocab", false]], "convert_examples_to_features() (in module neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.convert_examples_to_features", false]], "convert_examples_to_features() (in module neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.convert_examples_to_features", false]], "convert_tensorflow_tensor_to_onnx() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.convert_tensorflow_tensor_to_onnx", false]], "convert_to_unicode() (in module neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.convert_to_unicode", false]], "convertaddtobiasaddoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd)": [[38, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd.ConvertAddToBiasAddOptimizer", false]], "convertaddtobiasaddoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd)": [[310, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd.ConvertAddToBiasAddOptimizer", false]], "convertlayoutoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout)": [[39, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout.ConvertLayoutOptimizer", false]], "convertlayoutoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout)": [[311, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout.ConvertLayoutOptimizer", false]], "convertleakyreluoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu)": [[40, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu.ConvertLeakyReluOptimizer", false]], "convertleakyreluoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu)": [[312, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu.ConvertLeakyReluOptimizer", false]], "convertnantorandom (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random)": [[41, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random.ConvertNanToRandom", false]], "convertnantorandom (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random)": [[313, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random.ConvertNanToRandom", false]], "convertplaceholdertoconst (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const)": [[42, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const.ConvertPlaceholderToConst", false]], "convertplaceholdertoconst (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const)": [[314, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const.ConvertPlaceholderToConst", false]], "convoperator (class in neural_compressor.adaptor.ox_utils.operators.conv)": [[10, "neural_compressor.adaptor.ox_utils.operators.conv.ConvOperator", false]], "cpu_accelerator (class in neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.CPU_Accelerator", false]], "cpuinfo (class in neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.CpuInfo", false]], "cpuinfo (class in neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.CpuInfo", false]], "cpuinfo (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.CpuInfo", false]], "create_data_example() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.create_data_example", false]], "create_dataloader() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.create_dataloader", false]], "create_dataset() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.create_dataset", false]], "create_eval_func() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.create_eval_func", false]], "create_onnx_config() (in module neural_compressor.profiling.profiler.onnxrt_profiler.utils)": [[257, "neural_compressor.profiling.profiler.onnxrt_profiler.utils.create_onnx_config", false]], "create_quant_spec_from_config() (in module neural_compressor.torch.algorithms.pt2e_quant.utility)": [[409, "neural_compressor.torch.algorithms.pt2e_quant.utility.create_quant_spec_from_config", false]], "create_tf_config() (in module neural_compressor.profiling.profiler.tensorflow_profiler.utils)": [[261, "neural_compressor.profiling.profiler.tensorflow_profiler.utils.create_tf_config", false]], "create_train_func() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.create_train_func", false]], "create_xiq_quantizer_from_pt2e_config() (in module neural_compressor.torch.algorithms.pt2e_quant.utility)": [[409, "neural_compressor.torch.algorithms.pt2e_quant.utility.create_xiq_quantizer_from_pt2e_config", false]], "criterion (neural_compressor.compression.pruner.pruners.basic.kerasbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.KerasBasicPruner.criterion", false]], "criterion (neural_compressor.compression.pruner.pruners.basic.pytorchbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.PytorchBasicPruner.criterion", false]], "criterion (neural_compressor.compression.pruner.pruners.block_mask.pytorchblockmaskpruner attribute)": [[182, "neural_compressor.compression.pruner.pruners.block_mask.PytorchBlockMaskPruner.criterion", false]], "criterion (neural_compressor.compression.pruner.pruners.retrain_free.pytorchretrainfreepruner attribute)": [[187, "neural_compressor.compression.pruner.pruners.retrain_free.PytorchRetrainFreePruner.criterion", false]], "criterion_registry() (in module neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.criterion_registry", false]], "criterions (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.Criterions", false]], "cropresizetftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CropResizeTFTransform", false]], "cropresizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CropResizeTransform", false]], "croptoboundingbox (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.CropToBoundingBox", false]], "cuda_accelerator (class in neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.CUDA_Accelerator", false]], "current_pattern (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.current_pattern", false]], "current_sparsity_ratio (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.current_sparsity_ratio", false]], "current_sparsity_ratio (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.current_sparsity_ratio", false]], "current_sparsity_ratio (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.current_sparsity_ratio", false]], "dataiterloader (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.DataIterLoader", false]], "dataloader (class in neural_compressor.data.dataloaders.dataloader)": [[201, "neural_compressor.data.dataloaders.dataloader.DataLoader", false]], "dataloaderwrap (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.DataLoaderWrap", false]], "dataset (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.Dataset", false]], "dataset (neural_compressor.metric.coco_tools.cocowrapper attribute)": [[230, "neural_compressor.metric.coco_tools.COCOWrapper.dataset", false]], "dataset_registry() (in module neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.dataset_registry", false]], "datasets (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.Datasets", false]], "debug() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.debug", false]], "deep_get() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.deep_get", false]], "deep_get() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.deep_get", false]], "deep_set() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.deep_set", false]], "default_collate() (in module neural_compressor.data.dataloaders.default_dataloader)": [[202, "neural_compressor.data.dataloaders.default_dataloader.default_collate", false]], "default_collate() (in module neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.default_collate", false]], "defaultdataloader (class in neural_compressor.data.dataloaders.default_dataloader)": [[202, "neural_compressor.data.dataloaders.default_dataloader.DefaultDataLoader", false]], "delete_assign() (in module neural_compressor.profiling.profiler.tensorflow_profiler.utils)": [[261, "neural_compressor.profiling.profiler.tensorflow_profiler.utils.delete_assign", false]], "dequantize() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.Dequantize", false]], "dequantize_data() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.dequantize_data", false]], "dequantize_data_with_scale_zero() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.dequantize_data_with_scale_zero", false]], "dequantize_weight() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.dequantize_weight", false]], "dequantizecastoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer)": [[36, "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer.DequantizeCastOptimizer", false]], "dequantizecastoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer)": [[308, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer.DequantizeCastOptimizer", false]], "detect_processor_type_based_on_hw() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.detect_processor_type_based_on_hw", false]], "detection_type (neural_compressor.metric.coco_tools.cocowrapper attribute)": [[230, "neural_compressor.metric.coco_tools.COCOWrapper.detection_type", false]], "device (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcher.device", false]], "device (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearchertf attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcherTF.device", false]], "device (neural_compressor.compression.pruner.model_slim.pattern_analyzer.jitbasicsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher.device", false]], "device (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.device", false]], "device (neural_compressor.compression.pruner.model_slim.pattern_analyzer.selfmhasearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.SelfMHASearcher.device", false]], "device (neural_compressor.compression.pruner.model_slim.weight_slim.linearcompression attribute)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompression.device", false]], "device_synchronize() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.device_synchronize", false]], "dilatedcontraction (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction)": [[43, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction.DilatedContraction", false]], "dilatedcontraction (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction)": [[315, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction.DilatedContraction", false]], "direct8bitoperator (class in neural_compressor.adaptor.ox_utils.operators.direct_q8)": [[11, "neural_compressor.adaptor.ox_utils.operators.direct_q8.Direct8BitOperator", false]], "disable_random() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.disable_random", false]], "disable_random() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.disable_random", false]], "distillationcallbacks (class in neural_compressor.compression.callbacks)": [[162, "neural_compressor.compression.callbacks.DistillationCallbacks", false]], "distillationconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.DistillationConfig", false]], "distribute_calib_tensors() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.distribute_calib_tensors", false]], "dotdict (class in neural_compressor.config)": [[195, "neural_compressor.config.DotDict", false]], "dotdict (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.DotDict", false]], "dowload_hf_model() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.dowload_hf_model", false]], "dowload_hf_model() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.dowload_hf_model", false]], "dowload_hf_model() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.dowload_hf_model", false]], "download_url() (in module neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.download_url", false]], "dtype_to_name() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.dtype_to_name", false]], "dummydataset (class in neural_compressor.data.datasets.dummy_dataset)": [[212, "neural_compressor.data.datasets.dummy_dataset.DummyDataset", false]], "dummydataset (class in neural_compressor.data.datasets.dummy_dataset_v2)": [[213, "neural_compressor.data.datasets.dummy_dataset_v2.DummyDataset", false]], "dummydataset (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.DummyDataset", false]], "dummydatasetv2 (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.DummyDatasetV2", false]], "dump_class_attrs() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.dump_class_attrs", false]], "dump_data_to_local() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.dump_data_to_local", false]], "dump_elapsed_time() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.dump_elapsed_time", false]], "dump_elapsed_time() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.dump_elapsed_time", false]], "dump_elapsed_time() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.dump_elapsed_time", false]], "dump_model_op_stats() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.dump_model_op_stats", false]], "dump_model_op_stats() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.dump_model_op_stats", false]], "dump_model_op_stats() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.dump_model_op_stats", false]], "dump_numa_info() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.dump_numa_info", false]], "dump_table() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.dump_table", false]], "dump_table_to_csv() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.dump_table_to_csv", false]], "dynamic_quant_export() (in module neural_compressor.utils.export.torch2onnx)": [[458, "neural_compressor.utils.export.torch2onnx.dynamic_quant_export", false]], "dynamicquantconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.DynamicQuantConfig", false]], "elemformat (class in neural_compressor.torch.algorithms.mx_quant.utils)": [[404, "neural_compressor.torch.algorithms.mx_quant.utils.ElemFormat", false]], "embedlayernormalizationoperator (class in neural_compressor.adaptor.ox_utils.operators.embed_layernorm)": [[12, "neural_compressor.adaptor.ox_utils.operators.embed_layernorm.EmbedLayerNormalizationOperator", false]], "end_step (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.end_step", false]], "end_step (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.end_step", false]], "end_step (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.end_step", false]], "enough_memo_store_scale() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.enough_memo_store_scale", false]], "ensure_list() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.ensure_list", false]], "equal_dicts() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.equal_dicts", false]], "error() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.error", false]], "estimator_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.estimator_session", false]], "estimator_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.estimator_session", false]], "eval_frequency (neural_compressor.compression.callbacks.distillationcallbacks attribute)": [[162, "neural_compressor.compression.callbacks.DistillationCallbacks.eval_frequency", false]], "evaluate() (in module neural_compressor.metric.evaluate_squad)": [[231, "neural_compressor.metric.evaluate_squad.evaluate", false]], "evaluate() (in module neural_compressor.metric.f1)": [[232, "neural_compressor.metric.f1.evaluate", false]], "evaluationfuncwrapper (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.EvaluationFuncWrapper", false]], "evaluator (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.Evaluator", false]], "exact_match_score() (in module neural_compressor.metric.evaluate_squad)": [[231, "neural_compressor.metric.evaluate_squad.exact_match_score", false]], "exampleclass (class in neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.ExampleClass", false]], "exhaustivetunestrategy (class in neural_compressor.strategy.exhaustive)": [[268, "neural_compressor.strategy.exhaustive.ExhaustiveTuneStrategy", false]], "expanddimsoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer)": [[45, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer.ExpandDimsOptimizer", false]], "expanddimsoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer)": [[317, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer.ExpandDimsOptimizer", false]], "export() (in module neural_compressor.torch.export.pt2e_export)": [[435, "neural_compressor.torch.export.pt2e_export.export", false]], "export_compressed_model() (in module neural_compressor.utils.load_huggingface)": [[461, "neural_compressor.utils.load_huggingface.export_compressed_model", false]], "export_model_for_pt2e_quant() (in module neural_compressor.torch.export.pt2e_export)": [[435, "neural_compressor.torch.export.pt2e_export.export_model_for_pt2e_quant", false]], "exportconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.ExportConfig", false]], "exportsingleimagedetectionboxestococo() (in module neural_compressor.metric.coco_tools)": [[230, "neural_compressor.metric.coco_tools.ExportSingleImageDetectionBoxesToCoco", false]], "exportsingleimagedetectionmaskstococo() (in module neural_compressor.metric.coco_tools)": [[230, "neural_compressor.metric.coco_tools.ExportSingleImageDetectionMasksToCoco", false]], "exportsingleimagegroundtruthtococo() (in module neural_compressor.metric.coco_tools)": [[230, "neural_compressor.metric.coco_tools.ExportSingleImageGroundtruthToCoco", false]], "extract_data_type() (in module neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.extract_data_type", false]], "f1 (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.F1", false]], "f1_score() (in module neural_compressor.metric.evaluate_squad)": [[231, "neural_compressor.metric.evaluate_squad.f1_score", false]], "f1_score() (in module neural_compressor.metric.f1)": [[232, "neural_compressor.metric.f1.f1_score", false]], "fakeaffinetensorquantfunction (class in neural_compressor.adaptor.torch_utils.model_wrapper)": [[142, "neural_compressor.adaptor.torch_utils.model_wrapper.FakeAffineTensorQuantFunction", false]], "fakeaffinetensorquantfunction (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.FakeAffineTensorQuantFunction", false]], "fakequantize (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize)": [[98, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize.FakeQuantize", false]], "fakequantizebase (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize)": [[98, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize.FakeQuantizeBase", false]], "fallbacktuningsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.FallbackTuningSampler", false]], "fashionmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.FashionMNIST", false]], "fastbiascorrection (class in neural_compressor.algorithm.fast_bias_correction)": [[147, "neural_compressor.algorithm.fast_bias_correction.FastBiasCorrection", false]], "fatal() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.fatal", false]], "fault_tolerant_file() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.fault_tolerant_file", false]], "fetch_module() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.fetch_module", false]], "fetch_module() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.fetch_module", false]], "fetch_module() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.fetch_module", false]], "fetcher (class in neural_compressor.data.dataloaders.fetcher)": [[203, "neural_compressor.data.dataloaders.fetcher.Fetcher", false]], "fetchweightfromreshapeoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape)": [[46, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape.FetchWeightFromReshapeOptimizer", false]], "fetchweightfromreshapeoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape)": [[318, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape.FetchWeightFromReshapeOptimizer", false]], "filter (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.Filter", false]], "filter_fn() (in module neural_compressor.torch.algorithms.weight_only.hqq.quantizer)": [[427, "neural_compressor.torch.algorithms.weight_only.hqq.quantizer.filter_fn", false]], "filter_registry() (in module neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.filter_registry", false]], "filters (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.FILTERS", false]], "finalize_calibration() (in module neural_compressor.torch.quantization.quantize)": [[442, "neural_compressor.torch.quantization.quantize.finalize_calibration", false]], "find_by_name() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.find_by_name", false]], "find_layers() (in module neural_compressor.compression.pruner.wanda.utils)": [[194, "neural_compressor.compression.pruner.wanda.utils.find_layers", false]], "find_layers() (in module neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.find_layers", false]], "find_layers_name() (in module neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.find_layers_name", false]], "find_opset() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.find_opset", false]], "fit() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.fit", false]], "fit() (in module neural_compressor.mix_precision)": [[235, "neural_compressor.mix_precision.fit", false]], "fit() (in module neural_compressor.quantization)": [[262, "neural_compressor.quantization.fit", false]], "fit() (in module neural_compressor.training)": [[448, "neural_compressor.training.fit", false]], "fix_ref_type_of_graph_def() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.fix_ref_type_of_graph_def", false]], "fix_ref_type_of_graph_def() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.fix_ref_type_of_graph_def", false]], "flatten_static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcher.flatten_static_graph", false]], "flatten_static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearchertf attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcherTF.flatten_static_graph", false]], "flatten_static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.jitbasicsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher.flatten_static_graph", false]], "flatten_static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.flatten_static_graph", false]], "flatten_static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.selfmhasearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.SelfMHASearcher.flatten_static_graph", false]], "float16activationoperator (class in neural_compressor.adaptor.ox_utils.operators.activation)": [[5, "neural_compressor.adaptor.ox_utils.operators.activation.Float16ActivationOperator", false]], "float16binaryoperator (class in neural_compressor.adaptor.ox_utils.operators.binary_op)": [[8, "neural_compressor.adaptor.ox_utils.operators.binary_op.Float16BinaryOperator", false]], "float_to_bfloat16() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.float_to_bfloat16", false]], "float_to_float16() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.float_to_float16", false]], "fn (neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.patternpair attribute)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.PatternPair.fn", false]], "foldbatchnormnodesoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm)": [[47, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm.FoldBatchNormNodesOptimizer", false]], "foldbatchnormnodesoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm)": [[319, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm.FoldBatchNormNodesOptimizer", false]], "footprint (class in neural_compressor.objective)": [[245, "neural_compressor.objective.Footprint", false]], "format_list2str() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.format_list2str", false]], "forward_wrapper() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.forward_wrapper", false]], "forward_wrapper() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.forward_wrapper", false]], "forward_wrapper() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.forward_wrapper", false]], "fp8_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.fp8_entry", false]], "fp8config (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.FP8Config", false]], "framework_datasets (in module neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.framework_datasets", false]], "freezefakequantopoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant)": [[73, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant.FreezeFakeQuantOpOptimizer", false]], "freezefakequantopoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant)": [[345, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant.FreezeFakeQuantOpOptimizer", false]], "freezevaluetransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value)": [[74, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value.FreezeValueTransformer", false]], "freezevaluetransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value)": [[346, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value.FreezeValueTransformer", false]], "freezevaluewithoutcalibtransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib)": [[75, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib.FreezeValueWithoutCalibTransformer", false]], "frozen_pb_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.frozen_pb_session", false]], "frozen_pb_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.frozen_pb_session", false]], "fulltokenizer (class in neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.FullTokenizer", false]], "function1() (in module neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.function1", false]], "function2() (in module neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.function2", false]], "function3() (in module neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.function3", false]], "fuse() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.fuse", false]], "fusebiasaddandaddoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add)": [[49, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add.FuseBiasAddAndAddOptimizer", false]], "fusebiasaddandaddoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add)": [[321, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add.FuseBiasAddAndAddOptimizer", false]], "fusecolumnwisemuloptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul)": [[50, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul.FuseColumnWiseMulOptimizer", false]], "fusecolumnwisemuloptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul)": [[322, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul.FuseColumnWiseMulOptimizer", false]], "fuseconvredundantdequantizetransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize)": [[76, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize.FuseConvRedundantDequantizeTransformer", false]], "fuseconvredundantdequantizetransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize)": [[347, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize.FuseConvRedundantDequantizeTransformer", false]], "fuseconvrequantizetransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize)": [[77, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize.FuseConvRequantizeTransformer", false]], "fuseconvrequantizetransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize)": [[348, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize.FuseConvRequantizeTransformer", false]], "fuseconvwithmathoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math)": [[51, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math.FuseConvWithMathOptimizer", false]], "fuseconvwithmathoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math)": [[323, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math.FuseConvWithMathOptimizer", false]], "fusedecomposedbnoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.FuseDecomposedBNOptimizer", false]], "fusedecomposedbnoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.FuseDecomposedBNOptimizer", false]], "fusedecomposedinoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.FuseDecomposedINOptimizer", false]], "fusedecomposedinoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.FuseDecomposedINOptimizer", false]], "fusedmatmuloperator (class in neural_compressor.adaptor.ox_utils.operators.matmul)": [[18, "neural_compressor.adaptor.ox_utils.operators.matmul.FusedMatMulOperator", false]], "fusegeluoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu)": [[54, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu.FuseGeluOptimizer", false]], "fusegeluoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu)": [[326, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu.FuseGeluOptimizer", false]], "fuselayernormoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm)": [[55, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm.FuseLayerNormOptimizer", false]], "fuselayernormoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm)": [[327, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm.FuseLayerNormOptimizer", false]], "fusematmulredundantdequantizetransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize)": [[78, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize.FuseMatMulRedundantDequantizeTransformer", false]], "fusematmulredundantdequantizetransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize)": [[349, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize.FuseMatMulRedundantDequantizeTransformer", false]], "fusematmulrequantizedequantizenewapitransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize)": [[79, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeDequantizeNewAPITransformer", false]], "fusematmulrequantizedequantizenewapitransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize)": [[350, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeDequantizeNewAPITransformer", false]], "fusematmulrequantizedequantizetransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize)": [[79, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeDequantizeTransformer", false]], "fusematmulrequantizedequantizetransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize)": [[350, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeDequantizeTransformer", false]], "fusematmulrequantizenewapitransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize)": [[79, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeNewAPITransformer", false]], "fusematmulrequantizenewapitransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize)": [[350, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeNewAPITransformer", false]], "fusematmulrequantizetransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize)": [[79, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeTransformer", false]], "fusematmulrequantizetransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize)": [[350, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize.FuseMatMulRequantizeTransformer", false]], "fusenodestartwithconcatv2 (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2)": [[109, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2.FuseNodeStartWithConcatV2", false]], "fusenodestartwithconcatv2 (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2)": [[119, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2.FuseNodeStartWithConcatV2", false]], "fusenodestartwithconcatv2 (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2)": [[364, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2.FuseNodeStartWithConcatV2", false]], "fusenodestartwithconcatv2 (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2)": [[374, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2.FuseNodeStartWithConcatV2", false]], "fusenodestartwithconv2d (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv)": [[110, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv.FuseNodeStartWithConv2d", false]], "fusenodestartwithconv2d (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv)": [[120, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv.FuseNodeStartWithConv2d", false]], "fusenodestartwithconv2d (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv)": [[365, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv.FuseNodeStartWithConv2d", false]], "fusenodestartwithconv2d (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv)": [[375, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv.FuseNodeStartWithConv2d", false]], "fusenodestartwithdeconv2d (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv)": [[111, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv.FuseNodeStartWithDeconv2d", false]], "fusenodestartwithdeconv2d (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv)": [[366, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv.FuseNodeStartWithDeconv2d", false]], "fusenodestartwithfusedbatchnormv3 (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn)": [[108, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn.FuseNodeStartWithFusedBatchNormV3", false]], "fusenodestartwithfusedbatchnormv3 (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn)": [[118, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn.FuseNodeStartWithFusedBatchNormV3", false]], "fusenodestartwithfusedbatchnormv3 (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn)": [[363, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn.FuseNodeStartWithFusedBatchNormV3", false]], "fusenodestartwithfusedbatchnormv3 (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn)": [[373, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn.FuseNodeStartWithFusedBatchNormV3", false]], "fusenodestartwithfusedinstancenorm (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in)": [[112, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in.FuseNodeStartWithFusedInstanceNorm", false]], "fusenodestartwithfusedinstancenorm (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in)": [[367, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in.FuseNodeStartWithFusedInstanceNorm", false]], "fusenodestartwithmatmul (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul)": [[113, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul.FuseNodeStartWithMatmul", false]], "fusenodestartwithmatmul (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul)": [[122, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul.FuseNodeStartWithMatmul", false]], "fusenodestartwithmatmul (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul)": [[368, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul.FuseNodeStartWithMatmul", false]], "fusenodestartwithmatmul (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul)": [[377, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul.FuseNodeStartWithMatmul", false]], "fusenodestartwithpooling (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling)": [[114, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling.FuseNodeStartWithPooling", false]], "fusenodestartwithpooling (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling)": [[123, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling.FuseNodeStartWithPooling", false]], "fusenodestartwithpooling (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling)": [[369, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling.FuseNodeStartWithPooling", false]], "fusenodestartwithpooling (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling)": [[378, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling.FuseNodeStartWithPooling", false]], "fusepadwithconv2doptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv)": [[56, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv.FusePadWithConv2DOptimizer", false]], "fusepadwithconv2doptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv)": [[328, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv.FusePadWithConv2DOptimizer", false]], "fusepadwithfp32conv2doptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv)": [[57, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv.FusePadWithFP32Conv2DOptimizer", false]], "fusepadwithfp32conv2doptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv)": [[329, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv.FusePadWithFP32Conv2DOptimizer", false]], "fusetransposereshapeoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose)": [[58, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose.FuseTransposeReshapeOptimizer", false]], "fusetransposereshapeoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose)": [[330, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose.FuseTransposeReshapeOptimizer", false]], "gatheroperator (class in neural_compressor.adaptor.ox_utils.operators.gather)": [[13, "neural_compressor.adaptor.ox_utils.operators.gather.GatherOperator", false]], "gemmoperator (class in neural_compressor.adaptor.ox_utils.operators.gemm)": [[15, "neural_compressor.adaptor.ox_utils.operators.gemm.GemmOperator", false]], "gen_bar_updater() (in module neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.gen_bar_updater", false]], "generaltopk (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.GeneralTopK", false]], "generate_activation_observer() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.generate_activation_observer", false]], "generate_activation_observer() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.generate_activation_observer", false]], "generate_feed_dict() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.generate_feed_dict", false]], "generate_feed_dict() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.generate_feed_dict", false]], "generate_ffn2_pruning_config() (in module neural_compressor.compression.pruner.model_slim.auto_slim)": [[171, "neural_compressor.compression.pruner.model_slim.auto_slim.generate_ffn2_pruning_config", false]], "generate_mha_pruning_config() (in module neural_compressor.compression.pruner.model_slim.auto_slim)": [[171, "neural_compressor.compression.pruner.model_slim.auto_slim.generate_mha_pruning_config", false]], "generate_prefix() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.generate_prefix", false]], "generate_prefix() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.generate_prefix", false]], "generate_xpu_qconfig() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.generate_xpu_qconfig", false]], "generategraphwithqdqpattern (class in neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern)": [[92, "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern.GenerateGraphWithQDQPattern", false]], "generategraphwithqdqpattern (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern)": [[357, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern.GenerateGraphWithQDQPattern", false]], "generator1() (in module neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.generator1", false]], "get_absorb_layers() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_absorb_layers", false]], "get_absorb_layers() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.get_absorb_layers", false]], "get_accelerator() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.get_accelerator", false]], "get_activation() (in module neural_compressor.compression.distillation.utility)": [[166, "neural_compressor.compression.distillation.utility.get_activation", false]], "get_adaptor_name() (in module neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.get_adaptor_name", false]], "get_algorithm() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.get_algorithm", false]], "get_all_config_set() (in module neural_compressor.tensorflow.quantization.autotune)": [[302, "neural_compressor.tensorflow.quantization.autotune.get_all_config_set", false]], "get_all_config_set() (in module neural_compressor.torch.quantization.autotune)": [[438, "neural_compressor.torch.quantization.autotune.get_all_config_set", false]], "get_all_config_set_from_config_registry() (in module neural_compressor.common.base_config)": [[152, "neural_compressor.common.base_config.get_all_config_set_from_config_registry", false]], "get_all_fp32_data() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.get_all_fp32_data", false]], "get_all_fp32_data() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_all_fp32_data", false]], "get_all_registered_configs() (in module neural_compressor.tensorflow.keras.quantization.config)": [[299, "neural_compressor.tensorflow.keras.quantization.config.get_all_registered_configs", false]], "get_all_registered_configs() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_all_registered_configs", false]], "get_architecture() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.get_architecture", false]], "get_attributes() (in module neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.get_attributes", false]], "get_blob_size() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.get_blob_size", false]], "get_block_prefix() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_block_prefix", false]], "get_block_prefix() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.get_block_prefix", false]], "get_bounded_threads() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.get_bounded_threads", false]], "get_children() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.get_children", false]], "get_children() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.get_children", false]], "get_common_module() (in module neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.get_common_module", false]], "get_const_dim_count() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.get_const_dim_count", false]], "get_const_dim_count() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.get_const_dim_count", false]], "get_const_dim_count() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.get_const_dim_count", false]], "get_const_dim_count() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.get_const_dim_count", false]], "get_core_ids() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.get_core_ids", false]], "get_criterion() (in module neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.get_criterion", false]], "get_dataloader() (in module neural_compressor.torch.algorithms.weight_only.autoround)": [[418, "neural_compressor.torch.algorithms.weight_only.autoround.get_dataloader", false]], "get_default_autoround_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_AutoRound_config", false]], "get_default_awq_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_awq_config", false]], "get_default_double_quant_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_double_quant_config", false]], "get_default_dynamic_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_dynamic_config", false]], "get_default_fp8_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_fp8_config", false]], "get_default_fp8_config_set() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_fp8_config_set", false]], "get_default_gptq_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_gptq_config", false]], "get_default_hqq_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_hqq_config", false]], "get_default_mixed_precision_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_mixed_precision_config", false]], "get_default_mixed_precision_config_set() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_mixed_precision_config_set", false]], "get_default_mx_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_mx_config", false]], "get_default_rtn_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_rtn_config", false]], "get_default_sq_config() (in module neural_compressor.tensorflow.quantization.config)": [[303, "neural_compressor.tensorflow.quantization.config.get_default_sq_config", false]], "get_default_sq_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_sq_config", false]], "get_default_static_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_static_config", false]], "get_default_static_quant_config() (in module neural_compressor.tensorflow.keras.quantization.config)": [[299, "neural_compressor.tensorflow.keras.quantization.config.get_default_static_quant_config", false]], "get_default_static_quant_config() (in module neural_compressor.tensorflow.quantization.config)": [[303, "neural_compressor.tensorflow.quantization.config.get_default_static_quant_config", false]], "get_default_teq_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_default_teq_config", false]], "get_depth() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_depth", false]], "get_depth() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.get_depth", false]], "get_dict_at_depth() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_dict_at_depth", false]], "get_dict_at_depth() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.get_dict_at_depth", false]], "get_double_quant_config_dict() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.get_double_quant_config_dict", false]], "get_element_under_depth() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_element_under_depth", false]], "get_element_under_depth() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.get_element_under_depth", false]], "get_embedding_contiguous() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_embedding_contiguous", false]], "get_estimator_graph() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_estimator_graph", false]], "get_example_input() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_example_input", false]], "get_fallback_order() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_fallback_order", false]], "get_filter_fn() (in module neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.get_filter_fn", false]], "get_final_text() (in module neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.get_final_text", false]], "get_framework_name() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.get_framework_name", false]], "get_func_from_config() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.get_func_from_config", false]], "get_graph_def() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_graph_def", false]], "get_graph_def() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.get_graph_def", false]], "get_half_precision_node_set() (in module neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.get_half_precision_node_set", false]], "get_hidden_states() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_hidden_states", false]], "get_index_from_strided_slice_of_shape() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.get_index_from_strided_slice_of_shape", false]], "get_input_output_node_names() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_input_output_node_names", false]], "get_input_output_node_names() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.get_input_output_node_names", false]], "get_ipex_version() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.get_ipex_version", false]], "get_layers() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.get_layers", false]], "get_linux_numa_info() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.get_linux_numa_info", false]], "get_max_supported_opset_version() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema)": [[89, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema.get_max_supported_opset_version", false]], "get_metrics() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.get_metrics", false]], "get_model_device() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.get_model_device", false]], "get_model_fwk_name() (in module neural_compressor.model.model)": [[239, "neural_compressor.model.model.get_model_fwk_name", false]], "get_model_info() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.get_model_info", false]], "get_model_input_shape() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_model_input_shape", false]], "get_model_input_shape() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.get_model_input_shape", false]], "get_model_type() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.get_model_type", false]], "get_model_type() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.get_model_type", false]], "get_module() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.get_module", false]], "get_module() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.get_module", false]], "get_module() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.get_module", false]], "get_module() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.get_module", false]], "get_module_input_output() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_module_input_output", false]], "get_module_input_output() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.get_module_input_output", false]], "get_mse_order_per_fp32() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_mse_order_per_fp32", false]], "get_mse_order_per_int8() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_mse_order_per_int8", false]], "get_named_children() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.get_named_children", false]], "get_named_children() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.get_named_children", false]], "get_node_mapping() (in module neural_compressor.utils.export.torch2onnx)": [[458, "neural_compressor.utils.export.torch2onnx.get_node_mapping", false]], "get_node_original_name() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.get_node_original_name", false]], "get_numa_node() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.get_numa_node", false]], "get_number_of_sockets() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_number_of_sockets", false]], "get_op_list() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_op_list", false]], "get_op_type_by_name() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_op_type_by_name", false]], "get_parent() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.get_parent", false]], "get_parent() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.get_parent", false]], "get_pattern() (in module neural_compressor.compression.pruner.patterns)": [[176, "neural_compressor.compression.pruner.patterns.get_pattern", false]], "get_physical_ids() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.get_physical_ids", false]], "get_postprocess() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.get_postprocess", false]], "get_preprocess() (in module neural_compressor.utils.create_obj_from_config)": [[454, "neural_compressor.utils.create_obj_from_config.get_preprocess", false]], "get_processor_type_from_user_config() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.get_processor_type_from_user_config", false]], "get_pruner() (in module neural_compressor.compression.pruner.pruners)": [[183, "neural_compressor.compression.pruner.pruners.get_pruner", false]], "get_quant_dequant_output() (in module neural_compressor.adaptor.ox_utils.smooth_quant)": [[29, "neural_compressor.adaptor.ox_utils.smooth_quant.get_quant_dequant_output", false]], "get_quantizable_onnx_ops() (in module neural_compressor.utils.export.torch2onnx)": [[458, "neural_compressor.utils.export.torch2onnx.get_quantizable_onnx_ops", false]], "get_quantizable_ops_from_cfgs() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_quantizable_ops_from_cfgs", false]], "get_quantizable_ops_from_cfgs() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.get_quantizable_ops_from_cfgs", false]], "get_quantizable_ops_recursively() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.get_quantizable_ops_recursively", false]], "get_quantizable_ops_recursively() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.get_quantizable_ops_recursively", false]], "get_quantizer() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.get_quantizer", false]], "get_reg() (in module neural_compressor.compression.pruner.regs)": [[189, "neural_compressor.compression.pruner.regs.get_reg", false]], "get_reg_type() (in module neural_compressor.compression.pruner.regs)": [[189, "neural_compressor.compression.pruner.regs.get_reg_type", false]], "get_reversed_numa_info() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.get_reversed_numa_info", false]], "get_rtn_double_quant_config_set() (in module neural_compressor.torch.quantization.autotune)": [[438, "neural_compressor.torch.quantization.autotune.get_rtn_double_quant_config_set", false]], "get_scheduler() (in module neural_compressor.compression.pruner.schedulers)": [[190, "neural_compressor.compression.pruner.schedulers.get_scheduler", false]], "get_schema() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema)": [[89, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema.get_schema", false]], "get_size() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_size", false]], "get_sparsity_ratio() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.get_sparsity_ratio", false]], "get_sparsity_ratio_tf() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.get_sparsity_ratio_tf", false]], "get_subgraphs_from_onnx() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.get_subgraphs_from_onnx", false]], "get_super_module_by_name() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.get_super_module_by_name", false]], "get_super_module_by_name() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.get_super_module_by_name", false]], "get_tensor_by_name() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_tensor_by_name", false]], "get_tensor_by_name() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.get_tensor_by_name", false]], "get_tensor_histogram() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.get_tensor_histogram", false]], "get_tensor_histogram() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_tensor_histogram", false]], "get_tensor_val_from_graph_node() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_tensor_val_from_graph_node", false]], "get_tensorflow_node_attr() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.get_tensorflow_node_attr", false]], "get_tensorflow_node_shape_attr() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.get_tensorflow_node_shape_attr", false]], "get_tensorflow_tensor_data() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.get_tensorflow_tensor_data", false]], "get_tensorflow_tensor_shape() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.get_tensorflow_tensor_shape", false]], "get_tensors_info() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_tensors_info", false]], "get_tf_criterion() (in module neural_compressor.compression.pruner.tf_criteria)": [[191, "neural_compressor.compression.pruner.tf_criteria.get_tf_criterion", false]], "get_tf_model_type() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.get_tf_model_type", false]], "get_threads() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.get_threads", false]], "get_threads_per_core() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.get_threads_per_core", false]], "get_torch_version() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.get_torch_version", false]], "get_torch_version() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.get_torch_version", false]], "get_torchvision_map() (in module neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.get_torchvision_map", false]], "get_tuning_history() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_tuning_history", false]], "get_unquantized_node_set() (in module neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.get_unquantized_node_set", false]], "get_weight_from_input_tensor() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.get_weight_from_input_tensor", false]], "get_weight_scale() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.get_weight_scale", false]], "get_weights_details() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.get_weights_details", false]], "get_windows_numa_info() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.get_windows_numa_info", false]], "get_woq_tuning_config() (in module neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.get_woq_tuning_config", false]], "get_workspace() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.get_workspace", false]], "global_state (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.GLOBAL_STATE", false]], "global_step (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.global_step", false]], "global_step (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.global_step", false]], "global_step (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.global_step", false]], "globalaveragepooloperator (class in neural_compressor.adaptor.ox_utils.operators.gavgpool)": [[14, "neural_compressor.adaptor.ox_utils.operators.gavgpool.GlobalAveragePoolOperator", false]], "gptq (class in neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.GPTQ", false]], "gptq() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.gptq", false]], "gptq_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.gptq_entry", false]], "gptq_quantize() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.gptq_quantize", false]], "gptqconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.GPTQConfig", false]], "gptqconfig (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.GPTQConfig", false]], "gptquantizer (class in neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.GPTQuantizer", false]], "gradientcriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.GradientCriterion", false]], "graph_def_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.graph_def_session", false]], "graph_def_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.graph_def_session", false]], "graph_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.graph_session", false]], "graph_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.graph_session", false]], "graphanalyzer (class in neural_compressor.adaptor.tf_utils.graph_util)": [[95, "neural_compressor.adaptor.tf_utils.graph_util.GraphAnalyzer", false]], "graphanalyzer (class in neural_compressor.tensorflow.quantization.utils.graph_util)": [[360, "neural_compressor.tensorflow.quantization.utils.graph_util.GraphAnalyzer", false]], "graphconverter (class in neural_compressor.adaptor.tf_utils.graph_converter)": [[33, "neural_compressor.adaptor.tf_utils.graph_converter.GraphConverter", false]], "graphconverter (class in neural_compressor.tensorflow.quantization.utils.graph_converter)": [[306, "neural_compressor.tensorflow.quantization.utils.graph_converter.GraphConverter", false]], "graphconverterwithoutcalib (class in neural_compressor.adaptor.tf_utils.graph_converter_without_calib)": [[34, "neural_compressor.adaptor.tf_utils.graph_converter_without_calib.GraphConverterWithoutCalib", false]], "graphcseoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer)": [[59, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer.GraphCseOptimizer", false]], "graphcseoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer)": [[331, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer.GraphCseOptimizer", false]], "graphfoldconstantoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant)": [[48, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant.GraphFoldConstantOptimizer", false]], "graphfoldconstantoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant)": [[320, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant.GraphFoldConstantOptimizer", false]], "graphrewriterbase (class in neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base)": [[71, "neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base.GraphRewriterBase", false]], "graphrewriterbase (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base)": [[343, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base.GraphRewriterBase", false]], "graphrewriterhelper (class in neural_compressor.adaptor.tf_utils.graph_util)": [[95, "neural_compressor.adaptor.tf_utils.graph_util.GraphRewriterHelper", false]], "graphrewriterhelper (class in neural_compressor.tensorflow.quantization.utils.graph_util)": [[360, "neural_compressor.tensorflow.quantization.utils.graph_util.GraphRewriterHelper", false]], "graphtrace (class in neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.GraphTrace", false]], "graphtrace (class in neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.GraphTrace", false]], "graphtransformbase (class in neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base)": [[129, "neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base.GraphTransformBase", false]], "graphtransformbase (class in neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base)": [[381, "neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base.GraphTransformBase", false]], "grappleroptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass)": [[60, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass.GrapplerOptimizer", false]], "grappleroptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass)": [[332, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass.GrapplerOptimizer", false]], "group_size (neural_compressor.torch.algorithms.weight_only.hqq.qtensor.qtensormetainfo attribute)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo.group_size", false]], "grouplasso (class in neural_compressor.compression.pruner.regs)": [[189, "neural_compressor.compression.pruner.regs.GroupLasso", false]], "halfprecisionconverter (class in neural_compressor.torch.algorithms.mixed_precision.half_precision_convert)": [[399, "neural_compressor.torch.algorithms.mixed_precision.half_precision_convert.HalfPrecisionConverter", false]], "halfprecisionmodulewrapper (class in neural_compressor.torch.algorithms.mixed_precision.module_wrappers)": [[401, "neural_compressor.torch.algorithms.mixed_precision.module_wrappers.HalfPrecisionModuleWrapper", false]], "hawq_top() (in module neural_compressor.adaptor.torch_utils.hawq_metric)": [[135, "neural_compressor.adaptor.torch_utils.hawq_metric.hawq_top", false]], "hawq_v2tunestrategy (class in neural_compressor.strategy.hawq_v2)": [[269, "neural_compressor.strategy.hawq_v2.HAWQ_V2TuneStrategy", false]], "head_masks (neural_compressor.compression.pruner.pruners.mha.pythonmultiheadattentionpruner attribute)": [[184, "neural_compressor.compression.pruner.pruners.mha.PythonMultiheadAttentionPruner.head_masks", false]], "hessiantrace (class in neural_compressor.adaptor.torch_utils.hawq_metric)": [[135, "neural_compressor.adaptor.torch_utils.hawq_metric.HessianTrace", false]], "histogramcollector (class in neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.HistogramCollector", false]], "hpoconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.HPOConfig", false]], "hpu_accelerator (class in neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.HPU_Accelerator", false]], "hpuweightonlylinear (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.HPUWeightOnlyLinear", false]], "hqq_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.hqq_entry", false]], "hqqconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.HQQConfig", false]], "hqqlinear (class in neural_compressor.torch.algorithms.weight_only.hqq.core)": [[423, "neural_compressor.torch.algorithms.weight_only.hqq.core.HQQLinear", false]], "hqqmoduleconfig (class in neural_compressor.torch.algorithms.weight_only.hqq.config)": [[422, "neural_compressor.torch.algorithms.weight_only.hqq.config.HQQModuleConfig", false]], "hqqtensorhandle (class in neural_compressor.torch.algorithms.weight_only.hqq.core)": [[423, "neural_compressor.torch.algorithms.weight_only.hqq.core.HQQTensorHandle", false]], "hqquantizer (class in neural_compressor.torch.algorithms.weight_only.hqq.quantizer)": [[427, "neural_compressor.torch.algorithms.weight_only.hqq.quantizer.HQQuantizer", false]], "imagefolder (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.ImageFolder", false]], "imagenetraw (class in neural_compressor.data.datasets.imagenet_dataset)": [[214, "neural_compressor.data.datasets.imagenet_dataset.ImagenetRaw", false]], "incquantizationconfigmixin (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.INCQuantizationConfigMixin", false]], "incweightonlylinear (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.INCWeightOnlyLinear", false]], "indexfetcher (class in neural_compressor.data.dataloaders.fetcher)": [[203, "neural_compressor.data.dataloaders.fetcher.IndexFetcher", false]], "indexfetcher (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.IndexFetcher", false]], "infer_onnx_shape_dtype() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.infer_onnx_shape_dtype", false]], "infer_shapes() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.infer_shapes", false]], "info() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.info", false]], "init_quantize_config() (in module neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper)": [[101, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper.init_quantize_config", false]], "init_tuning() (in module neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.init_tuning", false]], "initial_tuning_cfg_with_quant_mode() (in module neural_compressor.strategy.utils.tuning_space)": [[278, "neural_compressor.strategy.utils.tuning_space.initial_tuning_cfg_with_quant_mode", false]], "initialize_int8_avgpool() (in module neural_compressor.tensorflow.keras.layers.pool2d)": [[297, "neural_compressor.tensorflow.keras.layers.pool2d.initialize_int8_avgpool", false]], "initialize_int8_conv2d() (in module neural_compressor.tensorflow.keras.layers.conv2d)": [[292, "neural_compressor.tensorflow.keras.layers.conv2d.initialize_int8_conv2d", false]], "initialize_int8_dense() (in module neural_compressor.tensorflow.keras.layers.dense)": [[293, "neural_compressor.tensorflow.keras.layers.dense.initialize_int8_dense", false]], "initialize_int8_depthwise_conv2d() (in module neural_compressor.tensorflow.keras.layers.depthwise_conv2d)": [[294, "neural_compressor.tensorflow.keras.layers.depthwise_conv2d.initialize_int8_depthwise_conv2d", false]], "initialize_int8_maxpool() (in module neural_compressor.tensorflow.keras.layers.pool2d)": [[297, "neural_compressor.tensorflow.keras.layers.pool2d.initialize_int8_maxpool", false]], "initialize_int8_separable_conv2d() (in module neural_compressor.tensorflow.keras.layers.separable_conv2d)": [[298, "neural_compressor.tensorflow.keras.layers.separable_conv2d.initialize_int8_separable_conv2d", false]], "initialize_name_counter() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.initialize_name_counter", false]], "injectdummybiasaddoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd)": [[44, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd.InjectDummyBiasAddOptimizer", false]], "injectdummybiasaddoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd)": [[316, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd.InjectDummyBiasAddOptimizer", false]], "input2tuple() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.input2tuple", false]], "inputfeatures (class in neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.InputFeatures", false]], "inputfeatures (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.InputFeatures", false]], "insertlogging (class in neural_compressor.adaptor.tf_utils.transform_graph.insert_logging)": [[131, "neural_compressor.adaptor.tf_utils.transform_graph.insert_logging.InsertLogging", false]], "insertlogging (class in neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging)": [[383, "neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging.InsertLogging", false]], "insertprintminmaxnode (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node)": [[62, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node.InsertPrintMinMaxNode", false]], "insertprintminmaxnode (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node)": [[334, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node.InsertPrintMinMaxNode", false]], "int8_node_name_reverse() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.int8_node_name_reverse", false]], "intermediatelayersknowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.IntermediateLayersKnowledgeDistillationLoss", false]], "intermediatelayersknowledgedistillationlossconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.IntermediateLayersKnowledgeDistillationLossConfig", false]], "invalid_layers (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.invalid_layers", false]], "invalid_layers (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.invalid_layers", false]], "invalid_layers (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.invalid_layers", false]], "ipexmodel (class in neural_compressor.model.torch_model)": [[244, "neural_compressor.model.torch_model.IPEXModel", false]], "is_b_transposed() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.is_B_transposed", false]], "is_ckpt_format() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.is_ckpt_format", false]], "is_ckpt_format() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.is_ckpt_format", false]], "is_fused_module() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.is_fused_module", false]], "is_global (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.is_global", false]], "is_global (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.is_global", false]], "is_global (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.is_global", false]], "is_hpex_available() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.is_hpex_available", false]], "is_int8_model() (in module neural_compressor.utils.pytorch)": [[464, "neural_compressor.utils.pytorch.is_int8_model", false]], "is_ipex_available() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.is_ipex_available", false]], "is_ipex_imported() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.is_ipex_imported", false]], "is_leaf() (in module neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.is_leaf", false]], "is_list_or_tuple() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.is_list_or_tuple", false]], "is_model_quantized() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.is_model_quantized", false]], "is_onnx_domain() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.is_onnx_domain", false]], "is_package_available() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.is_package_available", false]], "is_saved_model_format() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.is_saved_model_format", false]], "is_saved_model_format() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.is_saved_model_format", false]], "is_transformers_imported() (in module neural_compressor.torch.utils.environ)": [[445, "neural_compressor.torch.utils.environ.is_transformers_imported", false]], "isiterable() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.isiterable", false]], "iterabledataset (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.IterableDataset", false]], "iterablefetcher (class in neural_compressor.data.dataloaders.fetcher)": [[203, "neural_compressor.data.dataloaders.fetcher.IterableFetcher", false]], "iterablefetcher (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.IterableFetcher", false]], "iterablesampler (class in neural_compressor.data.dataloaders.sampler)": [[207, "neural_compressor.data.dataloaders.sampler.IterableSampler", false]], "iterablesampler (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.IterableSampler", false]], "iterativescheduler (class in neural_compressor.compression.pruner.schedulers)": [[190, "neural_compressor.compression.pruner.schedulers.IterativeScheduler", false]], "iterator_sess_run() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.iterator_sess_run", false]], "iterator_sess_run() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.iterator_sess_run", false]], "itex_installed() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.itex_installed", false]], "jitbasicsearcher (class in neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher", false]], "k (neural_compressor.metric.metric.generaltopk attribute)": [[234, "neural_compressor.metric.metric.GeneralTopK.k", false]], "k (neural_compressor.metric.metric.tensorflowtopk attribute)": [[234, "neural_compressor.metric.metric.TensorflowTopK.k", false]], "keep_mask_layers (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.keep_mask_layers", false]], "keep_mask_layers (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.keep_mask_layers", false]], "keep_mask_layers (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.keep_mask_layers", false]], "keras (class in neural_compressor.config)": [[195, "neural_compressor.config.Keras", false]], "keras_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.keras_session", false]], "keras_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.keras_session", false]], "kerasadaptor (class in neural_compressor.tensorflow.algorithms.static_quant.keras)": [[288, "neural_compressor.tensorflow.algorithms.static_quant.keras.KerasAdaptor", false]], "kerasbasepattern (class in neural_compressor.compression.pruner.patterns.base)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern", false]], "kerasbasepruner (class in neural_compressor.compression.pruner.pruners.base)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner", false]], "kerasbasicpruner (class in neural_compressor.compression.pruner.pruners.basic)": [[181, "neural_compressor.compression.pruner.pruners.basic.KerasBasicPruner", false]], "kerasconfigconverter (class in neural_compressor.tensorflow.algorithms.static_quant.keras)": [[288, "neural_compressor.tensorflow.algorithms.static_quant.keras.KerasConfigConverter", false]], "kerasmodel (class in neural_compressor.model.keras_model)": [[238, "neural_compressor.model.keras_model.KerasModel", false]], "kerasmodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.KerasModel", false]], "keraspatternnxm (class in neural_compressor.compression.pruner.patterns.nxm)": [[179, "neural_compressor.compression.pruner.patterns.nxm.KerasPatternNxM", false]], "kerasquery (class in neural_compressor.tensorflow.algorithms.static_quant.keras)": [[288, "neural_compressor.tensorflow.algorithms.static_quant.keras.KerasQuery", false]], "kerassurgery (class in neural_compressor.tensorflow.algorithms.static_quant.keras)": [[288, "neural_compressor.tensorflow.algorithms.static_quant.keras.KerasSurgery", false]], "kl_divergence (class in neural_compressor.utils.kl_divergence)": [[460, "neural_compressor.utils.kl_divergence.KL_Divergence", false]], "klcalibrator (class in neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.KLCalibrator", false]], "knowledgedistillationframework (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.KnowledgeDistillationFramework", false]], "knowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.KnowledgeDistillationLoss", false]], "knowledgedistillationlossconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.KnowledgeDistillationLossConfig", false]], "label_list (neural_compressor.metric.metric.accuracy attribute)": [[234, "neural_compressor.metric.metric.Accuracy.label_list", false]], "label_list (neural_compressor.metric.metric.mae attribute)": [[234, "neural_compressor.metric.metric.MAE.label_list", false]], "label_list (neural_compressor.metric.metric.mse attribute)": [[234, "neural_compressor.metric.metric.MSE.label_list", false]], "labelbalancecocorawfilter (class in neural_compressor.data.filters.coco_filter)": [[217, "neural_compressor.data.filters.coco_filter.LabelBalanceCOCORawFilter", false]], "labelbalancecocorecordfilter (class in neural_compressor.data.filters.coco_filter)": [[217, "neural_compressor.data.filters.coco_filter.LabelBalanceCOCORecordFilter", false]], "labels (neural_compressor.metric.bleu.bleu attribute)": [[227, "neural_compressor.metric.bleu.BLEU.labels", false]], "labelshift (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.LabelShift", false]], "layer_1 (neural_compressor.compression.pruner.model_slim.weight_slim.linearcompression attribute)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompression.layer_1", false]], "layer_2 (neural_compressor.compression.pruner.model_slim.weight_slim.linearcompression attribute)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompression.layer_2", false]], "layerhistogramcollector (class in neural_compressor.utils.collect_layer_histogram)": [[452, "neural_compressor.utils.collect_layer_histogram.LayerHistogramCollector", false]], "layerwisequant (class in neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize)": [[139, "neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize.LayerWiseQuant", false]], "lazyimport (class in neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.LazyImport", false]], "lazyimport (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.LazyImport", false]], "linear2linearsearcher (class in neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher", false]], "linear_layers (neural_compressor.compression.pruner.pruners.mha.pythonmultiheadattentionpruner attribute)": [[184, "neural_compressor.compression.pruner.pruners.mha.PythonMultiheadAttentionPruner.linear_layers", false]], "linear_patterns (neural_compressor.compression.pruner.model_slim.weight_slim.linearcompressioniterator attribute)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompressionIterator.linear_patterns", false]], "linearcompression (class in neural_compressor.compression.pruner.model_slim.weight_slim)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompression", false]], "linearcompressioniterator (class in neural_compressor.compression.pruner.model_slim.weight_slim)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompressionIterator", false]], "load() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load)": [[140, "neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load.load", false]], "load() (in module neural_compressor.torch.algorithms.layer_wise.load)": [[396, "neural_compressor.torch.algorithms.layer_wise.load.load", false]], "load() (in module neural_compressor.torch.algorithms.pt2e_quant.save_load)": [[408, "neural_compressor.torch.algorithms.pt2e_quant.save_load.load", false]], "load() (in module neural_compressor.torch.algorithms.static_quant.save_load)": [[415, "neural_compressor.torch.algorithms.static_quant.save_load.load", false]], "load() (in module neural_compressor.torch.algorithms.weight_only.save_load)": [[431, "neural_compressor.torch.algorithms.weight_only.save_load.load", false]], "load() (in module neural_compressor.torch.quantization.load_entry)": [[441, "neural_compressor.torch.quantization.load_entry.load", false]], "load() (in module neural_compressor.utils.pytorch)": [[464, "neural_compressor.utils.pytorch.load", false]], "load_and_cache_examples() (in module neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.load_and_cache_examples", false]], "load_config_mapping() (in module neural_compressor.common.utils.save_load)": [[160, "neural_compressor.common.utils.save_load.load_config_mapping", false]], "load_data_from_pkl() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.load_data_from_pkl", false]], "load_empty_model() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.load_empty_model", false]], "load_empty_model() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.load_empty_model", false]], "load_empty_model() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.load_empty_model", false]], "load_layer_wise_quantized_model() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.load_layer_wise_quantized_model", false]], "load_layer_wise_quantized_model() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.load_layer_wise_quantized_model", false]], "load_module() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.load_module", false]], "load_saved_model() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.load_saved_model", false]], "load_saved_model() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.load_saved_model", false]], "load_tensor() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.load_tensor", false]], "load_tensor() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.load_tensor", false]], "load_tensor_from_shard() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.load_tensor_from_shard", false]], "load_tensor_from_shard() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.load_tensor_from_shard", false]], "load_value() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.load_value", false]], "load_vocab() (in module neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.load_vocab", false]], "load_weight_only() (in module neural_compressor.utils.pytorch)": [[464, "neural_compressor.utils.pytorch.load_weight_only", false]], "loadformat (class in neural_compressor.torch.utils.constants)": [[444, "neural_compressor.torch.utils.constants.LoadFormat", false]], "log() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.log", false]], "log_process() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.log_process", false]], "log_quantizable_layers_per_transformer() (in module neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.log_quantizable_layers_per_transformer", false]], "logger (class in neural_compressor.common.utils.logger)": [[159, "neural_compressor.common.utils.logger.Logger", false]], "logger (class in neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.Logger", false]], "loss (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.Loss", false]], "lowerbitssampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.LowerBitsSampler", false]], "lstmoperator (class in neural_compressor.adaptor.ox_utils.operators.lstm)": [[17, "neural_compressor.adaptor.ox_utils.operators.lstm.LSTMOperator", false]], "m (neural_compressor.compression.pruner.patterns.mha.patternmha attribute)": [[177, "neural_compressor.compression.pruner.patterns.mha.PatternMHA.M", false]], "m (neural_compressor.compression.pruner.patterns.ninm.pytorchpatternninm attribute)": [[178, "neural_compressor.compression.pruner.patterns.ninm.PytorchPatternNInM.M", false]], "mae (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.MAE", false]], "magnitudecriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.MagnitudeCriterion", false]], "magnitudecriterion (class in neural_compressor.compression.pruner.tf_criteria)": [[191, "neural_compressor.compression.pruner.tf_criteria.MagnitudeCriterion", false]], "make_dquant_node() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.make_dquant_node", false]], "make_matmul_weight_only_node() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.make_matmul_weight_only_node", false]], "make_module() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.make_module", false]], "make_nc_model() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.make_nc_model", false]], "make_onnx_inputs_outputs() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.make_onnx_inputs_outputs", false]], "make_onnx_shape() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.make_onnx_shape", false]], "make_quant_node() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.make_quant_node", false]], "make_sub_graph() (in module neural_compressor.adaptor.ox_utils.smooth_quant)": [[29, "neural_compressor.adaptor.ox_utils.smooth_quant.make_sub_graph", false]], "make_symbol_block() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.make_symbol_block", false]], "map_numpy_to_onnx_dtype() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.map_numpy_to_onnx_dtype", false]], "map_onnx_to_numpy_type() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.map_onnx_to_numpy_type", false]], "map_tensorflow_dtype() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.map_tensorflow_dtype", false]], "masks (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.masks", false]], "masks (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.masks", false]], "masks (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.masks", false]], "match_datatype_pattern() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.match_datatype_pattern", false]], "matmuloperator (class in neural_compressor.adaptor.ox_utils.operators.matmul)": [[18, "neural_compressor.adaptor.ox_utils.operators.matmul.MatMulOperator", false]], "max_sparsity_ratio_per_op (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.max_sparsity_ratio_per_op", false]], "max_sparsity_ratio_per_op (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.max_sparsity_ratio_per_op", false]], "max_sparsity_ratio_per_op (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.max_sparsity_ratio_per_op", false]], "max_sparsity_ratio_per_op (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.max_sparsity_ratio_per_op", false]], "max_sparsity_ratio_per_op (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.max_sparsity_ratio_per_op", false]], "max_sparsity_ratio_per_op (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.max_sparsity_ratio_per_op", false]], "maxpooloperator (class in neural_compressor.adaptor.ox_utils.operators.maxpool)": [[19, "neural_compressor.adaptor.ox_utils.operators.maxpool.MaxPoolOperator", false]], "mergeduplicatedqdqoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq)": [[93, "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq.MergeDuplicatedQDQOptimizer", false]], "mergeduplicatedqdqoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq)": [[358, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq.MergeDuplicatedQDQOptimizer", false]], "metainfochangingmemopoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer)": [[81, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer.MetaInfoChangingMemOpOptimizer", false]], "metainfochangingmemopoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer)": [[352, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer.MetaInfoChangingMemOpOptimizer", false]], "metric (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.Metric", false]], "metric_max_over_ground_truths() (in module neural_compressor.metric.evaluate_squad)": [[231, "neural_compressor.metric.evaluate_squad.metric_max_over_ground_truths", false]], "metric_max_over_ground_truths() (in module neural_compressor.metric.f1)": [[232, "neural_compressor.metric.f1.metric_max_over_ground_truths", false]], "metric_registry() (in module neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.metric_registry", false]], "metrics (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.METRICS", false]], "metrics (neural_compressor.metric.metric.metrics attribute)": [[234, "neural_compressor.metric.metric.METRICS.metrics", false]], "metrics (neural_compressor.metric.metric.mxnetmetrics attribute)": [[234, "neural_compressor.metric.metric.MXNetMetrics.metrics", false]], "metrics (neural_compressor.metric.metric.onnxrtitmetrics attribute)": [[234, "neural_compressor.metric.metric.ONNXRTITMetrics.metrics", false]], "metrics (neural_compressor.metric.metric.onnxrtqlmetrics attribute)": [[234, "neural_compressor.metric.metric.ONNXRTQLMetrics.metrics", false]], "metrics (neural_compressor.metric.metric.pytorchmetrics attribute)": [[234, "neural_compressor.metric.metric.PyTorchMetrics.metrics", false]], "metrics (neural_compressor.metric.metric.tensorflowmetrics attribute)": [[234, "neural_compressor.metric.metric.TensorflowMetrics.metrics", false]], "mha_compressions (neural_compressor.compression.pruner.pruners.mha.pythonmultiheadattentionpruner attribute)": [[184, "neural_compressor.compression.pruner.pruners.mha.PythonMultiheadAttentionPruner.mha_compressions", false]], "mha_scores (neural_compressor.compression.pruner.pruners.mha.pythonmultiheadattentionpruner attribute)": [[184, "neural_compressor.compression.pruner.pruners.mha.PythonMultiheadAttentionPruner.mha_scores", false]], "min_sparsity_ratio_per_op (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.min_sparsity_ratio_per_op", false]], "min_sparsity_ratio_per_op (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.min_sparsity_ratio_per_op", false]], "min_sparsity_ratio_per_op (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.min_sparsity_ratio_per_op", false]], "minmaxcalibrator (class in neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.MinMaxCalibrator", false]], "miou (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.mIOU", false]], "mixed_precision_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.mixed_precision_entry", false]], "mixedprecisionconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.MixedPrecisionConfig", false]], "mixedprecisionconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.MixedPrecisionConfig", false]], "mnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MNIST", false]], "mode (class in neural_compressor.common.utils.constants)": [[157, "neural_compressor.common.utils.constants.Mode", false]], "mode (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.MODE", false]], "model (class in neural_compressor.model.model)": [[239, "neural_compressor.model.model.Model", false]], "model (class in neural_compressor.tensorflow.utils.model)": [[389, "neural_compressor.tensorflow.utils.model.Model", false]], "model (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcher.model", false]], "model (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearchertf attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcherTF.model", false]], "model (neural_compressor.compression.pruner.model_slim.pattern_analyzer.jitbasicsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher.model", false]], "model (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.model", false]], "model (neural_compressor.compression.pruner.model_slim.pattern_analyzer.recipesearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.RecipeSearcher.model", false]], "model (neural_compressor.compression.pruner.model_slim.pattern_analyzer.selfmhasearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.SelfMHASearcher.model", false]], "model (neural_compressor.compression.pruner.pruning.basepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasePruning.model", false]], "model (neural_compressor.compression.pruner.pruning.basicpruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasicPruning.model", false]], "model (neural_compressor.compression.pruner.pruning.retrainfreepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.RetrainFreePruning.model", false]], "model_forward() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.model_forward", false]], "model_forward() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.model_forward", false]], "model_forward_per_sample() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.model_forward_per_sample", false]], "model_level (neural_compressor.common.tuning_param.paramlevel attribute)": [[156, "neural_compressor.common.tuning_param.ParamLevel.MODEL_LEVEL", false]], "model_slim() (in module neural_compressor.compression.pruner.model_slim.auto_slim)": [[171, "neural_compressor.compression.pruner.model_slim.auto_slim.model_slim", false]], "model_slim_ffn2() (in module neural_compressor.compression.pruner.model_slim.auto_slim)": [[171, "neural_compressor.compression.pruner.model_slim.auto_slim.model_slim_ffn2", false]], "model_slim_mha() (in module neural_compressor.compression.pruner.model_slim.auto_slim)": [[171, "neural_compressor.compression.pruner.model_slim.auto_slim.model_slim_mha", false]], "modelsize (class in neural_compressor.objective)": [[245, "neural_compressor.objective.ModelSize", false]], "modelwisetuningsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.ModelWiseTuningSampler", false]], "module": [[0, "module-neural_compressor.adaptor.mxnet_utils", false], [1, "module-neural_compressor.adaptor.mxnet_utils.util", false], [2, "module-neural_compressor.adaptor.ox_utils.calibration", false], [3, "module-neural_compressor.adaptor.ox_utils.calibrator", false], [4, "module-neural_compressor.adaptor.ox_utils", false], [5, "module-neural_compressor.adaptor.ox_utils.operators.activation", false], [6, "module-neural_compressor.adaptor.ox_utils.operators.argmax", false], [7, "module-neural_compressor.adaptor.ox_utils.operators.attention", false], [8, "module-neural_compressor.adaptor.ox_utils.operators.binary_op", false], [9, "module-neural_compressor.adaptor.ox_utils.operators.concat", false], [10, "module-neural_compressor.adaptor.ox_utils.operators.conv", false], [11, "module-neural_compressor.adaptor.ox_utils.operators.direct_q8", false], [12, "module-neural_compressor.adaptor.ox_utils.operators.embed_layernorm", false], [13, "module-neural_compressor.adaptor.ox_utils.operators.gather", false], [14, "module-neural_compressor.adaptor.ox_utils.operators.gavgpool", false], [15, "module-neural_compressor.adaptor.ox_utils.operators.gemm", false], [16, "module-neural_compressor.adaptor.ox_utils.operators", false], [17, "module-neural_compressor.adaptor.ox_utils.operators.lstm", false], [18, "module-neural_compressor.adaptor.ox_utils.operators.matmul", false], [19, "module-neural_compressor.adaptor.ox_utils.operators.maxpool", false], [20, "module-neural_compressor.adaptor.ox_utils.operators.norm", false], [21, "module-neural_compressor.adaptor.ox_utils.operators.ops", false], [22, "module-neural_compressor.adaptor.ox_utils.operators.pad", false], [23, "module-neural_compressor.adaptor.ox_utils.operators.pooling", false], [24, "module-neural_compressor.adaptor.ox_utils.operators.reduce", false], [25, "module-neural_compressor.adaptor.ox_utils.operators.resize", false], [26, "module-neural_compressor.adaptor.ox_utils.operators.split", false], [27, "module-neural_compressor.adaptor.ox_utils.operators.unary_op", false], [28, "module-neural_compressor.adaptor.ox_utils.quantizer", false], [29, "module-neural_compressor.adaptor.ox_utils.smooth_quant", false], [30, "module-neural_compressor.adaptor.ox_utils.util", false], [31, "module-neural_compressor.adaptor.ox_utils.weight_only", false], [32, "module-neural_compressor.adaptor.tensorflow", false], [33, "module-neural_compressor.adaptor.tf_utils.graph_converter", false], [34, "module-neural_compressor.adaptor.tf_utils.graph_converter_without_calib", false], [35, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert", false], [36, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer", false], [37, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16", false], [38, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd", false], [39, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout", false], [40, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu", false], [41, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random", false], [42, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const", false], [43, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction", false], [44, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd", false], [45, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer", false], [46, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape", false], [47, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm", false], [48, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant", false], [49, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add", false], [50, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul", false], [51, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math", false], [52, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn", false], [53, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in", false], [54, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu", false], [55, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm", false], [56, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv", false], [57, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv", false], [58, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose", false], [59, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer", false], [60, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass", false], [61, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic", false], [62, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node", false], [63, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu", false], [64, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize", false], [65, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes", false], [66, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm", false], [67, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input", false], [68, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes", false], [69, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes", false], [70, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer", false], [71, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base", false], [72, "module-neural_compressor.adaptor.tf_utils.graph_rewriter", false], [73, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant", false], [74, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value", false], [75, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib", false], [76, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize", false], [77, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize", false], [78, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize", false], [79, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize", false], [80, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8", false], [81, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer", false], [82, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter", false], [83, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse", false], [84, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert", false], [85, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation", false], [86, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx", false], [87, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph", false], [88, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node", false], [89, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema", false], [90, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils", false], [91, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq", false], [92, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern", false], [93, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq", false], [94, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern", false], [95, "module-neural_compressor.adaptor.tf_utils.graph_util", false], [96, "module-neural_compressor.adaptor.tf_utils", false], [97, "module-neural_compressor.adaptor.tf_utils.quantize_graph", false], [98, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize", false], [99, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat", false], [100, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config", false], [101, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper", false], [102, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers", false], [103, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer", false], [104, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add", false], [105, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base", false], [106, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn", false], [107, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper", false], [108, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn", false], [109, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2", false], [110, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv", false], [111, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv", false], [112, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in", false], [113, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul", false], [114, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling", false], [115, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq", false], [116, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq", false], [117, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base", false], [118, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn", false], [119, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2", false], [120, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv", false], [121, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu", false], [122, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul", false], [123, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling", false], [124, "module-neural_compressor.adaptor.tf_utils.quantize_graph_common", false], [125, "module-neural_compressor.adaptor.tf_utils.smooth_quant_calibration", false], [126, "module-neural_compressor.adaptor.tf_utils.smooth_quant_scaler", false], [127, "module-neural_compressor.adaptor.tf_utils.tf2onnx_converter", false], [128, "module-neural_compressor.adaptor.tf_utils.transform_graph.bias_correction", false], [129, "module-neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base", false], [130, "module-neural_compressor.adaptor.tf_utils.transform_graph", false], [131, "module-neural_compressor.adaptor.tf_utils.transform_graph.insert_logging", false], [132, "module-neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat", false], [133, "module-neural_compressor.adaptor.tf_utils.util", false], [134, "module-neural_compressor.adaptor.torch_utils.bf16_convert", false], [135, "module-neural_compressor.adaptor.torch_utils.hawq_metric", false], [136, "module-neural_compressor.adaptor.torch_utils", false], [137, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant", false], [138, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle", false], [139, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize", false], [140, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load", false], [141, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.utils", false], [142, "module-neural_compressor.adaptor.torch_utils.model_wrapper", false], [143, "module-neural_compressor.adaptor.torch_utils.pattern_detector", false], [144, "module-neural_compressor.adaptor.torch_utils.symbolic_trace", false], [145, "module-neural_compressor.adaptor.torch_utils.util", false], [146, "module-neural_compressor.algorithm.algorithm", false], [147, "module-neural_compressor.algorithm.fast_bias_correction", false], [148, "module-neural_compressor.algorithm", false], [149, "module-neural_compressor.algorithm.smooth_quant", false], [150, "module-neural_compressor.algorithm.weight_correction", false], [151, "module-neural_compressor.benchmark", false], [152, "module-neural_compressor.common.base_config", false], [153, "module-neural_compressor.common.base_tuning", false], [154, "module-neural_compressor.common.benchmark", false], [155, "module-neural_compressor.common", false], [156, "module-neural_compressor.common.tuning_param", false], [157, "module-neural_compressor.common.utils.constants", false], [158, "module-neural_compressor.common.utils", false], [159, "module-neural_compressor.common.utils.logger", false], [160, "module-neural_compressor.common.utils.save_load", false], [161, "module-neural_compressor.common.utils.utility", false], [162, "module-neural_compressor.compression.callbacks", false], [163, "module-neural_compressor.compression.distillation.criterions", false], [164, "module-neural_compressor.compression.distillation", false], [165, "module-neural_compressor.compression.distillation.optimizers", false], [166, "module-neural_compressor.compression.distillation.utility", false], [167, "module-neural_compressor.compression.hpo", false], [168, "module-neural_compressor.compression.hpo.sa_optimizer", false], [169, "module-neural_compressor.compression.pruner.criteria", false], [170, "module-neural_compressor.compression.pruner", false], [171, "module-neural_compressor.compression.pruner.model_slim.auto_slim", false], [172, "module-neural_compressor.compression.pruner.model_slim", false], [173, "module-neural_compressor.compression.pruner.model_slim.pattern_analyzer", false], [174, "module-neural_compressor.compression.pruner.model_slim.weight_slim", false], [175, "module-neural_compressor.compression.pruner.patterns.base", false], [176, "module-neural_compressor.compression.pruner.patterns", false], [177, "module-neural_compressor.compression.pruner.patterns.mha", false], [178, "module-neural_compressor.compression.pruner.patterns.ninm", false], [179, "module-neural_compressor.compression.pruner.patterns.nxm", false], [180, "module-neural_compressor.compression.pruner.pruners.base", false], [181, "module-neural_compressor.compression.pruner.pruners.basic", false], [182, "module-neural_compressor.compression.pruner.pruners.block_mask", false], [183, "module-neural_compressor.compression.pruner.pruners", false], [184, "module-neural_compressor.compression.pruner.pruners.mha", false], [185, "module-neural_compressor.compression.pruner.pruners.pattern_lock", false], [186, "module-neural_compressor.compression.pruner.pruners.progressive", false], [187, "module-neural_compressor.compression.pruner.pruners.retrain_free", false], [188, "module-neural_compressor.compression.pruner.pruning", false], [189, "module-neural_compressor.compression.pruner.regs", false], [190, "module-neural_compressor.compression.pruner.schedulers", false], [191, "module-neural_compressor.compression.pruner.tf_criteria", false], [192, "module-neural_compressor.compression.pruner.utils", false], [193, "module-neural_compressor.compression.pruner.wanda", false], [194, "module-neural_compressor.compression.pruner.wanda.utils", false], [195, "module-neural_compressor.config", false], [196, "module-neural_compressor.contrib", false], [197, "module-neural_compressor.contrib.strategy", false], [198, "module-neural_compressor.contrib.strategy.sigopt", false], [199, "module-neural_compressor.contrib.strategy.tpe", false], [200, "module-neural_compressor.data.dataloaders.base_dataloader", false], [201, "module-neural_compressor.data.dataloaders.dataloader", false], [202, "module-neural_compressor.data.dataloaders.default_dataloader", false], [203, "module-neural_compressor.data.dataloaders.fetcher", false], [204, "module-neural_compressor.data.dataloaders.mxnet_dataloader", false], [205, "module-neural_compressor.data.dataloaders.onnxrt_dataloader", false], [206, "module-neural_compressor.data.dataloaders.pytorch_dataloader", false], [207, "module-neural_compressor.data.dataloaders.sampler", false], [208, "module-neural_compressor.data.dataloaders.tensorflow_dataloader", false], [209, "module-neural_compressor.data.datasets.bert_dataset", false], [210, "module-neural_compressor.data.datasets.coco_dataset", false], [211, "module-neural_compressor.data.datasets.dataset", false], [212, "module-neural_compressor.data.datasets.dummy_dataset", false], [213, "module-neural_compressor.data.datasets.dummy_dataset_v2", false], [214, "module-neural_compressor.data.datasets.imagenet_dataset", false], [215, "module-neural_compressor.data.datasets", false], [216, "module-neural_compressor.data.datasets.style_transfer_dataset", false], [217, "module-neural_compressor.data.filters.coco_filter", false], [218, "module-neural_compressor.data.filters.filter", false], [219, "module-neural_compressor.data.filters", false], [220, "module-neural_compressor.data", false], [221, "module-neural_compressor.data.transforms.imagenet_transform", false], [222, "module-neural_compressor.data.transforms", false], [223, "module-neural_compressor.data.transforms.postprocess", false], [224, "module-neural_compressor.data.transforms.tokenization", false], [225, "module-neural_compressor.data.transforms.transform", false], [226, "module-neural_compressor", false], [227, "module-neural_compressor.metric.bleu", false], [228, "module-neural_compressor.metric.bleu_util", false], [229, "module-neural_compressor.metric.coco_label_map", false], [230, "module-neural_compressor.metric.coco_tools", false], [231, "module-neural_compressor.metric.evaluate_squad", false], [232, "module-neural_compressor.metric.f1", false], [233, "module-neural_compressor.metric", false], [234, "module-neural_compressor.metric.metric", false], [235, "module-neural_compressor.mix_precision", false], [236, "module-neural_compressor.model.base_model", false], [237, "module-neural_compressor.model", false], [238, "module-neural_compressor.model.keras_model", false], [239, "module-neural_compressor.model.model", false], [240, "module-neural_compressor.model.mxnet_model", false], [241, "module-neural_compressor.model.nets_factory", false], [242, "module-neural_compressor.model.onnx_model", false], [243, "module-neural_compressor.model.tensorflow_model", false], [244, "module-neural_compressor.model.torch_model", false], [245, "module-neural_compressor.objective", false], [246, "module-neural_compressor.profiling", false], [247, "module-neural_compressor.profiling.parser.factory", false], [248, "module-neural_compressor.profiling.parser.onnx_parser.factory", false], [249, "module-neural_compressor.profiling.parser.onnx_parser.parser", false], [250, "module-neural_compressor.profiling.parser.parser", false], [251, "module-neural_compressor.profiling.parser.result", false], [252, "module-neural_compressor.profiling.parser.tensorflow_parser.factory", false], [253, "module-neural_compressor.profiling.parser.tensorflow_parser.parser", false], [254, "module-neural_compressor.profiling.profiler.factory", false], [255, "module-neural_compressor.profiling.profiler.onnxrt_profiler.factory", false], [256, "module-neural_compressor.profiling.profiler.onnxrt_profiler.profiler", false], [257, "module-neural_compressor.profiling.profiler.onnxrt_profiler.utils", false], [258, "module-neural_compressor.profiling.profiler.profiler", false], [259, "module-neural_compressor.profiling.profiler.tensorflow_profiler.factory", false], [260, "module-neural_compressor.profiling.profiler.tensorflow_profiler.profiler", false], [261, "module-neural_compressor.profiling.profiler.tensorflow_profiler.utils", false], [262, "module-neural_compressor.quantization", false], [263, "module-neural_compressor.strategy.auto", false], [264, "module-neural_compressor.strategy.auto_mixed_precision", false], [265, "module-neural_compressor.strategy.basic", false], [266, "module-neural_compressor.strategy.bayesian", false], [267, "module-neural_compressor.strategy.conservative", false], [268, "module-neural_compressor.strategy.exhaustive", false], [269, "module-neural_compressor.strategy.hawq_v2", false], [270, "module-neural_compressor.strategy", false], [271, "module-neural_compressor.strategy.mse", false], [272, "module-neural_compressor.strategy.mse_v2", false], [273, "module-neural_compressor.strategy.random", false], [274, "module-neural_compressor.strategy.strategy", false], [275, "module-neural_compressor.strategy.utils.constant", false], [276, "module-neural_compressor.strategy.utils", false], [277, "module-neural_compressor.strategy.utils.tuning_sampler", false], [278, "module-neural_compressor.strategy.utils.tuning_space", false], [279, "module-neural_compressor.strategy.utils.tuning_structs", false], [280, "module-neural_compressor.strategy.utils.utility", false], [281, "module-neural_compressor.template.api_doc_example", false], [282, "module-neural_compressor.tensorflow.algorithms", false], [283, "module-neural_compressor.tensorflow.algorithms.smoother.calibration", false], [284, "module-neural_compressor.tensorflow.algorithms.smoother.core", false], [285, "module-neural_compressor.tensorflow.algorithms.smoother", false], [286, "module-neural_compressor.tensorflow.algorithms.smoother.scaler", false], [287, "module-neural_compressor.tensorflow.algorithms.static_quant", false], [288, "module-neural_compressor.tensorflow.algorithms.static_quant.keras", false], [289, "module-neural_compressor.tensorflow.algorithms.static_quant.tensorflow", false], [290, "module-neural_compressor.tensorflow", false], [291, "module-neural_compressor.tensorflow.keras", false], [292, "module-neural_compressor.tensorflow.keras.layers.conv2d", false], [293, "module-neural_compressor.tensorflow.keras.layers.dense", false], [294, "module-neural_compressor.tensorflow.keras.layers.depthwise_conv2d", false], [295, "module-neural_compressor.tensorflow.keras.layers", false], [296, "module-neural_compressor.tensorflow.keras.layers.layer_initializer", false], [297, "module-neural_compressor.tensorflow.keras.layers.pool2d", false], [298, "module-neural_compressor.tensorflow.keras.layers.separable_conv2d", false], [299, "module-neural_compressor.tensorflow.keras.quantization.config", false], [300, "module-neural_compressor.tensorflow.keras.quantization", false], [301, "module-neural_compressor.tensorflow.quantization.algorithm_entry", false], [302, "module-neural_compressor.tensorflow.quantization.autotune", false], [303, "module-neural_compressor.tensorflow.quantization.config", false], [304, "module-neural_compressor.tensorflow.quantization", false], [305, "module-neural_compressor.tensorflow.quantization.quantize", false], [306, "module-neural_compressor.tensorflow.quantization.utils.graph_converter", false], [307, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert", false], [308, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer", false], [309, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16", false], [310, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd", false], [311, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout", false], [312, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu", false], [313, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random", false], [314, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const", false], [315, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction", false], [316, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd", false], [317, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer", false], [318, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape", false], [319, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm", false], [320, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant", false], [321, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add", false], [322, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul", false], [323, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math", false], [324, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn", false], [325, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in", false], [326, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu", false], [327, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm", false], [328, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv", false], [329, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv", false], [330, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose", false], [331, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer", false], [332, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass", false], [333, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic", false], [334, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node", false], [335, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu", false], [336, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize", false], [337, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes", false], [338, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm", false], [339, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input", false], [340, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes", false], [341, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes", false], [342, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer", false], [343, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base", false], [344, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter", false], [345, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant", false], [346, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value", false], [347, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize", false], [348, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize", false], [349, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize", false], [350, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize", false], [351, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8", false], [352, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer", false], [353, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter", false], [354, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse", false], [355, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation", false], [356, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq", false], [357, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern", false], [358, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq", false], [359, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern", false], [360, "module-neural_compressor.tensorflow.quantization.utils.graph_util", false], [361, "module-neural_compressor.tensorflow.quantization.utils", false], [362, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph", false], [363, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn", false], [364, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2", false], [365, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv", false], [366, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv", false], [367, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in", false], [368, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul", false], [369, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling", false], [370, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq", false], [371, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq", false], [372, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base", false], [373, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn", false], [374, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2", false], [375, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv", false], [376, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu", false], [377, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul", false], [378, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling", false], [379, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph_common", false], [380, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction", false], [381, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base", false], [382, "module-neural_compressor.tensorflow.quantization.utils.transform_graph", false], [383, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging", false], [384, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat", false], [385, "module-neural_compressor.tensorflow.quantization.utils.utility", false], [386, "module-neural_compressor.tensorflow.utils.constants", false], [387, "module-neural_compressor.tensorflow.utils.data", false], [388, "module-neural_compressor.tensorflow.utils", false], [389, "module-neural_compressor.tensorflow.utils.model", false], [390, "module-neural_compressor.tensorflow.utils.model_wrappers", false], [391, "module-neural_compressor.tensorflow.utils.utility", false], [392, "module-neural_compressor.torch.algorithms.base_algorithm", false], [393, "module-neural_compressor.torch.algorithms.fp8_quant.utils.logger", false], [394, "module-neural_compressor.torch.algorithms", false], [395, "module-neural_compressor.torch.algorithms.layer_wise", false], [396, "module-neural_compressor.torch.algorithms.layer_wise.load", false], [397, "module-neural_compressor.torch.algorithms.layer_wise.modified_pickle", false], [398, "module-neural_compressor.torch.algorithms.layer_wise.utils", false], [399, "module-neural_compressor.torch.algorithms.mixed_precision.half_precision_convert", false], [400, "module-neural_compressor.torch.algorithms.mixed_precision", false], [401, "module-neural_compressor.torch.algorithms.mixed_precision.module_wrappers", false], [402, "module-neural_compressor.torch.algorithms.mx_quant", false], [403, "module-neural_compressor.torch.algorithms.mx_quant.mx", false], [404, "module-neural_compressor.torch.algorithms.mx_quant.utils", false], [405, "module-neural_compressor.torch.algorithms.pt2e_quant.core", false], [406, "module-neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter", false], [407, "module-neural_compressor.torch.algorithms.pt2e_quant", false], [408, "module-neural_compressor.torch.algorithms.pt2e_quant.save_load", false], [409, "module-neural_compressor.torch.algorithms.pt2e_quant.utility", false], [410, "module-neural_compressor.torch.algorithms.smooth_quant", false], [411, "module-neural_compressor.torch.algorithms.smooth_quant.save_load", false], [412, "module-neural_compressor.torch.algorithms.smooth_quant.smooth_quant", false], [413, "module-neural_compressor.torch.algorithms.smooth_quant.utility", false], [414, "module-neural_compressor.torch.algorithms.static_quant", false], [415, "module-neural_compressor.torch.algorithms.static_quant.save_load", false], [416, "module-neural_compressor.torch.algorithms.static_quant.static_quant", false], [417, "module-neural_compressor.torch.algorithms.static_quant.utility", false], [418, "module-neural_compressor.torch.algorithms.weight_only.autoround", false], [419, "module-neural_compressor.torch.algorithms.weight_only.awq", false], [420, "module-neural_compressor.torch.algorithms.weight_only.gptq", false], [421, "module-neural_compressor.torch.algorithms.weight_only.hqq.bitpack", false], [422, "module-neural_compressor.torch.algorithms.weight_only.hqq.config", false], [423, "module-neural_compressor.torch.algorithms.weight_only.hqq.core", false], [424, "module-neural_compressor.torch.algorithms.weight_only.hqq", false], [425, "module-neural_compressor.torch.algorithms.weight_only.hqq.optimizer", false], [426, "module-neural_compressor.torch.algorithms.weight_only.hqq.qtensor", false], [427, "module-neural_compressor.torch.algorithms.weight_only.hqq.quantizer", false], [428, "module-neural_compressor.torch.algorithms.weight_only", false], [429, "module-neural_compressor.torch.algorithms.weight_only.modules", false], [430, "module-neural_compressor.torch.algorithms.weight_only.rtn", false], [431, "module-neural_compressor.torch.algorithms.weight_only.save_load", false], [432, "module-neural_compressor.torch.algorithms.weight_only.teq", false], [433, "module-neural_compressor.torch.algorithms.weight_only.utility", false], [434, "module-neural_compressor.torch.export", false], [435, "module-neural_compressor.torch.export.pt2e_export", false], [436, "module-neural_compressor.torch", false], [437, "module-neural_compressor.torch.quantization.algorithm_entry", false], [438, "module-neural_compressor.torch.quantization.autotune", false], [439, "module-neural_compressor.torch.quantization.config", false], [440, "module-neural_compressor.torch.quantization", false], [441, "module-neural_compressor.torch.quantization.load_entry", false], [442, "module-neural_compressor.torch.quantization.quantize", false], [443, "module-neural_compressor.torch.utils.auto_accelerator", false], [444, "module-neural_compressor.torch.utils.constants", false], [445, "module-neural_compressor.torch.utils.environ", false], [446, "module-neural_compressor.torch.utils", false], [447, "module-neural_compressor.torch.utils.utility", false], [448, "module-neural_compressor.training", false], [449, "module-neural_compressor.transformers.quantization.utils", false], [450, "module-neural_compressor.transformers.utils", false], [451, "module-neural_compressor.transformers.utils.quantization_config", false], [452, "module-neural_compressor.utils.collect_layer_histogram", false], [453, "module-neural_compressor.utils.constant", false], [454, "module-neural_compressor.utils.create_obj_from_config", false], [455, "module-neural_compressor.utils.export", false], [456, "module-neural_compressor.utils.export.qlinear2qdq", false], [457, "module-neural_compressor.utils.export.tf2onnx", false], [458, "module-neural_compressor.utils.export.torch2onnx", false], [459, "module-neural_compressor.utils", false], [460, "module-neural_compressor.utils.kl_divergence", false], [461, "module-neural_compressor.utils.load_huggingface", false], [462, "module-neural_compressor.utils.logger", false], [463, "module-neural_compressor.utils.options", false], [464, "module-neural_compressor.utils.pytorch", false], [465, "module-neural_compressor.utils.utility", false], [466, "module-neural_compressor.utils.weights_details", false], [467, "module-neural_compressor.version", false]], "module_debug_level1 (in module neural_compressor.template.api_doc_example)": [[281, "neural_compressor.template.api_doc_example.module_debug_level1", false]], "modules (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.modules", false]], "modules (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.modules", false]], "modules (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.modules", false]], "modules (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.modules", false]], "modules (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.modules", false]], "modules (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.modules", false]], "move_input_device() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.move_input_device", false]], "move_input_to_device() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.move_input_to_device", false]], "move_input_to_device() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.move_input_to_device", false]], "movesqueezeafterreluoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu)": [[63, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu.MoveSqueezeAfterReluOptimizer", false]], "movesqueezeafterreluoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu)": [[335, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu.MoveSqueezeAfterReluOptimizer", false]], "mse (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.MSE", false]], "mse (neural_compressor.metric.metric.rmse attribute)": [[234, "neural_compressor.metric.metric.RMSE.mse", false]], "mse_metric_gap() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.mse_metric_gap", false]], "mse_v2tunestrategy (class in neural_compressor.strategy.mse_v2)": [[272, "neural_compressor.strategy.mse_v2.MSE_V2TuneStrategy", false]], "msetunestrategy (class in neural_compressor.strategy.mse)": [[271, "neural_compressor.strategy.mse.MSETuneStrategy", false]], "mullinear (class in neural_compressor.adaptor.torch_utils.model_wrapper)": [[142, "neural_compressor.adaptor.torch_utils.model_wrapper.MulLinear", false]], "mullinear (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.MulLinear", false]], "multiobjective (class in neural_compressor.objective)": [[245, "neural_compressor.objective.MultiObjective", false]], "mx_quant_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.mx_quant_entry", false]], "mxlinear (class in neural_compressor.torch.algorithms.mx_quant.mx)": [[403, "neural_compressor.torch.algorithms.mx_quant.mx.MXLinear", false]], "mxnet (class in neural_compressor.config)": [[195, "neural_compressor.config.MXNet", false]], "mxnetcifar10 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MXNetCIFAR10", false]], "mxnetcifar100 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MXNetCIFAR100", false]], "mxnetcropresizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.MXNetCropResizeTransform", false]], "mxnetcroptoboundingbox (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.MXNetCropToBoundingBox", false]], "mxnetdataloader (class in neural_compressor.data.dataloaders.mxnet_dataloader)": [[204, "neural_compressor.data.dataloaders.mxnet_dataloader.MXNetDataLoader", false]], "mxnetdatasets (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MXNetDatasets", false]], "mxnetfashionmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MXNetFashionMNIST", false]], "mxnetfilters (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.MXNetFilters", false]], "mxnetimagefolder (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MXNetImageFolder", false]], "mxnetimagenetraw (class in neural_compressor.data.datasets.imagenet_dataset)": [[214, "neural_compressor.data.datasets.imagenet_dataset.MXNetImagenetRaw", false]], "mxnetmetrics (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.MXNetMetrics", false]], "mxnetmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.MXNetMNIST", false]], "mxnetmodel (class in neural_compressor.model.mxnet_model)": [[240, "neural_compressor.model.mxnet_model.MXNetModel", false]], "mxnetnormalizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.MXNetNormalizeTransform", false]], "mxnettransforms (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.MXNetTransforms", false]], "mxnettranspose (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.MXNetTranspose", false]], "mxquantconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.MXQuantConfig", false]], "mxquantizer (class in neural_compressor.torch.algorithms.mx_quant.mx)": [[403, "neural_compressor.torch.algorithms.mx_quant.mx.MXQuantizer", false]], "n (neural_compressor.compression.pruner.patterns.mha.patternmha attribute)": [[177, "neural_compressor.compression.pruner.patterns.mha.PatternMHA.N", false]], "n (neural_compressor.compression.pruner.patterns.ninm.pytorchpatternninm attribute)": [[178, "neural_compressor.compression.pruner.patterns.ninm.PytorchPatternNInM.N", false]], "name (neural_compressor.common.base_config.baseconfig attribute)": [[152, "neural_compressor.common.base_config.BaseConfig.name", false]], "namecollector (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.NameCollector", false]], "nasconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.NASConfig", false]], "nbits (neural_compressor.torch.algorithms.weight_only.hqq.qtensor.qtensormetainfo attribute)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo.nbits", false]], "ndarray_to_device() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.ndarray_to_device", false]], "need_apply() (in module neural_compressor.tensorflow.quantization.quantize)": [[305, "neural_compressor.tensorflow.quantization.quantize.need_apply", false]], "need_apply() (in module neural_compressor.torch.quantization.quantize)": [[442, "neural_compressor.torch.quantization.quantize.need_apply", false]], "neural_compressor": [[226, "module-neural_compressor", false]], "neural_compressor.adaptor.mxnet_utils": [[0, "module-neural_compressor.adaptor.mxnet_utils", false]], "neural_compressor.adaptor.mxnet_utils.util": [[1, "module-neural_compressor.adaptor.mxnet_utils.util", false]], "neural_compressor.adaptor.ox_utils": [[4, "module-neural_compressor.adaptor.ox_utils", false]], "neural_compressor.adaptor.ox_utils.calibration": [[2, "module-neural_compressor.adaptor.ox_utils.calibration", false]], "neural_compressor.adaptor.ox_utils.calibrator": [[3, "module-neural_compressor.adaptor.ox_utils.calibrator", false]], "neural_compressor.adaptor.ox_utils.operators": [[16, "module-neural_compressor.adaptor.ox_utils.operators", false]], "neural_compressor.adaptor.ox_utils.operators.activation": [[5, "module-neural_compressor.adaptor.ox_utils.operators.activation", false]], "neural_compressor.adaptor.ox_utils.operators.argmax": [[6, "module-neural_compressor.adaptor.ox_utils.operators.argmax", false]], "neural_compressor.adaptor.ox_utils.operators.attention": [[7, "module-neural_compressor.adaptor.ox_utils.operators.attention", false]], "neural_compressor.adaptor.ox_utils.operators.binary_op": [[8, "module-neural_compressor.adaptor.ox_utils.operators.binary_op", false]], "neural_compressor.adaptor.ox_utils.operators.concat": [[9, "module-neural_compressor.adaptor.ox_utils.operators.concat", false]], "neural_compressor.adaptor.ox_utils.operators.conv": [[10, "module-neural_compressor.adaptor.ox_utils.operators.conv", false]], "neural_compressor.adaptor.ox_utils.operators.direct_q8": [[11, "module-neural_compressor.adaptor.ox_utils.operators.direct_q8", false]], "neural_compressor.adaptor.ox_utils.operators.embed_layernorm": [[12, "module-neural_compressor.adaptor.ox_utils.operators.embed_layernorm", false]], "neural_compressor.adaptor.ox_utils.operators.gather": [[13, "module-neural_compressor.adaptor.ox_utils.operators.gather", false]], "neural_compressor.adaptor.ox_utils.operators.gavgpool": [[14, "module-neural_compressor.adaptor.ox_utils.operators.gavgpool", false]], "neural_compressor.adaptor.ox_utils.operators.gemm": [[15, "module-neural_compressor.adaptor.ox_utils.operators.gemm", false]], "neural_compressor.adaptor.ox_utils.operators.lstm": [[17, "module-neural_compressor.adaptor.ox_utils.operators.lstm", false]], "neural_compressor.adaptor.ox_utils.operators.matmul": [[18, "module-neural_compressor.adaptor.ox_utils.operators.matmul", false]], "neural_compressor.adaptor.ox_utils.operators.maxpool": [[19, "module-neural_compressor.adaptor.ox_utils.operators.maxpool", false]], "neural_compressor.adaptor.ox_utils.operators.norm": [[20, "module-neural_compressor.adaptor.ox_utils.operators.norm", false]], "neural_compressor.adaptor.ox_utils.operators.ops": [[21, "module-neural_compressor.adaptor.ox_utils.operators.ops", false]], "neural_compressor.adaptor.ox_utils.operators.pad": [[22, "module-neural_compressor.adaptor.ox_utils.operators.pad", false]], "neural_compressor.adaptor.ox_utils.operators.pooling": [[23, "module-neural_compressor.adaptor.ox_utils.operators.pooling", false]], "neural_compressor.adaptor.ox_utils.operators.reduce": [[24, "module-neural_compressor.adaptor.ox_utils.operators.reduce", false]], "neural_compressor.adaptor.ox_utils.operators.resize": [[25, "module-neural_compressor.adaptor.ox_utils.operators.resize", false]], "neural_compressor.adaptor.ox_utils.operators.split": [[26, "module-neural_compressor.adaptor.ox_utils.operators.split", false]], "neural_compressor.adaptor.ox_utils.operators.unary_op": [[27, "module-neural_compressor.adaptor.ox_utils.operators.unary_op", false]], "neural_compressor.adaptor.ox_utils.quantizer": [[28, "module-neural_compressor.adaptor.ox_utils.quantizer", false]], "neural_compressor.adaptor.ox_utils.smooth_quant": [[29, "module-neural_compressor.adaptor.ox_utils.smooth_quant", false]], "neural_compressor.adaptor.ox_utils.util": [[30, "module-neural_compressor.adaptor.ox_utils.util", false]], "neural_compressor.adaptor.ox_utils.weight_only": [[31, "module-neural_compressor.adaptor.ox_utils.weight_only", false]], "neural_compressor.adaptor.tensorflow": [[32, "module-neural_compressor.adaptor.tensorflow", false]], "neural_compressor.adaptor.tf_utils": [[96, "module-neural_compressor.adaptor.tf_utils", false]], "neural_compressor.adaptor.tf_utils.graph_converter": [[33, "module-neural_compressor.adaptor.tf_utils.graph_converter", false]], "neural_compressor.adaptor.tf_utils.graph_converter_without_calib": [[34, "module-neural_compressor.adaptor.tf_utils.graph_converter_without_calib", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter": [[72, "module-neural_compressor.adaptor.tf_utils.graph_rewriter", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16": [[37, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert": [[35, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer": [[36, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic": [[61, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd": [[38, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout": [[39, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu": [[40, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random": [[41, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const": [[42, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction": [[43, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd": [[44, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer": [[45, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape": [[46, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm": [[47, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant": [[48, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add": [[49, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul": [[50, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math": [[51, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn": [[52, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in": [[53, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu": [[54, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm": [[55, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv": [[56, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv": [[57, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose": [[58, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer": [[59, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass": [[60, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node": [[62, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu": [[63, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize": [[64, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes": [[65, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm": [[66, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input": [[67, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes": [[68, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes": [[69, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer": [[70, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base": [[71, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8": [[80, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant": [[73, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value": [[74, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib": [[75, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize": [[76, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize": [[77, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize": [[78, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize": [[79, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer": [[81, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter": [[82, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse": [[83, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert": [[84, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation": [[85, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx": [[86, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph": [[87, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node": [[88, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema": [[89, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils": [[90, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq": [[91, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern": [[92, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq": [[93, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq", false]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern": [[94, "module-neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern", false]], "neural_compressor.adaptor.tf_utils.graph_util": [[95, "module-neural_compressor.adaptor.tf_utils.graph_util", false]], "neural_compressor.adaptor.tf_utils.quantize_graph": [[97, "module-neural_compressor.adaptor.tf_utils.quantize_graph", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat": [[99, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize": [[98, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config": [[100, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper": [[101, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers": [[102, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer": [[103, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add": [[104, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base": [[105, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn": [[106, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper": [[107, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq": [[115, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn": [[108, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2": [[109, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv": [[110, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv": [[111, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in": [[112, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul": [[113, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling": [[114, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq": [[116, "module-neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base": [[117, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn": [[118, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2": [[119, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv": [[120, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu": [[121, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul": [[122, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul", false]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling": [[123, "module-neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling", false]], "neural_compressor.adaptor.tf_utils.quantize_graph_common": [[124, "module-neural_compressor.adaptor.tf_utils.quantize_graph_common", false]], "neural_compressor.adaptor.tf_utils.smooth_quant_calibration": [[125, "module-neural_compressor.adaptor.tf_utils.smooth_quant_calibration", false]], "neural_compressor.adaptor.tf_utils.smooth_quant_scaler": [[126, "module-neural_compressor.adaptor.tf_utils.smooth_quant_scaler", false]], "neural_compressor.adaptor.tf_utils.tf2onnx_converter": [[127, "module-neural_compressor.adaptor.tf_utils.tf2onnx_converter", false]], "neural_compressor.adaptor.tf_utils.transform_graph": [[130, "module-neural_compressor.adaptor.tf_utils.transform_graph", false]], "neural_compressor.adaptor.tf_utils.transform_graph.bias_correction": [[128, "module-neural_compressor.adaptor.tf_utils.transform_graph.bias_correction", false]], "neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base": [[129, "module-neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base", false]], "neural_compressor.adaptor.tf_utils.transform_graph.insert_logging": [[131, "module-neural_compressor.adaptor.tf_utils.transform_graph.insert_logging", false]], "neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat": [[132, "module-neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat", false]], "neural_compressor.adaptor.tf_utils.util": [[133, "module-neural_compressor.adaptor.tf_utils.util", false]], "neural_compressor.adaptor.torch_utils": [[136, "module-neural_compressor.adaptor.torch_utils", false]], "neural_compressor.adaptor.torch_utils.bf16_convert": [[134, "module-neural_compressor.adaptor.torch_utils.bf16_convert", false]], "neural_compressor.adaptor.torch_utils.hawq_metric": [[135, "module-neural_compressor.adaptor.torch_utils.hawq_metric", false]], "neural_compressor.adaptor.torch_utils.layer_wise_quant": [[137, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant", false]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle": [[138, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle", false]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize": [[139, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize", false]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load": [[140, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load", false]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils": [[141, "module-neural_compressor.adaptor.torch_utils.layer_wise_quant.utils", false]], "neural_compressor.adaptor.torch_utils.model_wrapper": [[142, "module-neural_compressor.adaptor.torch_utils.model_wrapper", false]], "neural_compressor.adaptor.torch_utils.pattern_detector": [[143, "module-neural_compressor.adaptor.torch_utils.pattern_detector", false]], "neural_compressor.adaptor.torch_utils.symbolic_trace": [[144, "module-neural_compressor.adaptor.torch_utils.symbolic_trace", false]], "neural_compressor.adaptor.torch_utils.util": [[145, "module-neural_compressor.adaptor.torch_utils.util", false]], "neural_compressor.algorithm": [[148, "module-neural_compressor.algorithm", false]], "neural_compressor.algorithm.algorithm": [[146, "module-neural_compressor.algorithm.algorithm", false]], "neural_compressor.algorithm.fast_bias_correction": [[147, "module-neural_compressor.algorithm.fast_bias_correction", false]], "neural_compressor.algorithm.smooth_quant": [[149, "module-neural_compressor.algorithm.smooth_quant", false]], "neural_compressor.algorithm.weight_correction": [[150, "module-neural_compressor.algorithm.weight_correction", false]], "neural_compressor.benchmark": [[151, "module-neural_compressor.benchmark", false]], "neural_compressor.common": [[155, "module-neural_compressor.common", false]], "neural_compressor.common.base_config": [[152, "module-neural_compressor.common.base_config", false]], "neural_compressor.common.base_tuning": [[153, "module-neural_compressor.common.base_tuning", false]], "neural_compressor.common.benchmark": [[154, "module-neural_compressor.common.benchmark", false]], "neural_compressor.common.tuning_param": [[156, "module-neural_compressor.common.tuning_param", false]], "neural_compressor.common.utils": [[158, "module-neural_compressor.common.utils", false]], "neural_compressor.common.utils.constants": [[157, "module-neural_compressor.common.utils.constants", false]], "neural_compressor.common.utils.logger": [[159, "module-neural_compressor.common.utils.logger", false]], "neural_compressor.common.utils.save_load": [[160, "module-neural_compressor.common.utils.save_load", false]], "neural_compressor.common.utils.utility": [[161, "module-neural_compressor.common.utils.utility", false]], "neural_compressor.compression.callbacks": [[162, "module-neural_compressor.compression.callbacks", false]], "neural_compressor.compression.distillation": [[164, "module-neural_compressor.compression.distillation", false]], "neural_compressor.compression.distillation.criterions": [[163, "module-neural_compressor.compression.distillation.criterions", false]], "neural_compressor.compression.distillation.optimizers": [[165, "module-neural_compressor.compression.distillation.optimizers", false]], "neural_compressor.compression.distillation.utility": [[166, "module-neural_compressor.compression.distillation.utility", false]], "neural_compressor.compression.hpo": [[167, "module-neural_compressor.compression.hpo", false]], "neural_compressor.compression.hpo.sa_optimizer": [[168, "module-neural_compressor.compression.hpo.sa_optimizer", false]], "neural_compressor.compression.pruner": [[170, "module-neural_compressor.compression.pruner", false]], "neural_compressor.compression.pruner.criteria": [[169, "module-neural_compressor.compression.pruner.criteria", false]], "neural_compressor.compression.pruner.model_slim": [[172, "module-neural_compressor.compression.pruner.model_slim", false]], "neural_compressor.compression.pruner.model_slim.auto_slim": [[171, "module-neural_compressor.compression.pruner.model_slim.auto_slim", false]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer": [[173, "module-neural_compressor.compression.pruner.model_slim.pattern_analyzer", false]], "neural_compressor.compression.pruner.model_slim.weight_slim": [[174, "module-neural_compressor.compression.pruner.model_slim.weight_slim", false]], "neural_compressor.compression.pruner.patterns": [[176, "module-neural_compressor.compression.pruner.patterns", false]], "neural_compressor.compression.pruner.patterns.base": [[175, "module-neural_compressor.compression.pruner.patterns.base", false]], "neural_compressor.compression.pruner.patterns.mha": [[177, "module-neural_compressor.compression.pruner.patterns.mha", false]], "neural_compressor.compression.pruner.patterns.ninm": [[178, "module-neural_compressor.compression.pruner.patterns.ninm", false]], "neural_compressor.compression.pruner.patterns.nxm": [[179, "module-neural_compressor.compression.pruner.patterns.nxm", false]], "neural_compressor.compression.pruner.pruners": [[183, "module-neural_compressor.compression.pruner.pruners", false]], "neural_compressor.compression.pruner.pruners.base": [[180, "module-neural_compressor.compression.pruner.pruners.base", false]], "neural_compressor.compression.pruner.pruners.basic": [[181, "module-neural_compressor.compression.pruner.pruners.basic", false]], "neural_compressor.compression.pruner.pruners.block_mask": [[182, "module-neural_compressor.compression.pruner.pruners.block_mask", false]], "neural_compressor.compression.pruner.pruners.mha": [[184, "module-neural_compressor.compression.pruner.pruners.mha", false]], "neural_compressor.compression.pruner.pruners.pattern_lock": [[185, "module-neural_compressor.compression.pruner.pruners.pattern_lock", false]], "neural_compressor.compression.pruner.pruners.progressive": [[186, "module-neural_compressor.compression.pruner.pruners.progressive", false]], "neural_compressor.compression.pruner.pruners.retrain_free": [[187, "module-neural_compressor.compression.pruner.pruners.retrain_free", false]], "neural_compressor.compression.pruner.pruning": [[188, "module-neural_compressor.compression.pruner.pruning", false]], "neural_compressor.compression.pruner.regs": [[189, "module-neural_compressor.compression.pruner.regs", false]], "neural_compressor.compression.pruner.schedulers": [[190, "module-neural_compressor.compression.pruner.schedulers", false]], "neural_compressor.compression.pruner.tf_criteria": [[191, "module-neural_compressor.compression.pruner.tf_criteria", false]], "neural_compressor.compression.pruner.utils": [[192, "module-neural_compressor.compression.pruner.utils", false]], "neural_compressor.compression.pruner.wanda": [[193, "module-neural_compressor.compression.pruner.wanda", false]], "neural_compressor.compression.pruner.wanda.utils": [[194, "module-neural_compressor.compression.pruner.wanda.utils", false]], "neural_compressor.config": [[195, "module-neural_compressor.config", false]], "neural_compressor.contrib": [[196, "module-neural_compressor.contrib", false]], "neural_compressor.contrib.strategy": [[197, "module-neural_compressor.contrib.strategy", false]], "neural_compressor.contrib.strategy.sigopt": [[198, "module-neural_compressor.contrib.strategy.sigopt", false]], "neural_compressor.contrib.strategy.tpe": [[199, "module-neural_compressor.contrib.strategy.tpe", false]], "neural_compressor.data": [[220, "module-neural_compressor.data", false]], "neural_compressor.data.dataloaders.base_dataloader": [[200, "module-neural_compressor.data.dataloaders.base_dataloader", false]], "neural_compressor.data.dataloaders.dataloader": [[201, "module-neural_compressor.data.dataloaders.dataloader", false]], "neural_compressor.data.dataloaders.default_dataloader": [[202, "module-neural_compressor.data.dataloaders.default_dataloader", false]], "neural_compressor.data.dataloaders.fetcher": [[203, "module-neural_compressor.data.dataloaders.fetcher", false]], "neural_compressor.data.dataloaders.mxnet_dataloader": [[204, "module-neural_compressor.data.dataloaders.mxnet_dataloader", false]], "neural_compressor.data.dataloaders.onnxrt_dataloader": [[205, "module-neural_compressor.data.dataloaders.onnxrt_dataloader", false]], "neural_compressor.data.dataloaders.pytorch_dataloader": [[206, "module-neural_compressor.data.dataloaders.pytorch_dataloader", false]], "neural_compressor.data.dataloaders.sampler": [[207, "module-neural_compressor.data.dataloaders.sampler", false]], "neural_compressor.data.dataloaders.tensorflow_dataloader": [[208, "module-neural_compressor.data.dataloaders.tensorflow_dataloader", false]], "neural_compressor.data.datasets": [[215, "module-neural_compressor.data.datasets", false]], "neural_compressor.data.datasets.bert_dataset": [[209, "module-neural_compressor.data.datasets.bert_dataset", false]], "neural_compressor.data.datasets.coco_dataset": [[210, "module-neural_compressor.data.datasets.coco_dataset", false]], "neural_compressor.data.datasets.dataset": [[211, "module-neural_compressor.data.datasets.dataset", false]], "neural_compressor.data.datasets.dummy_dataset": [[212, "module-neural_compressor.data.datasets.dummy_dataset", false]], "neural_compressor.data.datasets.dummy_dataset_v2": [[213, "module-neural_compressor.data.datasets.dummy_dataset_v2", false]], "neural_compressor.data.datasets.imagenet_dataset": [[214, "module-neural_compressor.data.datasets.imagenet_dataset", false]], "neural_compressor.data.datasets.style_transfer_dataset": [[216, "module-neural_compressor.data.datasets.style_transfer_dataset", false]], "neural_compressor.data.filters": [[219, "module-neural_compressor.data.filters", false]], "neural_compressor.data.filters.coco_filter": [[217, "module-neural_compressor.data.filters.coco_filter", false]], "neural_compressor.data.filters.filter": [[218, "module-neural_compressor.data.filters.filter", false]], "neural_compressor.data.transforms": [[222, "module-neural_compressor.data.transforms", false]], "neural_compressor.data.transforms.imagenet_transform": [[221, "module-neural_compressor.data.transforms.imagenet_transform", false]], "neural_compressor.data.transforms.postprocess": [[223, "module-neural_compressor.data.transforms.postprocess", false]], "neural_compressor.data.transforms.tokenization": [[224, "module-neural_compressor.data.transforms.tokenization", false]], "neural_compressor.data.transforms.transform": [[225, "module-neural_compressor.data.transforms.transform", false]], "neural_compressor.metric": [[233, "module-neural_compressor.metric", false]], "neural_compressor.metric.bleu": [[227, "module-neural_compressor.metric.bleu", false]], "neural_compressor.metric.bleu_util": [[228, "module-neural_compressor.metric.bleu_util", false]], "neural_compressor.metric.coco_label_map": [[229, "module-neural_compressor.metric.coco_label_map", false]], "neural_compressor.metric.coco_tools": [[230, "module-neural_compressor.metric.coco_tools", false]], "neural_compressor.metric.evaluate_squad": [[231, "module-neural_compressor.metric.evaluate_squad", false]], "neural_compressor.metric.f1": [[232, "module-neural_compressor.metric.f1", false]], "neural_compressor.metric.metric": [[234, "module-neural_compressor.metric.metric", false]], "neural_compressor.mix_precision": [[235, "module-neural_compressor.mix_precision", false]], "neural_compressor.model": [[237, "module-neural_compressor.model", false]], "neural_compressor.model.base_model": [[236, "module-neural_compressor.model.base_model", false]], "neural_compressor.model.keras_model": [[238, "module-neural_compressor.model.keras_model", false]], "neural_compressor.model.model": [[239, "module-neural_compressor.model.model", false]], "neural_compressor.model.mxnet_model": [[240, "module-neural_compressor.model.mxnet_model", false]], "neural_compressor.model.nets_factory": [[241, "module-neural_compressor.model.nets_factory", false]], "neural_compressor.model.onnx_model": [[242, "module-neural_compressor.model.onnx_model", false]], "neural_compressor.model.tensorflow_model": [[243, "module-neural_compressor.model.tensorflow_model", false]], "neural_compressor.model.torch_model": [[244, "module-neural_compressor.model.torch_model", false]], "neural_compressor.objective": [[245, "module-neural_compressor.objective", false]], "neural_compressor.profiling": [[246, "module-neural_compressor.profiling", false]], "neural_compressor.profiling.parser.factory": [[247, "module-neural_compressor.profiling.parser.factory", false]], "neural_compressor.profiling.parser.onnx_parser.factory": [[248, "module-neural_compressor.profiling.parser.onnx_parser.factory", false]], "neural_compressor.profiling.parser.onnx_parser.parser": [[249, "module-neural_compressor.profiling.parser.onnx_parser.parser", false]], "neural_compressor.profiling.parser.parser": [[250, "module-neural_compressor.profiling.parser.parser", false]], "neural_compressor.profiling.parser.result": [[251, "module-neural_compressor.profiling.parser.result", false]], "neural_compressor.profiling.parser.tensorflow_parser.factory": [[252, "module-neural_compressor.profiling.parser.tensorflow_parser.factory", false]], "neural_compressor.profiling.parser.tensorflow_parser.parser": [[253, "module-neural_compressor.profiling.parser.tensorflow_parser.parser", false]], "neural_compressor.profiling.profiler.factory": [[254, "module-neural_compressor.profiling.profiler.factory", false]], "neural_compressor.profiling.profiler.onnxrt_profiler.factory": [[255, "module-neural_compressor.profiling.profiler.onnxrt_profiler.factory", false]], "neural_compressor.profiling.profiler.onnxrt_profiler.profiler": [[256, "module-neural_compressor.profiling.profiler.onnxrt_profiler.profiler", false]], "neural_compressor.profiling.profiler.onnxrt_profiler.utils": [[257, "module-neural_compressor.profiling.profiler.onnxrt_profiler.utils", false]], "neural_compressor.profiling.profiler.profiler": [[258, "module-neural_compressor.profiling.profiler.profiler", false]], "neural_compressor.profiling.profiler.tensorflow_profiler.factory": [[259, "module-neural_compressor.profiling.profiler.tensorflow_profiler.factory", false]], "neural_compressor.profiling.profiler.tensorflow_profiler.profiler": [[260, "module-neural_compressor.profiling.profiler.tensorflow_profiler.profiler", false]], "neural_compressor.profiling.profiler.tensorflow_profiler.utils": [[261, "module-neural_compressor.profiling.profiler.tensorflow_profiler.utils", false]], "neural_compressor.quantization": [[262, "module-neural_compressor.quantization", false]], "neural_compressor.strategy": [[270, "module-neural_compressor.strategy", false]], "neural_compressor.strategy.auto": [[263, "module-neural_compressor.strategy.auto", false]], "neural_compressor.strategy.auto_mixed_precision": [[264, "module-neural_compressor.strategy.auto_mixed_precision", false]], "neural_compressor.strategy.basic": [[265, "module-neural_compressor.strategy.basic", false]], "neural_compressor.strategy.bayesian": [[266, "module-neural_compressor.strategy.bayesian", false]], "neural_compressor.strategy.conservative": [[267, "module-neural_compressor.strategy.conservative", false]], "neural_compressor.strategy.exhaustive": [[268, "module-neural_compressor.strategy.exhaustive", false]], "neural_compressor.strategy.hawq_v2": [[269, "module-neural_compressor.strategy.hawq_v2", false]], "neural_compressor.strategy.mse": [[271, "module-neural_compressor.strategy.mse", false]], "neural_compressor.strategy.mse_v2": [[272, "module-neural_compressor.strategy.mse_v2", false]], "neural_compressor.strategy.random": [[273, "module-neural_compressor.strategy.random", false]], "neural_compressor.strategy.strategy": [[274, "module-neural_compressor.strategy.strategy", false]], "neural_compressor.strategy.utils": [[276, "module-neural_compressor.strategy.utils", false]], "neural_compressor.strategy.utils.constant": [[275, "module-neural_compressor.strategy.utils.constant", false]], "neural_compressor.strategy.utils.tuning_sampler": [[277, "module-neural_compressor.strategy.utils.tuning_sampler", false]], "neural_compressor.strategy.utils.tuning_space": [[278, "module-neural_compressor.strategy.utils.tuning_space", false]], "neural_compressor.strategy.utils.tuning_structs": [[279, "module-neural_compressor.strategy.utils.tuning_structs", false]], "neural_compressor.strategy.utils.utility": [[280, "module-neural_compressor.strategy.utils.utility", false]], "neural_compressor.template.api_doc_example": [[281, "module-neural_compressor.template.api_doc_example", false]], "neural_compressor.tensorflow": [[290, "module-neural_compressor.tensorflow", false]], "neural_compressor.tensorflow.algorithms": [[282, "module-neural_compressor.tensorflow.algorithms", false]], "neural_compressor.tensorflow.algorithms.smoother": [[285, "module-neural_compressor.tensorflow.algorithms.smoother", false]], "neural_compressor.tensorflow.algorithms.smoother.calibration": [[283, "module-neural_compressor.tensorflow.algorithms.smoother.calibration", false]], "neural_compressor.tensorflow.algorithms.smoother.core": [[284, "module-neural_compressor.tensorflow.algorithms.smoother.core", false]], "neural_compressor.tensorflow.algorithms.smoother.scaler": [[286, "module-neural_compressor.tensorflow.algorithms.smoother.scaler", false]], "neural_compressor.tensorflow.algorithms.static_quant": [[287, "module-neural_compressor.tensorflow.algorithms.static_quant", false]], "neural_compressor.tensorflow.algorithms.static_quant.keras": [[288, "module-neural_compressor.tensorflow.algorithms.static_quant.keras", false]], "neural_compressor.tensorflow.algorithms.static_quant.tensorflow": [[289, "module-neural_compressor.tensorflow.algorithms.static_quant.tensorflow", false]], "neural_compressor.tensorflow.keras": [[291, "module-neural_compressor.tensorflow.keras", false]], "neural_compressor.tensorflow.keras.layers": [[295, "module-neural_compressor.tensorflow.keras.layers", false]], "neural_compressor.tensorflow.keras.layers.conv2d": [[292, "module-neural_compressor.tensorflow.keras.layers.conv2d", false]], "neural_compressor.tensorflow.keras.layers.dense": [[293, "module-neural_compressor.tensorflow.keras.layers.dense", false]], "neural_compressor.tensorflow.keras.layers.depthwise_conv2d": [[294, "module-neural_compressor.tensorflow.keras.layers.depthwise_conv2d", false]], "neural_compressor.tensorflow.keras.layers.layer_initializer": [[296, "module-neural_compressor.tensorflow.keras.layers.layer_initializer", false]], "neural_compressor.tensorflow.keras.layers.pool2d": [[297, "module-neural_compressor.tensorflow.keras.layers.pool2d", false]], "neural_compressor.tensorflow.keras.layers.separable_conv2d": [[298, "module-neural_compressor.tensorflow.keras.layers.separable_conv2d", false]], "neural_compressor.tensorflow.keras.quantization": [[300, "module-neural_compressor.tensorflow.keras.quantization", false]], "neural_compressor.tensorflow.keras.quantization.config": [[299, "module-neural_compressor.tensorflow.keras.quantization.config", false]], "neural_compressor.tensorflow.quantization": [[304, "module-neural_compressor.tensorflow.quantization", false]], "neural_compressor.tensorflow.quantization.algorithm_entry": [[301, "module-neural_compressor.tensorflow.quantization.algorithm_entry", false]], "neural_compressor.tensorflow.quantization.autotune": [[302, "module-neural_compressor.tensorflow.quantization.autotune", false]], "neural_compressor.tensorflow.quantization.config": [[303, "module-neural_compressor.tensorflow.quantization.config", false]], "neural_compressor.tensorflow.quantization.quantize": [[305, "module-neural_compressor.tensorflow.quantization.quantize", false]], "neural_compressor.tensorflow.quantization.utils": [[361, "module-neural_compressor.tensorflow.quantization.utils", false]], "neural_compressor.tensorflow.quantization.utils.graph_converter": [[306, "module-neural_compressor.tensorflow.quantization.utils.graph_converter", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter": [[344, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16": [[309, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert": [[307, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer": [[308, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic": [[333, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd": [[310, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout": [[311, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu": [[312, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random": [[313, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const": [[314, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction": [[315, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd": [[316, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer": [[317, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape": [[318, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm": [[319, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant": [[320, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add": [[321, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul": [[322, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math": [[323, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn": [[324, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in": [[325, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu": [[326, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm": [[327, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv": [[328, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv": [[329, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose": [[330, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer": [[331, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass": [[332, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node": [[334, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu": [[335, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize": [[336, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes": [[337, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm": [[338, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input": [[339, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes": [[340, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes": [[341, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer": [[342, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base": [[343, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8": [[351, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant": [[345, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value": [[346, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize": [[347, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize": [[348, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize": [[349, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize": [[350, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer": [[352, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter": [[353, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse": [[354, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation": [[355, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq": [[356, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern": [[357, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq": [[358, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq", false]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern": [[359, "module-neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern", false]], "neural_compressor.tensorflow.quantization.utils.graph_util": [[360, "module-neural_compressor.tensorflow.quantization.utils.graph_util", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph": [[362, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq": [[370, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn": [[363, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2": [[364, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv": [[365, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv": [[366, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in": [[367, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul": [[368, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling": [[369, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq": [[371, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base": [[372, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn": [[373, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2": [[374, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv": [[375, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu": [[376, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul": [[377, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling": [[378, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling", false]], "neural_compressor.tensorflow.quantization.utils.quantize_graph_common": [[379, "module-neural_compressor.tensorflow.quantization.utils.quantize_graph_common", false]], "neural_compressor.tensorflow.quantization.utils.transform_graph": [[382, "module-neural_compressor.tensorflow.quantization.utils.transform_graph", false]], "neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction": [[380, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction", false]], "neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base": [[381, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base", false]], "neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging": [[383, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging", false]], "neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat": [[384, "module-neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat", false]], "neural_compressor.tensorflow.quantization.utils.utility": [[385, "module-neural_compressor.tensorflow.quantization.utils.utility", false]], "neural_compressor.tensorflow.utils": [[388, "module-neural_compressor.tensorflow.utils", false]], "neural_compressor.tensorflow.utils.constants": [[386, "module-neural_compressor.tensorflow.utils.constants", false]], "neural_compressor.tensorflow.utils.data": [[387, "module-neural_compressor.tensorflow.utils.data", false]], "neural_compressor.tensorflow.utils.model": [[389, "module-neural_compressor.tensorflow.utils.model", false]], "neural_compressor.tensorflow.utils.model_wrappers": [[390, "module-neural_compressor.tensorflow.utils.model_wrappers", false]], "neural_compressor.tensorflow.utils.utility": [[391, "module-neural_compressor.tensorflow.utils.utility", false]], "neural_compressor.torch": [[436, "module-neural_compressor.torch", false]], "neural_compressor.torch.algorithms": [[394, "module-neural_compressor.torch.algorithms", false]], "neural_compressor.torch.algorithms.base_algorithm": [[392, "module-neural_compressor.torch.algorithms.base_algorithm", false]], "neural_compressor.torch.algorithms.fp8_quant.utils.logger": [[393, "module-neural_compressor.torch.algorithms.fp8_quant.utils.logger", false]], "neural_compressor.torch.algorithms.layer_wise": [[395, "module-neural_compressor.torch.algorithms.layer_wise", false]], "neural_compressor.torch.algorithms.layer_wise.load": [[396, "module-neural_compressor.torch.algorithms.layer_wise.load", false]], "neural_compressor.torch.algorithms.layer_wise.modified_pickle": [[397, "module-neural_compressor.torch.algorithms.layer_wise.modified_pickle", false]], "neural_compressor.torch.algorithms.layer_wise.utils": [[398, "module-neural_compressor.torch.algorithms.layer_wise.utils", false]], "neural_compressor.torch.algorithms.mixed_precision": [[400, "module-neural_compressor.torch.algorithms.mixed_precision", false]], "neural_compressor.torch.algorithms.mixed_precision.half_precision_convert": [[399, "module-neural_compressor.torch.algorithms.mixed_precision.half_precision_convert", false]], "neural_compressor.torch.algorithms.mixed_precision.module_wrappers": [[401, "module-neural_compressor.torch.algorithms.mixed_precision.module_wrappers", false]], "neural_compressor.torch.algorithms.mx_quant": [[402, "module-neural_compressor.torch.algorithms.mx_quant", false]], "neural_compressor.torch.algorithms.mx_quant.mx": [[403, "module-neural_compressor.torch.algorithms.mx_quant.mx", false]], "neural_compressor.torch.algorithms.mx_quant.utils": [[404, "module-neural_compressor.torch.algorithms.mx_quant.utils", false]], "neural_compressor.torch.algorithms.pt2e_quant": [[407, "module-neural_compressor.torch.algorithms.pt2e_quant", false]], "neural_compressor.torch.algorithms.pt2e_quant.core": [[405, "module-neural_compressor.torch.algorithms.pt2e_quant.core", false]], "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter": [[406, "module-neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter", false]], "neural_compressor.torch.algorithms.pt2e_quant.save_load": [[408, "module-neural_compressor.torch.algorithms.pt2e_quant.save_load", false]], "neural_compressor.torch.algorithms.pt2e_quant.utility": [[409, "module-neural_compressor.torch.algorithms.pt2e_quant.utility", false]], "neural_compressor.torch.algorithms.smooth_quant": [[410, "module-neural_compressor.torch.algorithms.smooth_quant", false]], "neural_compressor.torch.algorithms.smooth_quant.save_load": [[411, "module-neural_compressor.torch.algorithms.smooth_quant.save_load", false]], "neural_compressor.torch.algorithms.smooth_quant.smooth_quant": [[412, "module-neural_compressor.torch.algorithms.smooth_quant.smooth_quant", false]], "neural_compressor.torch.algorithms.smooth_quant.utility": [[413, "module-neural_compressor.torch.algorithms.smooth_quant.utility", false]], "neural_compressor.torch.algorithms.static_quant": [[414, "module-neural_compressor.torch.algorithms.static_quant", false]], "neural_compressor.torch.algorithms.static_quant.save_load": [[415, "module-neural_compressor.torch.algorithms.static_quant.save_load", false]], "neural_compressor.torch.algorithms.static_quant.static_quant": [[416, "module-neural_compressor.torch.algorithms.static_quant.static_quant", false]], "neural_compressor.torch.algorithms.static_quant.utility": [[417, "module-neural_compressor.torch.algorithms.static_quant.utility", false]], "neural_compressor.torch.algorithms.weight_only": [[428, "module-neural_compressor.torch.algorithms.weight_only", false]], "neural_compressor.torch.algorithms.weight_only.autoround": [[418, "module-neural_compressor.torch.algorithms.weight_only.autoround", false]], "neural_compressor.torch.algorithms.weight_only.awq": [[419, "module-neural_compressor.torch.algorithms.weight_only.awq", false]], "neural_compressor.torch.algorithms.weight_only.gptq": [[420, "module-neural_compressor.torch.algorithms.weight_only.gptq", false]], "neural_compressor.torch.algorithms.weight_only.hqq": [[424, "module-neural_compressor.torch.algorithms.weight_only.hqq", false]], "neural_compressor.torch.algorithms.weight_only.hqq.bitpack": [[421, "module-neural_compressor.torch.algorithms.weight_only.hqq.bitpack", false]], "neural_compressor.torch.algorithms.weight_only.hqq.config": [[422, "module-neural_compressor.torch.algorithms.weight_only.hqq.config", false]], "neural_compressor.torch.algorithms.weight_only.hqq.core": [[423, "module-neural_compressor.torch.algorithms.weight_only.hqq.core", false]], "neural_compressor.torch.algorithms.weight_only.hqq.optimizer": [[425, "module-neural_compressor.torch.algorithms.weight_only.hqq.optimizer", false]], "neural_compressor.torch.algorithms.weight_only.hqq.qtensor": [[426, "module-neural_compressor.torch.algorithms.weight_only.hqq.qtensor", false]], "neural_compressor.torch.algorithms.weight_only.hqq.quantizer": [[427, "module-neural_compressor.torch.algorithms.weight_only.hqq.quantizer", false]], "neural_compressor.torch.algorithms.weight_only.modules": [[429, "module-neural_compressor.torch.algorithms.weight_only.modules", false]], "neural_compressor.torch.algorithms.weight_only.rtn": [[430, "module-neural_compressor.torch.algorithms.weight_only.rtn", false]], "neural_compressor.torch.algorithms.weight_only.save_load": [[431, "module-neural_compressor.torch.algorithms.weight_only.save_load", false]], "neural_compressor.torch.algorithms.weight_only.teq": [[432, "module-neural_compressor.torch.algorithms.weight_only.teq", false]], "neural_compressor.torch.algorithms.weight_only.utility": [[433, "module-neural_compressor.torch.algorithms.weight_only.utility", false]], "neural_compressor.torch.export": [[434, "module-neural_compressor.torch.export", false]], "neural_compressor.torch.export.pt2e_export": [[435, "module-neural_compressor.torch.export.pt2e_export", false]], "neural_compressor.torch.quantization": [[440, "module-neural_compressor.torch.quantization", false]], "neural_compressor.torch.quantization.algorithm_entry": [[437, "module-neural_compressor.torch.quantization.algorithm_entry", false]], "neural_compressor.torch.quantization.autotune": [[438, "module-neural_compressor.torch.quantization.autotune", false]], "neural_compressor.torch.quantization.config": [[439, "module-neural_compressor.torch.quantization.config", false]], "neural_compressor.torch.quantization.load_entry": [[441, "module-neural_compressor.torch.quantization.load_entry", false]], "neural_compressor.torch.quantization.quantize": [[442, "module-neural_compressor.torch.quantization.quantize", false]], "neural_compressor.torch.utils": [[446, "module-neural_compressor.torch.utils", false]], "neural_compressor.torch.utils.auto_accelerator": [[443, "module-neural_compressor.torch.utils.auto_accelerator", false]], "neural_compressor.torch.utils.constants": [[444, "module-neural_compressor.torch.utils.constants", false]], "neural_compressor.torch.utils.environ": [[445, "module-neural_compressor.torch.utils.environ", false]], "neural_compressor.torch.utils.utility": [[447, "module-neural_compressor.torch.utils.utility", false]], "neural_compressor.training": [[448, "module-neural_compressor.training", false]], "neural_compressor.transformers.quantization.utils": [[449, "module-neural_compressor.transformers.quantization.utils", false]], "neural_compressor.transformers.utils": [[450, "module-neural_compressor.transformers.utils", false]], "neural_compressor.transformers.utils.quantization_config": [[451, "module-neural_compressor.transformers.utils.quantization_config", false]], "neural_compressor.utils": [[459, "module-neural_compressor.utils", false]], "neural_compressor.utils.collect_layer_histogram": [[452, "module-neural_compressor.utils.collect_layer_histogram", false]], "neural_compressor.utils.constant": [[453, "module-neural_compressor.utils.constant", false]], "neural_compressor.utils.create_obj_from_config": [[454, "module-neural_compressor.utils.create_obj_from_config", false]], "neural_compressor.utils.export": [[455, "module-neural_compressor.utils.export", false]], "neural_compressor.utils.export.qlinear2qdq": [[456, "module-neural_compressor.utils.export.qlinear2qdq", false]], "neural_compressor.utils.export.tf2onnx": [[457, "module-neural_compressor.utils.export.tf2onnx", false]], "neural_compressor.utils.export.torch2onnx": [[458, "module-neural_compressor.utils.export.torch2onnx", false]], "neural_compressor.utils.kl_divergence": [[460, "module-neural_compressor.utils.kl_divergence", false]], "neural_compressor.utils.load_huggingface": [[461, "module-neural_compressor.utils.load_huggingface", false]], "neural_compressor.utils.logger": [[462, "module-neural_compressor.utils.logger", false]], "neural_compressor.utils.options": [[463, "module-neural_compressor.utils.options", false]], "neural_compressor.utils.pytorch": [[464, "module-neural_compressor.utils.pytorch", false]], "neural_compressor.utils.utility": [[465, "module-neural_compressor.utils.utility", false]], "neural_compressor.utils.weights_details": [[466, "module-neural_compressor.utils.weights_details", false]], "neural_compressor.version": [[467, "module-neural_compressor.version", false]], "node_collector (class in neural_compressor.adaptor.torch_utils.hawq_metric)": [[135, "neural_compressor.adaptor.torch_utils.hawq_metric.Node_collector", false]], "node_from_map() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.node_from_map", false]], "node_from_map() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.node_from_map", false]], "node_from_map() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm)": [[55, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm.node_from_map", false]], "node_from_map() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.node_from_map", false]], "node_from_map() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.node_from_map", false]], "node_from_map() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm)": [[327, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm.node_from_map", false]], "node_name_from_input() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.node_name_from_input", false]], "node_name_from_input() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.node_name_from_input", false]], "node_name_from_input() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm)": [[55, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm.node_name_from_input", false]], "node_name_from_input() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.node_name_from_input", false]], "node_name_from_input() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.node_name_from_input", false]], "node_name_from_input() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm)": [[327, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm.node_name_from_input", false]], "nondigit_punct_re (neural_compressor.metric.bleu.unicoderegex attribute)": [[227, "neural_compressor.metric.bleu.UnicodeRegex.nondigit_punct_re", false]], "normalizationoperator (class in neural_compressor.adaptor.ox_utils.operators.norm)": [[20, "neural_compressor.adaptor.ox_utils.operators.norm.NormalizationOperator", false]], "normalize_answer() (in module neural_compressor.metric.f1)": [[232, "neural_compressor.metric.f1.normalize_answer", false]], "normalizetftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.NormalizeTFTransform", false]], "normalizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.NormalizeTransform", false]], "num_correct (neural_compressor.metric.metric.generaltopk attribute)": [[234, "neural_compressor.metric.metric.GeneralTopK.num_correct", false]], "num_correct (neural_compressor.metric.metric.tensorflowtopk attribute)": [[234, "neural_compressor.metric.metric.TensorflowTopK.num_correct", false]], "num_sample (neural_compressor.metric.metric.generaltopk attribute)": [[234, "neural_compressor.metric.metric.GeneralTopK.num_sample", false]], "num_sample (neural_compressor.metric.metric.tensorflowtopk attribute)": [[234, "neural_compressor.metric.metric.TensorflowTopK.num_sample", false]], "objective (class in neural_compressor.objective)": [[245, "neural_compressor.objective.Objective", false]], "objective_custom_registry() (in module neural_compressor.objective)": [[245, "neural_compressor.objective.objective_custom_registry", false]], "objective_registry() (in module neural_compressor.objective)": [[245, "neural_compressor.objective.objective_registry", false]], "oneshotscheduler (class in neural_compressor.compression.pruner.schedulers)": [[190, "neural_compressor.compression.pruner.schedulers.OneshotScheduler", false]], "onnx (class in neural_compressor.config)": [[195, "neural_compressor.config.ONNX", false]], "onnx_qlinear_to_qdq() (in module neural_compressor.utils.export.qlinear2qdq)": [[456, "neural_compressor.utils.export.qlinear2qdq.onnx_qlinear_to_qdq", false]], "onnxbilinearimagenettransform (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.OnnxBilinearImagenetTransform", false]], "onnxgraph (class in neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph)": [[87, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph.OnnxGraph", false]], "onnxmodel (class in neural_compressor.model.onnx_model)": [[242, "neural_compressor.model.onnx_model.ONNXModel", false]], "onnxnode (class in neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node)": [[88, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node.OnnxNode", false]], "onnxopschema (class in neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema)": [[89, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema.OnnxOpSchema", false]], "onnxprofilingparser (class in neural_compressor.profiling.parser.onnx_parser.parser)": [[249, "neural_compressor.profiling.parser.onnx_parser.parser.OnnxProfilingParser", false]], "onnxqlinear2qdqconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.ONNXQlinear2QDQConfig", false]], "onnxresizecropimagenettransform (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.ONNXResizeCropImagenetTransform", false]], "onnxrt (class in neural_compressor.utils.options)": [[463, "neural_compressor.utils.options.onnxrt", false]], "onnxrtaugment (class in neural_compressor.adaptor.ox_utils.calibration)": [[2, "neural_compressor.adaptor.ox_utils.calibration.ONNXRTAugment", false]], "onnxrtbertdataloader (class in neural_compressor.data.dataloaders.onnxrt_dataloader)": [[205, "neural_compressor.data.dataloaders.onnxrt_dataloader.ONNXRTBertDataLoader", false]], "onnxrtbertdataset (class in neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.ONNXRTBertDataset", false]], "onnxrtcroptoboundingbox (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ONNXRTCropToBoundingBox", false]], "onnxrtdataloader (class in neural_compressor.data.dataloaders.onnxrt_dataloader)": [[205, "neural_compressor.data.dataloaders.onnxrt_dataloader.ONNXRTDataLoader", false]], "onnxrtglue (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.ONNXRTGLUE", false]], "onnxrtimagenetdataset (class in neural_compressor.data.datasets.imagenet_dataset)": [[214, "neural_compressor.data.datasets.imagenet_dataset.ONNXRTImagenetDataset", false]], "onnxrtitdatasets (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.ONNXRTITDatasets", false]], "onnxrtitfilters (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.ONNXRTITFilters", false]], "onnxrtitmetrics (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.ONNXRTITMetrics", false]], "onnxrtittransforms (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ONNXRTITTransforms", false]], "onnxrtparserfactory (class in neural_compressor.profiling.parser.onnx_parser.factory)": [[248, "neural_compressor.profiling.parser.onnx_parser.factory.OnnxrtParserFactory", false]], "onnxrtqldatasets (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.ONNXRTQLDatasets", false]], "onnxrtqlfilters (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.ONNXRTQLFilters", false]], "onnxrtqlmetrics (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.ONNXRTQLMetrics", false]], "onnxrtqltransforms (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ONNXRTQLTransforms", false]], "op_level (neural_compressor.common.tuning_param.paramlevel attribute)": [[156, "neural_compressor.common.tuning_param.ParamLevel.OP_LEVEL", false]], "op_registry() (in module neural_compressor.adaptor.ox_utils.operators.ops)": [[21, "neural_compressor.adaptor.ox_utils.operators.ops.op_registry", false]], "op_type_level (neural_compressor.common.tuning_param.paramlevel attribute)": [[156, "neural_compressor.common.tuning_param.ParamLevel.OP_TYPE_LEVEL", false]], "opentry (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.OpEntry", false]], "operator (class in neural_compressor.adaptor.ox_utils.operators.ops)": [[21, "neural_compressor.adaptor.ox_utils.operators.ops.Operator", false]], "operatorconfig (class in neural_compressor.tensorflow.keras.quantization.config)": [[299, "neural_compressor.tensorflow.keras.quantization.config.OperatorConfig", false]], "operatorconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.OperatorConfig", false]], "optimize_weights_proximal_legacy() (in module neural_compressor.torch.algorithms.weight_only.hqq.optimizer)": [[425, "neural_compressor.torch.algorithms.weight_only.hqq.optimizer.optimize_weights_proximal_legacy", false]], "optimizedmodel (class in neural_compressor.utils.load_huggingface)": [[461, "neural_compressor.utils.load_huggingface.OptimizedModel", false]], "optimizeqdqgraph (class in neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq)": [[116, "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq.OptimizeQDQGraph", false]], "optimizeqdqgraph (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq)": [[371, "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq.OptimizeQDQGraph", false]], "optimizer_registry() (in module neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.optimizer_registry", false]], "optimizers (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.Optimizers", false]], "options (class in neural_compressor.config)": [[195, "neural_compressor.config.Options", false]], "optuningconfig (class in neural_compressor.strategy.utils.tuning_structs)": [[279, "neural_compressor.strategy.utils.tuning_structs.OpTuningConfig", false]], "optype (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.OpType", false]], "optypewisetuningsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.OpTypeWiseTuningSampler", false]], "opwisetuningsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.OpWiseTuningSampler", false]], "ordereddefaultdict (class in neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.OrderedDefaultDict", false]], "ortsmoothquant (class in neural_compressor.adaptor.ox_utils.smooth_quant)": [[29, "neural_compressor.adaptor.ox_utils.smooth_quant.ORTSmoothQuant", false]], "packer (class in neural_compressor.torch.algorithms.weight_only.hqq.bitpack)": [[421, "neural_compressor.torch.algorithms.weight_only.hqq.bitpack.Packer", false]], "packing (neural_compressor.torch.algorithms.weight_only.hqq.qtensor.qtensormetainfo attribute)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo.packing", false]], "pad_tensor() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.pad_tensor", false]], "paddedcentercroptransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PaddedCenterCropTransform", false]], "padoperator (class in neural_compressor.adaptor.ox_utils.operators.pad)": [[22, "neural_compressor.adaptor.ox_utils.operators.pad.PadOperator", false]], "paramlevel (class in neural_compressor.common.tuning_param)": [[156, "neural_compressor.common.tuning_param.ParamLevel", false]], "params_list (neural_compressor.common.base_config.baseconfig attribute)": [[152, "neural_compressor.common.base_config.BaseConfig.params_list", false]], "parse_auto_slim_config() (in module neural_compressor.compression.pruner.model_slim.auto_slim)": [[171, "neural_compressor.compression.pruner.model_slim.auto_slim.parse_auto_slim_config", false]], "parse_cfgs() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.parse_cfgs", false]], "parse_last_linear() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.parse_last_linear", false]], "parse_last_linear_tf() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.parse_last_linear_tf", false]], "parse_saved_model() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.parse_saved_model", false]], "parse_saved_model() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.parse_saved_model", false]], "parse_str2list() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.parse_str2list", false]], "parse_to_prune() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.parse_to_prune", false]], "parse_to_prune_tf() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.parse_to_prune_tf", false]], "parse_tune_config() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.parse_tune_config", false]], "parse_valid_pruner_types() (in module neural_compressor.compression.pruner.pruners)": [[183, "neural_compressor.compression.pruner.pruners.parse_valid_pruner_types", false]], "parsedecodebert (class in neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.ParseDecodeBert", false]], "parsedecodecoco (class in neural_compressor.data.datasets.coco_dataset)": [[210, "neural_compressor.data.datasets.coco_dataset.ParseDecodeCoco", false]], "parsedecodeimagenet (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.ParseDecodeImagenet", false]], "parsedecodeimagenettransform (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.ParseDecodeImagenetTransform", false]], "parsedecodevoctransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ParseDecodeVocTransform", false]], "parserfactory (class in neural_compressor.profiling.parser.factory)": [[247, "neural_compressor.profiling.parser.factory.ParserFactory", false]], "paser_cfgs() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.paser_cfgs", false]], "patch_hqq_moduile() (in module neural_compressor.torch.algorithms.weight_only.hqq.quantizer)": [[427, "neural_compressor.torch.algorithms.weight_only.hqq.quantizer.patch_hqq_moduile", false]], "pattern (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.pattern", false]], "pattern (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.pattern", false]], "pattern (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.basic.kerasbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.KerasBasicPruner.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.basic.pytorchbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.PytorchBasicPruner.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.block_mask.pytorchblockmaskpruner attribute)": [[182, "neural_compressor.compression.pruner.pruners.block_mask.PytorchBlockMaskPruner.pattern", false]], "pattern (neural_compressor.compression.pruner.pruners.retrain_free.pytorchretrainfreepruner attribute)": [[187, "neural_compressor.compression.pruner.pruners.retrain_free.PytorchRetrainFreePruner.pattern", false]], "pattern_factory() (in module neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.pattern_factory", false]], "pattern_to_internal() (in module neural_compressor.strategy.utils.tuning_space)": [[278, "neural_compressor.strategy.utils.tuning_space.pattern_to_internal", false]], "pattern_to_path() (in module neural_compressor.strategy.utils.tuning_space)": [[278, "neural_compressor.strategy.utils.tuning_space.pattern_to_path", false]], "patternmha (class in neural_compressor.compression.pruner.patterns.mha)": [[177, "neural_compressor.compression.pruner.patterns.mha.PatternMHA", false]], "patternpair (class in neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.PatternPair", false]], "percentilecalibrator (class in neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.PercentileCalibrator", false]], "performance (class in neural_compressor.objective)": [[245, "neural_compressor.objective.Performance", false]], "pickleerror": [[138, "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle.PickleError", false], [397, "neural_compressor.torch.algorithms.layer_wise.modified_pickle.PickleError", false]], "picklingerror": [[138, "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle.PicklingError", false], [397, "neural_compressor.torch.algorithms.layer_wise.modified_pickle.PicklingError", false]], "pooloperator (class in neural_compressor.adaptor.ox_utils.operators.pooling)": [[23, "neural_compressor.adaptor.ox_utils.operators.pooling.PoolOperator", false]], "postcompressionutils (class in neural_compressor.compression.pruner.model_slim.weight_slim)": [[174, "neural_compressor.compression.pruner.model_slim.weight_slim.PostCompressionUtils", false]], "postcseoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse)": [[83, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse.PostCseOptimizer", false]], "postcseoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse)": [[354, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse.PostCseOptimizer", false]], "posthostconstconverter (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter)": [[82, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter.PostHostConstConverter", false]], "posthostconstconverter (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter)": [[353, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter.PostHostConstConverter", false]], "postprocess (class in neural_compressor.data.transforms.postprocess)": [[223, "neural_compressor.data.transforms.postprocess.Postprocess", false]], "postprocess_model() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.postprocess_model", false]], "posttrainingquantconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.PostTrainingQuantConfig", false]], "pred_list (neural_compressor.metric.metric.accuracy attribute)": [[234, "neural_compressor.metric.metric.Accuracy.pred_list", false]], "pred_list (neural_compressor.metric.metric.mae attribute)": [[234, "neural_compressor.metric.metric.MAE.pred_list", false]], "pred_list (neural_compressor.metric.metric.mse attribute)": [[234, "neural_compressor.metric.metric.MSE.pred_list", false]], "predictions (neural_compressor.metric.bleu.bleu attribute)": [[227, "neural_compressor.metric.bleu.BLEU.predictions", false]], "preoptimization (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize)": [[64, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize.PreOptimization", false]], "preoptimization (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize)": [[336, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize.PreOptimization", false]], "prepare() (in module neural_compressor.torch.quantization.quantize)": [[442, "neural_compressor.torch.quantization.quantize.prepare", false]], "prepare_compression() (in module neural_compressor.training)": [[448, "neural_compressor.training.prepare_compression", false]], "prepare_dataloader() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.prepare_dataloader", false]], "prepare_inputs() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.prepare_inputs", false]], "prepare_model() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.prepare_model", false]], "prepare_model_data() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.prepare_model_data", false]], "prepare_pruning() (in module neural_compressor.compression.pruner)": [[170, "neural_compressor.compression.pruner.prepare_pruning", false]], "preprocess_user_cfg() (in module neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.preprocess_user_cfg", false]], "print_iterables() (in module neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.print_iterables", false]], "print_op_list() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.print_op_list", false]], "print_table() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.print_table", false]], "process_and_check_config() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.process_and_check_config", false]], "process_config() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.process_config", false]], "process_weight_config() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.process_weight_config", false]], "process_yaml_config() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.process_yaml_config", false]], "processortype (class in neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.ProcessorType", false]], "profile() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.profile", false]], "profiler (class in neural_compressor.profiling.profiler.onnxrt_profiler.profiler)": [[256, "neural_compressor.profiling.profiler.onnxrt_profiler.profiler.Profiler", false]], "profiler (class in neural_compressor.profiling.profiler.profiler)": [[258, "neural_compressor.profiling.profiler.profiler.Profiler", false]], "profiler (class in neural_compressor.profiling.profiler.tensorflow_profiler.profiler)": [[260, "neural_compressor.profiling.profiler.tensorflow_profiler.profiler.Profiler", false]], "profilerfactory (class in neural_compressor.profiling.profiler.factory)": [[254, "neural_compressor.profiling.profiler.factory.ProfilerFactory", false]], "profilerfactory (class in neural_compressor.profiling.profiler.onnxrt_profiler.factory)": [[255, "neural_compressor.profiling.profiler.onnxrt_profiler.factory.ProfilerFactory", false]], "profilerfactory (class in neural_compressor.profiling.profiler.tensorflow_profiler.factory)": [[259, "neural_compressor.profiling.profiler.tensorflow_profiler.factory.ProfilerFactory", false]], "profilingparser (class in neural_compressor.profiling.parser.parser)": [[250, "neural_compressor.profiling.parser.parser.ProfilingParser", false]], "profilingresult (class in neural_compressor.profiling.parser.result)": [[251, "neural_compressor.profiling.parser.result.ProfilingResult", false]], "pruner_info (neural_compressor.compression.pruner.pruning.basepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasePruning.pruner_info", false]], "pruner_info (neural_compressor.compression.pruner.pruning.basicpruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasicPruning.pruner_info", false]], "pruner_info (neural_compressor.compression.pruner.pruning.retrainfreepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.RetrainFreePruning.pruner_info", false]], "pruners (neural_compressor.compression.pruner.pruning.basepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasePruning.pruners", false]], "pruners (neural_compressor.compression.pruner.pruning.basicpruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.BasicPruning.pruners", false]], "pruners (neural_compressor.compression.pruner.pruning.retrainfreepruning attribute)": [[188, "neural_compressor.compression.pruner.pruning.RetrainFreePruning.pruners", false]], "pruning_frequency (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.pruning_frequency", false]], "pruning_frequency (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.pruning_frequency", false]], "pruning_frequency (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.pruning_frequency", false]], "pruningcallbacks (class in neural_compressor.compression.callbacks)": [[162, "neural_compressor.compression.callbacks.PruningCallbacks", false]], "pruningcriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.PruningCriterion", false]], "pruningcriterion (class in neural_compressor.compression.pruner.tf_criteria)": [[191, "neural_compressor.compression.pruner.tf_criteria.PruningCriterion", false]], "pruningscheduler (class in neural_compressor.compression.pruner.schedulers)": [[190, "neural_compressor.compression.pruner.schedulers.PruningScheduler", false]], "pt2e_dynamic_quant_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.pt2e_dynamic_quant_entry", false]], "pt2e_static_quant_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.pt2e_static_quant_entry", false]], "punct_nondigit_re (neural_compressor.metric.bleu.unicoderegex attribute)": [[227, "neural_compressor.metric.bleu.UnicodeRegex.punct_nondigit_re", false]], "pythonmultiheadattentionpruner (class in neural_compressor.compression.pruner.pruners.mha)": [[184, "neural_compressor.compression.pruner.pruners.mha.PythonMultiheadAttentionPruner", false]], "pytorch (class in neural_compressor.config)": [[195, "neural_compressor.config.PyTorch", false]], "pytorchalignimagechannel (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PyTorchAlignImageChannel", false]], "pytorchbasemodel (class in neural_compressor.model.torch_model)": [[244, "neural_compressor.model.torch_model.PyTorchBaseModel", false]], "pytorchbasepattern (class in neural_compressor.compression.pruner.patterns.base)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern", false]], "pytorchbasepruner (class in neural_compressor.compression.pruner.pruners.base)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner", false]], "pytorchbasicpruner (class in neural_compressor.compression.pruner.pruners.basic)": [[181, "neural_compressor.compression.pruner.pruners.basic.PytorchBasicPruner", false]], "pytorchbertdataset (class in neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.PytorchBertDataset", false]], "pytorchblockmaskpruner (class in neural_compressor.compression.pruner.pruners.block_mask)": [[182, "neural_compressor.compression.pruner.pruners.block_mask.PytorchBlockMaskPruner", false]], "pytorchcifar10 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PytorchCIFAR10", false]], "pytorchcifar100 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PytorchCIFAR100", false]], "pytorchcriterions (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchCriterions", false]], "pytorchcropresizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PyTorchCropResizeTransform", false]], "pytorchcrossentropyloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchCrossEntropyLoss", false]], "pytorchdataloader (class in neural_compressor.data.dataloaders.pytorch_dataloader)": [[206, "neural_compressor.data.dataloaders.pytorch_dataloader.PyTorchDataLoader", false]], "pytorchdatasets (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PyTorchDatasets", false]], "pytorchfashionmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PytorchFashionMNIST", false]], "pytorchfilters (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.PyTorchFilters", false]], "pytorchfxmodel (class in neural_compressor.model.torch_model)": [[244, "neural_compressor.model.torch_model.PyTorchFXModel", false]], "pytorchimagenetraw (class in neural_compressor.data.datasets.imagenet_dataset)": [[214, "neural_compressor.data.datasets.imagenet_dataset.PytorchImagenetRaw", false]], "pytorchintermediatelayersknowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchIntermediateLayersKnowledgeDistillationLoss", false]], "pytorchintermediatelayersknowledgedistillationlosswrapper (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchIntermediateLayersKnowledgeDistillationLossWrapper", false]], "pytorchknowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchKnowledgeDistillationLoss", false]], "pytorchknowledgedistillationlosswrapper (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchKnowledgeDistillationLossWrapper", false]], "pytorchloss (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.PyTorchLoss", false]], "pytorchmetrics (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.PyTorchMetrics", false]], "pytorchmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PytorchMNIST", false]], "pytorchmodel (class in neural_compressor.model.torch_model)": [[244, "neural_compressor.model.torch_model.PyTorchModel", false]], "pytorchmxnettransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PytorchMxnetTransform", false]], "pytorchmxnetwrapdataset (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PytorchMxnetWrapDataset", false]], "pytorchmxnetwrapfunction (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.PytorchMxnetWrapFunction", false]], "pytorchmxnetwrapfunction (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PytorchMxnetWrapFunction", false]], "pytorchnormalizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PyTorchNormalizeTransform", false]], "pytorchoptimizers (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.PyTorchOptimizers", false]], "pytorchpatternlockpruner (class in neural_compressor.compression.pruner.pruners.pattern_lock)": [[185, "neural_compressor.compression.pruner.pruners.pattern_lock.PytorchPatternLockPruner", false]], "pytorchpatternninm (class in neural_compressor.compression.pruner.patterns.ninm)": [[178, "neural_compressor.compression.pruner.patterns.ninm.PytorchPatternNInM", false]], "pytorchpatternnxm (class in neural_compressor.compression.pruner.patterns.nxm)": [[179, "neural_compressor.compression.pruner.patterns.nxm.PytorchPatternNxM", false]], "pytorchprogressivepruner (class in neural_compressor.compression.pruner.pruners.progressive)": [[186, "neural_compressor.compression.pruner.pruners.progressive.PytorchProgressivePruner", false]], "pytorchretrainfreepruner (class in neural_compressor.compression.pruner.pruners.retrain_free)": [[187, "neural_compressor.compression.pruner.pruners.retrain_free.PytorchRetrainFreePruner", false]], "pytorchselfknowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchSelfKnowledgeDistillationLoss", false]], "pytorchselfknowledgedistillationlosswrapper (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.PyTorchSelfKnowledgeDistillationLossWrapper", false]], "pytorchsgd (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.PyTorchSGD", false]], "pytorchtransforms (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PyTorchTransforms", false]], "pytorchtranspose (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.PyTorchTranspose", false]], "qactivationoperator (class in neural_compressor.adaptor.ox_utils.operators.activation)": [[5, "neural_compressor.adaptor.ox_utils.operators.activation.QActivationOperator", false]], "qargmaxoperator (class in neural_compressor.adaptor.ox_utils.operators.argmax)": [[6, "neural_compressor.adaptor.ox_utils.operators.argmax.QArgMaxOperator", false]], "qat_clone_function() (in module neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper)": [[101, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper.qat_clone_function", false]], "qattentionoperator (class in neural_compressor.adaptor.ox_utils.operators.attention)": [[7, "neural_compressor.adaptor.ox_utils.operators.attention.QAttentionOperator", false]], "qavgpool2d (class in neural_compressor.tensorflow.keras.layers.pool2d)": [[297, "neural_compressor.tensorflow.keras.layers.pool2d.QAvgPool2D", false]], "qbinaryoperator (class in neural_compressor.adaptor.ox_utils.operators.binary_op)": [[8, "neural_compressor.adaptor.ox_utils.operators.binary_op.QBinaryOperator", false]], "qconcatoperator (class in neural_compressor.adaptor.ox_utils.operators.concat)": [[9, "neural_compressor.adaptor.ox_utils.operators.concat.QConcatOperator", false]], "qconv2d (class in neural_compressor.tensorflow.keras.layers.conv2d)": [[292, "neural_compressor.tensorflow.keras.layers.conv2d.QConv2D", false]], "qconvoperator (class in neural_compressor.adaptor.ox_utils.operators.conv)": [[10, "neural_compressor.adaptor.ox_utils.operators.conv.QConvOperator", false]], "qdense (class in neural_compressor.tensorflow.keras.layers.dense)": [[293, "neural_compressor.tensorflow.keras.layers.dense.QDense", false]], "qdepthwiseconv2d (class in neural_compressor.tensorflow.keras.layers.depthwise_conv2d)": [[294, "neural_compressor.tensorflow.keras.layers.depthwise_conv2d.QDepthwiseConv2D", false]], "qdirectoperator (class in neural_compressor.adaptor.ox_utils.operators.direct_q8)": [[11, "neural_compressor.adaptor.ox_utils.operators.direct_q8.QDirectOperator", false]], "qdq_quantize() (in module neural_compressor.torch.algorithms.smooth_quant.smooth_quant)": [[412, "neural_compressor.torch.algorithms.smooth_quant.smooth_quant.qdq_quantize", false]], "qdq_tensor() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.qdq_tensor", false]], "qdq_weight_actor() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.qdq_weight_actor", false]], "qdq_weight_asym() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.qdq_weight_asym", false]], "qdq_weight_sym() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.qdq_weight_sym", false]], "qdqlayer (class in neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.QDQLayer", false]], "qdqlayer (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.QDQLayer", false]], "qembedlayernormalizationoperator (class in neural_compressor.adaptor.ox_utils.operators.embed_layernorm)": [[12, "neural_compressor.adaptor.ox_utils.operators.embed_layernorm.QEmbedLayerNormalizationOperator", false]], "qgatheroperator (class in neural_compressor.adaptor.ox_utils.operators.gather)": [[13, "neural_compressor.adaptor.ox_utils.operators.gather.QGatherOperator", false]], "qgemmoperator (class in neural_compressor.adaptor.ox_utils.operators.gemm)": [[15, "neural_compressor.adaptor.ox_utils.operators.gemm.QGemmOperator", false]], "qglobalaveragepooloperator (class in neural_compressor.adaptor.ox_utils.operators.gavgpool)": [[14, "neural_compressor.adaptor.ox_utils.operators.gavgpool.QGlobalAveragePoolOperator", false]], "qmatmuloperator (class in neural_compressor.adaptor.ox_utils.operators.matmul)": [[18, "neural_compressor.adaptor.ox_utils.operators.matmul.QMatMulOperator", false]], "qmaxpool2d (class in neural_compressor.tensorflow.keras.layers.pool2d)": [[297, "neural_compressor.tensorflow.keras.layers.pool2d.QMaxPool2D", false]], "qmaxpooloperator (class in neural_compressor.adaptor.ox_utils.operators.maxpool)": [[19, "neural_compressor.adaptor.ox_utils.operators.maxpool.QMaxPoolOperator", false]], "qop_registry() (in module neural_compressor.adaptor.ox_utils.operators.ops)": [[21, "neural_compressor.adaptor.ox_utils.operators.ops.qop_registry", false]], "qoperator (class in neural_compressor.adaptor.ox_utils.operators.ops)": [[21, "neural_compressor.adaptor.ox_utils.operators.ops.QOperator", false]], "qpadoperator (class in neural_compressor.adaptor.ox_utils.operators.pad)": [[22, "neural_compressor.adaptor.ox_utils.operators.pad.QPadOperator", false]], "qpooloperator (class in neural_compressor.adaptor.ox_utils.operators.pooling)": [[23, "neural_compressor.adaptor.ox_utils.operators.pooling.QPoolOperator", false]], "qresizeoperator (class in neural_compressor.adaptor.ox_utils.operators.resize)": [[25, "neural_compressor.adaptor.ox_utils.operators.resize.QResizeOperator", false]], "qseparableconv2d (class in neural_compressor.tensorflow.keras.layers.separable_conv2d)": [[298, "neural_compressor.tensorflow.keras.layers.separable_conv2d.QSeparableConv2D", false]], "qsplitoperator (class in neural_compressor.adaptor.ox_utils.operators.split)": [[26, "neural_compressor.adaptor.ox_utils.operators.split.QSplitOperator", false]], "qtensor (class in neural_compressor.torch.algorithms.weight_only.hqq.qtensor)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensor", false]], "qtensorconfig (class in neural_compressor.torch.algorithms.weight_only.hqq.config)": [[422, "neural_compressor.torch.algorithms.weight_only.hqq.config.QTensorConfig", false]], "qtensormetainfo (class in neural_compressor.torch.algorithms.weight_only.hqq.qtensor)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo", false]], "quant_dequant_data() (in module neural_compressor.adaptor.ox_utils.smooth_quant)": [[29, "neural_compressor.adaptor.ox_utils.smooth_quant.quant_dequant_data", false]], "quant_dequant_w_v1() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.quant_dequant_w_v1", false]], "quant_dequant_x_v1() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.quant_dequant_x_v1", false]], "quant_mode_from_pattern() (in module neural_compressor.strategy.utils.tuning_space)": [[278, "neural_compressor.strategy.utils.tuning_space.quant_mode_from_pattern", false]], "quant_tensor() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.quant_tensor", false]], "quant_tensor() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.quant_tensor", false]], "quant_weight_w_scale() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.quant_weight_w_scale", false]], "quantformat (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.QuantFormat", false]], "quantizationawaretrainingcallbacks (class in neural_compressor.compression.callbacks)": [[162, "neural_compressor.compression.callbacks.QuantizationAwareTrainingCallbacks", false]], "quantizationawaretrainingconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.QuantizationAwareTrainingConfig", false]], "quantizationmethod (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.QuantizationMethod", false]], "quantizationmode (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.QuantizationMode", false]], "quantize() (in module neural_compressor.torch.quantization.quantize)": [[442, "neural_compressor.torch.quantization.quantize.quantize", false]], "quantize_4bit() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.quantize_4bit", false]], "quantize_data() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.quantize_data", false]], "quantize_data_per_channel() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.quantize_data_per_channel", false]], "quantize_data_with_scale_zero() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.quantize_data_with_scale_zero", false]], "quantize_elemwise_op() (in module neural_compressor.torch.algorithms.mx_quant.utils)": [[404, "neural_compressor.torch.algorithms.mx_quant.utils.quantize_elemwise_op", false]], "quantize_model() (in module neural_compressor.tensorflow.quantization.quantize)": [[305, "neural_compressor.tensorflow.quantization.quantize.quantize_model", false]], "quantize_model_with_single_config() (in module neural_compressor.tensorflow.quantization.quantize)": [[305, "neural_compressor.tensorflow.quantization.quantize.quantize_model_with_single_config", false]], "quantize_mx_op() (in module neural_compressor.torch.algorithms.mx_quant.utils)": [[404, "neural_compressor.torch.algorithms.mx_quant.utils.quantize_mx_op", false]], "quantize_nparray() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.quantize_nparray", false]], "quantize_sym_model() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.quantize_sym_model", false]], "quantizeconfig (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config)": [[100, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config.QuantizeConfig", false]], "quantizedinitializer (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.QuantizedInitializer", false]], "quantizedinput (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.QuantizedInput", false]], "quantizedrnnconverter (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert)": [[84, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert.QuantizedRNNConverter", false]], "quantizedvalue (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.QuantizedValue", false]], "quantizedvaluetype (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.QuantizedValueType", false]], "quantizegraphbase (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base)": [[117, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base.QuantizeGraphBase", false]], "quantizegraphbase (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base)": [[372, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base.QuantizeGraphBase", false]], "quantizegraphforintel (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu)": [[121, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu.QuantizeGraphForIntel", false]], "quantizegraphforintel (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu)": [[376, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu.QuantizeGraphForIntel", false]], "quantizegraphhelper (class in neural_compressor.adaptor.tf_utils.quantize_graph_common)": [[124, "neural_compressor.adaptor.tf_utils.quantize_graph_common.QuantizeGraphHelper", false]], "quantizegraphhelper (class in neural_compressor.tensorflow.quantization.utils.quantize_graph_common)": [[379, "neural_compressor.tensorflow.quantization.utils.quantize_graph_common.QuantizeGraphHelper", false]], "quantizelayeradd (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add)": [[104, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add.QuantizeLayerAdd", false]], "quantizelayerbase (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base)": [[105, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base.QuantizeLayerBase", false]], "quantizelayerbatchnormalization (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn)": [[106, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn.QuantizeLayerBatchNormalization", false]], "quantizenodebase (class in neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base)": [[117, "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base.QuantizeNodeBase", false]], "quantizenodebase (class in neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base)": [[372, "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base.QuantizeNodeBase", false]], "quantizer (class in neural_compressor.adaptor.ox_utils.quantizer)": [[28, "neural_compressor.adaptor.ox_utils.quantizer.Quantizer", false]], "quantizer (class in neural_compressor.torch.algorithms.base_algorithm)": [[392, "neural_compressor.torch.algorithms.base_algorithm.Quantizer", false]], "quantizer (class in neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.Quantizer", false]], "quantizewrapper (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper)": [[107, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper.QuantizeWrapper", false]], "quantizewrapperbase (class in neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper)": [[107, "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper.QuantizeWrapperBase", false]], "quantoptions (class in neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.QuantOptions", false]], "quanttype (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.QuantType", false]], "quanttype (class in neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.QuantType", false]], "query_quantizable_nodes() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.query_quantizable_nodes", false]], "randomcroptftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomCropTFTransform", false]], "randomcroptransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomCropTransform", false]], "randomhorizontalflip (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomHorizontalFlip", false]], "randomresizedcropmxnettransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomResizedCropMXNetTransform", false]], "randomresizedcroppytorchtransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomResizedCropPytorchTransform", false]], "randomresizedcroptftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomResizedCropTFTransform", false]], "randomresizedcroptransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomResizedCropTransform", false]], "randomtunestrategy (class in neural_compressor.strategy.random)": [[273, "neural_compressor.strategy.random.RandomTuneStrategy", false]], "randomverticalflip (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RandomVerticalFlip", false]], "rawgptquantizer (class in neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.RAWGPTQuantizer", false]], "read_graph() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.read_graph", false]], "read_graph() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.read_graph", false]], "read_squad_examples() (in module neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.read_squad_examples", false]], "read_tensorflow_node_attrs() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.read_tensorflow_node_attrs", false]], "recipe (neural_compressor.compression.pruner.model_slim.pattern_analyzer.recipesearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.RecipeSearcher.recipe", false]], "recipesearcher (class in neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.RecipeSearcher", false]], "reconstruct_saved_model() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.reconstruct_saved_model", false]], "reconstruct_saved_model() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.reconstruct_saved_model", false]], "record_output() (in module neural_compressor.compression.distillation.utility)": [[166, "neural_compressor.compression.distillation.utility.record_output", false]], "recover() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.recover", false]], "recover_forward() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.recover_forward", false]], "recover_model_from_json() (in module neural_compressor.torch.algorithms.smooth_quant.save_load)": [[411, "neural_compressor.torch.algorithms.smooth_quant.save_load.recover_model_from_json", false]], "recover_model_from_json() (in module neural_compressor.utils.pytorch)": [[464, "neural_compressor.utils.pytorch.recover_model_from_json", false]], "reduceminmaxoperator (class in neural_compressor.adaptor.ox_utils.operators.reduce)": [[24, "neural_compressor.adaptor.ox_utils.operators.reduce.ReduceMinMaxOperator", false]], "reduceoperator (class in neural_compressor.adaptor.ox_utils.operators.reduce)": [[24, "neural_compressor.adaptor.ox_utils.operators.reduce.ReduceOperator", false]], "reg (neural_compressor.compression.pruner.pruners.basic.kerasbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.KerasBasicPruner.reg", false]], "reg (neural_compressor.compression.pruner.pruners.basic.pytorchbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.PytorchBasicPruner.reg", false]], "reg (neural_compressor.compression.pruner.pruners.block_mask.pytorchblockmaskpruner attribute)": [[182, "neural_compressor.compression.pruner.pruners.block_mask.PytorchBlockMaskPruner.reg", false]], "reg (neural_compressor.compression.pruner.pruners.retrain_free.pytorchretrainfreepruner attribute)": [[187, "neural_compressor.compression.pruner.pruners.retrain_free.PytorchRetrainFreePruner.reg", false]], "reg_terms (neural_compressor.compression.pruner.regs.grouplasso attribute)": [[189, "neural_compressor.compression.pruner.regs.GroupLasso.reg_terms", false]], "register_accelerator() (in module neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.register_accelerator", false]], "register_algo() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.register_algo", false]], "register_algo() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.register_algo", false]], "register_autotune() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.register_autotune", false]], "register_config() (in module neural_compressor.common.base_config)": [[152, "neural_compressor.common.base_config.register_config", false]], "register_criterion() (in module neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.register_criterion", false]], "register_criterion() (in module neural_compressor.compression.pruner.tf_criteria)": [[191, "neural_compressor.compression.pruner.tf_criteria.register_criterion", false]], "register_customer_metric() (in module neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.register_customer_metric", false]], "register_pattern() (in module neural_compressor.compression.pruner.patterns.base)": [[175, "neural_compressor.compression.pruner.patterns.base.register_pattern", false]], "register_pruner() (in module neural_compressor.compression.pruner.pruners.base)": [[180, "neural_compressor.compression.pruner.pruners.base.register_pruner", false]], "register_pruning() (in module neural_compressor.compression.pruner.pruning)": [[188, "neural_compressor.compression.pruner.pruning.register_pruning", false]], "register_reg() (in module neural_compressor.compression.pruner.regs)": [[189, "neural_compressor.compression.pruner.regs.register_reg", false]], "register_scheduler() (in module neural_compressor.compression.pruner.schedulers)": [[190, "neural_compressor.compression.pruner.schedulers.register_scheduler", false]], "register_supported_configs_for_fwk() (in module neural_compressor.common.base_config)": [[152, "neural_compressor.common.base_config.register_supported_configs_for_fwk", false]], "register_weight_hooks() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.register_weight_hooks", false]], "removableactivationoperator (class in neural_compressor.adaptor.ox_utils.operators.activation)": [[5, "neural_compressor.adaptor.ox_utils.operators.activation.RemovableActivationOperator", false]], "remove_init_from_model_input() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.remove_init_from_model_input", false]], "removetrainingnodesoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes)": [[65, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes.RemoveTrainingNodesOptimizer", false]], "removetrainingnodesoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes)": [[337, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes.RemoveTrainingNodesOptimizer", false]], "renamebatchnormoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm)": [[66, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm.RenameBatchNormOptimizer", false]], "renamebatchnormoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm)": [[338, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm.RenameBatchNormOptimizer", false]], "replace_forward() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.replace_forward", false]], "replace_pattern (neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.patternpair attribute)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.PatternPair.replace_pattern", false]], "replacement_fn() (in module neural_compressor.torch.algorithms.weight_only.hqq.quantizer)": [[427, "neural_compressor.torch.algorithms.weight_only.hqq.quantizer.replacement_fn", false]], "rerangequantizedconcat (class in neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat)": [[132, "neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat.RerangeQuantizedConcat", false]], "rerangequantizedconcat (class in neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat)": [[384, "neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat.RerangeQuantizedConcat", false]], "rescalekeraspretraintransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RescaleKerasPretrainTransform", false]], "rescaletftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RescaleTFTransform", false]], "rescaletransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.RescaleTransform", false]], "reset_none_to_default() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.reset_none_to_default", false]], "reshape_in_channel_to_last() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.reshape_in_channel_to_last", false]], "reshape_scale_as_input() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.reshape_scale_as_input", false]], "reshape_scale_as_weight() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.reshape_scale_as_weight", false]], "resizemxnettransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ResizeMXNetTransform", false]], "resizeoperator (class in neural_compressor.adaptor.ox_utils.operators.resize)": [[25, "neural_compressor.adaptor.ox_utils.operators.resize.ResizeOperator", false]], "resizepytorchtransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ResizePytorchTransform", false]], "resizetftransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ResizeTFTransform", false]], "resizetransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ResizeTransform", false]], "resizewithaspectratio (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.ResizeWithAspectRatio", false]], "resizewithratio (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ResizeWithRatio", false]], "retrainfreecriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.RetrainFreeCriterion", false]], "retrainfreepruning (class in neural_compressor.compression.pruner.pruning)": [[188, "neural_compressor.compression.pruner.pruning.RetrainFreePruning", false]], "reverted_data_type() (in module neural_compressor.strategy.utils.utility)": [[280, "neural_compressor.strategy.utils.utility.reverted_data_type", false]], "rmse (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.RMSE", false]], "roc (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.ROC", false]], "roundingmode (class in neural_compressor.torch.algorithms.mx_quant.utils)": [[404, "neural_compressor.torch.algorithms.mx_quant.utils.RoundingMode", false]], "rtn_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.rtn_entry", false]], "rtn_quantize() (in module neural_compressor.adaptor.ox_utils.weight_only)": [[31, "neural_compressor.adaptor.ox_utils.weight_only.rtn_quantize", false]], "rtnconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.RTNConfig", false]], "rtnconfig (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.RtnConfig", false]], "rtnquantizer (class in neural_compressor.torch.algorithms.weight_only.rtn)": [[430, "neural_compressor.torch.algorithms.weight_only.rtn.RTNQuantizer", false]], "run_forward() (in module neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.run_forward", false]], "run_instance() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.run_instance", false]], "run_multi_instance_command() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.run_multi_instance_command", false]], "sample (neural_compressor.metric.metric.accuracy attribute)": [[234, "neural_compressor.metric.metric.Accuracy.sample", false]], "sample (neural_compressor.metric.metric.loss attribute)": [[234, "neural_compressor.metric.metric.Loss.sample", false]], "sampler (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.Sampler", false]], "sampler (class in neural_compressor.data.dataloaders.sampler)": [[207, "neural_compressor.data.dataloaders.sampler.Sampler", false]], "save() (in module neural_compressor.compression.pruner)": [[170, "neural_compressor.compression.pruner.save", false]], "save() (in module neural_compressor.torch.algorithms.pt2e_quant.save_load)": [[408, "neural_compressor.torch.algorithms.pt2e_quant.save_load.save", false]], "save() (in module neural_compressor.torch.algorithms.static_quant.save_load)": [[415, "neural_compressor.torch.algorithms.static_quant.save_load.save", false]], "save() (in module neural_compressor.torch.algorithms.weight_only.save_load)": [[431, "neural_compressor.torch.algorithms.weight_only.save_load.save", false]], "save_config_mapping() (in module neural_compressor.common.utils.save_load)": [[160, "neural_compressor.common.utils.save_load.save_config_mapping", false]], "save_for_huggingface_upstream() (in module neural_compressor.utils.load_huggingface)": [[461, "neural_compressor.utils.load_huggingface.save_for_huggingface_upstream", false]], "save_protobuf() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.save_protobuf", false]], "saved_model_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.saved_model_session", false]], "saved_model_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.saved_model_session", false]], "scalepropagationtransformer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation)": [[85, "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation.ScaleProPagationTransformer", false]], "scalepropagationtransformer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation)": [[355, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation.ScaleProPagationTransformer", false]], "scheduler (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.scheduler", false]], "scheduler (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.scheduler", false]], "scheduler (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.scheduler", false]], "scheduler (neural_compressor.compression.pruner.pruners.basic.kerasbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.KerasBasicPruner.scheduler", false]], "scheduler (neural_compressor.compression.pruner.pruners.basic.pytorchbasicpruner attribute)": [[181, "neural_compressor.compression.pruner.pruners.basic.PytorchBasicPruner.scheduler", false]], "scheduler (neural_compressor.compression.pruner.pruners.block_mask.pytorchblockmaskpruner attribute)": [[182, "neural_compressor.compression.pruner.pruners.block_mask.PytorchBlockMaskPruner.scheduler", false]], "scheduler (neural_compressor.compression.pruner.pruners.retrain_free.pytorchretrainfreepruner attribute)": [[187, "neural_compressor.compression.pruner.pruners.retrain_free.PytorchRetrainFreePruner.scheduler", false]], "scores (neural_compressor.compression.pruner.criteria.blockmaskcriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.BlockMaskCriterion.scores", false]], "scores (neural_compressor.compression.pruner.criteria.gradientcriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.GradientCriterion.scores", false]], "scores (neural_compressor.compression.pruner.criteria.magnitudecriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.MagnitudeCriterion.scores", false]], "scores (neural_compressor.compression.pruner.criteria.pruningcriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.PruningCriterion.scores", false]], "scores (neural_compressor.compression.pruner.criteria.retrainfreecriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.RetrainFreeCriterion.scores", false]], "scores (neural_compressor.compression.pruner.criteria.snipcriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.SnipCriterion.scores", false]], "scores (neural_compressor.compression.pruner.criteria.snipmomentumcriterion attribute)": [[169, "neural_compressor.compression.pruner.criteria.SnipMomentumCriterion.scores", false]], "scores (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.scores", false]], "scores (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.scores", false]], "scores (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.scores", false]], "scores (neural_compressor.compression.pruner.tf_criteria.magnitudecriterion attribute)": [[191, "neural_compressor.compression.pruner.tf_criteria.MagnitudeCriterion.scores", false]], "scores (neural_compressor.compression.pruner.tf_criteria.pruningcriterion attribute)": [[191, "neural_compressor.compression.pruner.tf_criteria.PruningCriterion.scores", false]], "search_clip() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.search_clip", false]], "search_pattern (neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.patternpair attribute)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.PatternPair.search_pattern", false]], "searching_results (neural_compressor.compression.pruner.model_slim.pattern_analyzer.jitbasicsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher.searching_results", false]], "searching_results (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.searching_results", false]], "searching_results (neural_compressor.compression.pruner.model_slim.pattern_analyzer.recipesearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.RecipeSearcher.searching_results", false]], "selfknowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.SelfKnowledgeDistillationLoss", false]], "selfknowledgedistillationlossconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.SelfKnowledgeDistillationLossConfig", false]], "selfmhasearcher (class in neural_compressor.compression.pruner.model_slim.pattern_analyzer)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.SelfMHASearcher", false]], "seqtype (class in neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.SeqType", false]], "sequentialsampler (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.SequentialSampler", false]], "sequentialsampler (class in neural_compressor.data.dataloaders.sampler)": [[207, "neural_compressor.data.dataloaders.sampler.SequentialSampler", false]], "sequentialsampler (class in neural_compressor.tensorflow.utils.data)": [[387, "neural_compressor.tensorflow.utils.data.SequentialSampler", false]], "set_all_env_var() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.set_all_env_var", false]], "set_cores_for_instance() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.set_cores_for_instance", false]], "set_eager_execution() (in module neural_compressor.profiling.profiler.tensorflow_profiler.utils)": [[261, "neural_compressor.profiling.profiler.tensorflow_profiler.utils.set_eager_execution", false]], "set_env_var() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.set_env_var", false]], "set_module() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.set_module", false]], "set_module() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.set_module", false]], "set_module() (in module neural_compressor.torch.algorithms.weight_only.utility)": [[433, "neural_compressor.torch.algorithms.weight_only.utility.set_module", false]], "set_module() (in module neural_compressor.torch.utils.utility)": [[447, "neural_compressor.torch.utils.utility.set_module", false]], "set_name() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils)": [[90, "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils.set_name", false]], "set_random_seed() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.set_random_seed", false]], "set_random_seed() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.set_random_seed", false]], "set_resume_from() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.set_resume_from", false]], "set_resume_from() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.set_resume_from", false]], "set_tensorboard() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.set_tensorboard", false]], "set_tensorboard() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.set_tensorboard", false]], "set_workspace() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.set_workspace", false]], "set_workspace() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.set_workspace", false]], "shape (neural_compressor.torch.algorithms.weight_only.hqq.qtensor.qtensormetainfo attribute)": [[426, "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo.shape", false]], "shareqdqforitexypatternoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern)": [[94, "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern.ShareQDQForItexYPatternOptimizer", false]], "shareqdqforitexypatternoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern)": [[359, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern.ShareQDQForItexYPatternOptimizer", false]], "show_memory_info() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.show_memory_info", false]], "sigopttunestrategy (class in neural_compressor.contrib.strategy.sigopt)": [[198, "neural_compressor.contrib.strategy.sigopt.SigOptTuneStrategy", false]], "simple_inference() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.simple_inference", false]], "simple_inference() (in module neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.simple_inference", false]], "simple_progress_bar() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.simple_progress_bar", false]], "singleton() (in module neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.singleton", false]], "singleton() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.singleton", false]], "singleton() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.singleton", false]], "slim_session() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.slim_session", false]], "slim_session() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.slim_session", false]], "smooth_distribution() (in module neural_compressor.adaptor.ox_utils.calibrator)": [[3, "neural_compressor.adaptor.ox_utils.calibrator.smooth_distribution", false]], "smooth_quant_entry() (in module neural_compressor.tensorflow.quantization.algorithm_entry)": [[301, "neural_compressor.tensorflow.quantization.algorithm_entry.smooth_quant_entry", false]], "smooth_quant_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.smooth_quant_entry", false]], "smoothquant (class in neural_compressor.algorithm.smooth_quant)": [[149, "neural_compressor.algorithm.smooth_quant.SmoothQuant", false]], "smoothquant (class in neural_compressor.tensorflow.algorithms.smoother.core)": [[284, "neural_compressor.tensorflow.algorithms.smoother.core.SmoothQuant", false]], "smoothquantcalibration (class in neural_compressor.adaptor.tf_utils.smooth_quant_calibration)": [[125, "neural_compressor.adaptor.tf_utils.smooth_quant_calibration.SmoothQuantCalibration", false]], "smoothquantcalibration (class in neural_compressor.tensorflow.algorithms.smoother.calibration)": [[283, "neural_compressor.tensorflow.algorithms.smoother.calibration.SmoothQuantCalibration", false]], "smoothquantcalibrationllm (class in neural_compressor.adaptor.tf_utils.smooth_quant_calibration)": [[125, "neural_compressor.adaptor.tf_utils.smooth_quant_calibration.SmoothQuantCalibrationLLM", false]], "smoothquantcalibrationllm (class in neural_compressor.tensorflow.algorithms.smoother.calibration)": [[283, "neural_compressor.tensorflow.algorithms.smoother.calibration.SmoothQuantCalibrationLLM", false]], "smoothquantconfig (class in neural_compressor.tensorflow.quantization.config)": [[303, "neural_compressor.tensorflow.quantization.config.SmoothQuantConfig", false]], "smoothquantconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.SmoothQuantConfig", false]], "smoothquantquantizer (class in neural_compressor.torch.algorithms.smooth_quant.smooth_quant)": [[412, "neural_compressor.torch.algorithms.smooth_quant.smooth_quant.SmoothQuantQuantizer", false]], "smoothquantsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.SmoothQuantSampler", false]], "smoothquantscaler (class in neural_compressor.adaptor.tf_utils.smooth_quant_scaler)": [[126, "neural_compressor.adaptor.tf_utils.smooth_quant_scaler.SmoothQuantScaler", false]], "smoothquantscaler (class in neural_compressor.tensorflow.algorithms.smoother.scaler)": [[286, "neural_compressor.tensorflow.algorithms.smoother.scaler.SmoothQuantScaler", false]], "smoothquantscalerllm (class in neural_compressor.adaptor.tf_utils.smooth_quant_scaler)": [[126, "neural_compressor.adaptor.tf_utils.smooth_quant_scaler.SmoothQuantScalerLLM", false]], "smoothquantscalerllm (class in neural_compressor.tensorflow.algorithms.smoother.scaler)": [[286, "neural_compressor.tensorflow.algorithms.smoother.scaler.SmoothQuantScalerLLM", false]], "snipcriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.SnipCriterion", false]], "snipmomentumcriterion (class in neural_compressor.compression.pruner.criteria)": [[169, "neural_compressor.compression.pruner.criteria.SnipMomentumCriterion", false]], "sparsedummydataset (class in neural_compressor.data.datasets.dummy_dataset_v2)": [[213, "neural_compressor.data.datasets.dummy_dataset_v2.SparseDummyDataset", false]], "sparsegptpruning (class in neural_compressor.compression.pruner.pruning)": [[188, "neural_compressor.compression.pruner.pruning.SparseGPTPruning", false]], "split_shared_bias() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.split_shared_bias", false]], "splitoperator (class in neural_compressor.adaptor.ox_utils.operators.split)": [[26, "neural_compressor.adaptor.ox_utils.operators.split.SplitOperator", false]], "splitsharedinputoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input)": [[67, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input.SplitSharedInputOptimizer", false]], "splitsharedinputoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input)": [[339, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input.SplitSharedInputOptimizer", false]], "sqlinearwrapper (class in neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.SQLinearWrapper", false]], "squadexample (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.SquadExample", false]], "squadf1 (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.SquadF1", false]], "start_step (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.start_step", false]], "start_step (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.start_step", false]], "start_step (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.start_step", false]], "static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcher.static_graph", false]], "static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.classifierheadsearchertf attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcherTF.static_graph", false]], "static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.jitbasicsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher.static_graph", false]], "static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.static_graph", false]], "static_graph (neural_compressor.compression.pruner.model_slim.pattern_analyzer.selfmhasearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.SelfMHASearcher.static_graph", false]], "static_quant_entry() (in module neural_compressor.tensorflow.quantization.algorithm_entry)": [[301, "neural_compressor.tensorflow.quantization.algorithm_entry.static_quant_entry", false]], "static_quant_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.static_quant_entry", false]], "static_quant_export() (in module neural_compressor.utils.export.torch2onnx)": [[458, "neural_compressor.utils.export.torch2onnx.static_quant_export", false]], "staticquantconfig (class in neural_compressor.tensorflow.keras.quantization.config)": [[299, "neural_compressor.tensorflow.keras.quantization.config.StaticQuantConfig", false]], "staticquantconfig (class in neural_compressor.tensorflow.quantization.config)": [[303, "neural_compressor.tensorflow.quantization.config.StaticQuantConfig", false]], "staticquantconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.StaticQuantConfig", false]], "staticquantquantizer (class in neural_compressor.torch.algorithms.static_quant.static_quant)": [[416, "neural_compressor.torch.algorithms.static_quant.static_quant.StaticQuantQuantizer", false]], "statistics (class in neural_compressor.common.utils.utility)": [[161, "neural_compressor.common.utils.utility.Statistics", false]], "statistics (class in neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.Statistics", false]], "str2array() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.str2array", false]], "strategy_registry() (in module neural_compressor.strategy.strategy)": [[274, "neural_compressor.strategy.strategy.strategy_registry", false]], "strip_equivalent_nodes() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.strip_equivalent_nodes", false]], "strip_equivalent_nodes() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.strip_equivalent_nodes", false]], "strip_unused_nodes() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.strip_unused_nodes", false]], "strip_unused_nodes() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.strip_unused_nodes", false]], "stripequivalentnodesoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes)": [[68, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes.StripEquivalentNodesOptimizer", false]], "stripequivalentnodesoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes)": [[340, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes.StripEquivalentNodesOptimizer", false]], "stripunusednodesoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes)": [[69, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes.StripUnusedNodesOptimizer", false]], "stripunusednodesoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes)": [[341, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes.StripUnusedNodesOptimizer", false]], "styletransferdataset (class in neural_compressor.data.datasets.style_transfer_dataset)": [[216, "neural_compressor.data.datasets.style_transfer_dataset.StyleTransferDataset", false]], "sum (neural_compressor.metric.metric.loss attribute)": [[234, "neural_compressor.metric.metric.Loss.sum", false]], "summary_benchmark() (in module neural_compressor.benchmark)": [[151, "neural_compressor.benchmark.summary_benchmark", false]], "summary_latency_throughput() (in module neural_compressor.common.benchmark)": [[154, "neural_compressor.common.benchmark.summary_latency_throughput", false]], "switchoptimizer (class in neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer)": [[70, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer.SwitchOptimizer", false]], "switchoptimizer (class in neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer)": [[342, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer.SwitchOptimizer", false]], "symbol_re (neural_compressor.metric.bleu.unicoderegex attribute)": [[227, "neural_compressor.metric.bleu.UnicodeRegex.symbol_re", false]], "symbolic_trace() (in module neural_compressor.adaptor.torch_utils.symbolic_trace)": [[144, "neural_compressor.adaptor.torch_utils.symbolic_trace.symbolic_trace", false]], "target_layers (neural_compressor.compression.pruner.model_slim.pattern_analyzer.jitbasicsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher.target_layers", false]], "target_layers (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.target_layers", false]], "target_op_lut (neural_compressor.compression.pruner.model_slim.pattern_analyzer.linear2linearsearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher.target_op_lut", false]], "target_sparsity (neural_compressor.compression.pruner.patterns.base.basepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.BasePattern.target_sparsity", false]], "target_sparsity (neural_compressor.compression.pruner.patterns.base.kerasbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.KerasBasePattern.target_sparsity", false]], "target_sparsity (neural_compressor.compression.pruner.patterns.base.pytorchbasepattern attribute)": [[175, "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern.target_sparsity", false]], "target_sparsity_ratio (neural_compressor.compression.pruner.pruners.base.basepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.BasePruner.target_sparsity_ratio", false]], "target_sparsity_ratio (neural_compressor.compression.pruner.pruners.base.kerasbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.KerasBasePruner.target_sparsity_ratio", false]], "target_sparsity_ratio (neural_compressor.compression.pruner.pruners.base.pytorchbasepruner attribute)": [[180, "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner.target_sparsity_ratio", false]], "targets (neural_compressor.compression.pruner.model_slim.pattern_analyzer.recipesearcher attribute)": [[173, "neural_compressor.compression.pruner.model_slim.pattern_analyzer.RecipeSearcher.targets", false]], "targetspace (class in neural_compressor.strategy.bayesian)": [[266, "neural_compressor.strategy.bayesian.TargetSpace", false]], "tensorcollector (class in neural_compressor.adaptor.mxnet_utils.util)": [[1, "neural_compressor.adaptor.mxnet_utils.util.TensorCollector", false]], "tensorflow (class in neural_compressor.config)": [[195, "neural_compressor.config.TensorFlow", false]], "tensorflow (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.Tensorflow", false]], "tensorflow_itexadaptor (class in neural_compressor.adaptor.tensorflow)": [[32, "neural_compressor.adaptor.tensorflow.Tensorflow_ITEXAdaptor", false]], "tensorflow_itexadaptor (class in neural_compressor.tensorflow.algorithms.static_quant.tensorflow)": [[289, "neural_compressor.tensorflow.algorithms.static_quant.tensorflow.Tensorflow_ITEXAdaptor", false]], "tensorflowadam (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.TensorFlowAdam", false]], "tensorflowadamw (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.TensorFlowAdamW", false]], "tensorflowadaptor (class in neural_compressor.adaptor.tensorflow)": [[32, "neural_compressor.adaptor.tensorflow.TensorFlowAdaptor", false]], "tensorflowadaptor (class in neural_compressor.tensorflow.algorithms.static_quant.tensorflow)": [[289, "neural_compressor.tensorflow.algorithms.static_quant.tensorflow.TensorFlowAdaptor", false]], "tensorflowbasemodel (class in neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.TensorflowBaseModel", false]], "tensorflowbasemodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.TensorflowBaseModel", false]], "tensorflowbertdataloader (class in neural_compressor.data.dataloaders.tensorflow_dataloader)": [[208, "neural_compressor.data.dataloaders.tensorflow_dataloader.TensorflowBertDataLoader", false]], "tensorflowbertdataset (class in neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.TensorflowBertDataset", false]], "tensorflowcheckpointmodel (class in neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.TensorflowCheckpointModel", false]], "tensorflowcheckpointmodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.TensorflowCheckpointModel", false]], "tensorflowcifar10 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowCIFAR10", false]], "tensorflowcifar100 (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowCIFAR100", false]], "tensorflowcocomap (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.TensorflowCOCOMAP", false]], "tensorflowconfig (class in neural_compressor.tensorflow.algorithms.static_quant.tensorflow)": [[289, "neural_compressor.tensorflow.algorithms.static_quant.tensorflow.TensorFlowConfig", false]], "tensorflowconfigconverter (class in neural_compressor.tensorflow.algorithms.static_quant.tensorflow)": [[289, "neural_compressor.tensorflow.algorithms.static_quant.tensorflow.TensorflowConfigConverter", false]], "tensorflowcriterions (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.TensorflowCriterions", false]], "tensorflowcroptoboundingbox (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowCropToBoundingBox", false]], "tensorflowcrossentropyloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.TensorFlowCrossEntropyLoss", false]], "tensorflowdataloader (class in neural_compressor.data.dataloaders.tensorflow_dataloader)": [[208, "neural_compressor.data.dataloaders.tensorflow_dataloader.TensorflowDataLoader", false]], "tensorflowdatasets (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowDatasets", false]], "tensorflowfashionmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowFashionMNIST", false]], "tensorflowfilters (class in neural_compressor.data.filters.filter)": [[218, "neural_compressor.data.filters.filter.TensorflowFilters", false]], "tensorflowglobalconfig (class in neural_compressor.tensorflow.utils.model)": [[389, "neural_compressor.tensorflow.utils.model.TensorflowGlobalConfig", false]], "tensorflowimagenetdataset (class in neural_compressor.data.datasets.imagenet_dataset)": [[214, "neural_compressor.data.datasets.imagenet_dataset.TensorflowImagenetDataset", false]], "tensorflowimagenetraw (class in neural_compressor.data.datasets.imagenet_dataset)": [[214, "neural_compressor.data.datasets.imagenet_dataset.TensorflowImagenetRaw", false]], "tensorflowimagerecord (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowImageRecord", false]], "tensorflowknowledgedistillationloss (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.TensorflowKnowledgeDistillationLoss", false]], "tensorflowknowledgedistillationlossexternal (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.TensorflowKnowledgeDistillationLossExternal", false]], "tensorflowknowledgedistillationlosswrapper (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.TensorflowKnowledgeDistillationLossWrapper", false]], "tensorflowllmmodel (class in neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.TensorflowLLMModel", false]], "tensorflowllmmodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.TensorflowLLMModel", false]], "tensorflowmap (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.TensorflowMAP", false]], "tensorflowmetrics (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.TensorflowMetrics", false]], "tensorflowmnist (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowMNIST", false]], "tensorflowmodel (class in neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.TensorflowModel", false]], "tensorflowmodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.TensorflowModel", false]], "tensorflowmodelzoobertdataloader (class in neural_compressor.data.dataloaders.tensorflow_dataloader)": [[208, "neural_compressor.data.dataloaders.tensorflow_dataloader.TensorflowModelZooBertDataLoader", false]], "tensorflowmodelzoobertdataset (class in neural_compressor.data.datasets.bert_dataset)": [[209, "neural_compressor.data.datasets.bert_dataset.TensorflowModelZooBertDataset", false]], "tensorflowoptimizers (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.TensorflowOptimizers", false]], "tensorflowparserfactory (class in neural_compressor.profiling.parser.tensorflow_parser.factory)": [[252, "neural_compressor.profiling.parser.tensorflow_parser.factory.TensorFlowParserFactory", false]], "tensorflowprofilingparser (class in neural_compressor.profiling.parser.tensorflow_parser.parser)": [[253, "neural_compressor.profiling.parser.tensorflow_parser.parser.TensorFlowProfilingParser", false]], "tensorflowqatmodel (class in neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.TensorflowQATModel", false]], "tensorflowqdqtoonnxqdqconverter (class in neural_compressor.adaptor.tf_utils.tf2onnx_converter)": [[127, "neural_compressor.adaptor.tf_utils.tf2onnx_converter.TensorflowQDQToOnnxQDQConverter", false]], "tensorflowquery (class in neural_compressor.adaptor.tensorflow)": [[32, "neural_compressor.adaptor.tensorflow.TensorflowQuery", false]], "tensorflowquery (class in neural_compressor.tensorflow.algorithms.static_quant.tensorflow)": [[289, "neural_compressor.tensorflow.algorithms.static_quant.tensorflow.TensorflowQuery", false]], "tensorflowrandomhorizontalflip (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowRandomHorizontalFlip", false]], "tensorflowrandomverticalflip (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowRandomVerticalFlip", false]], "tensorflowresizecropimagenettransform (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.TensorflowResizeCropImagenetTransform", false]], "tensorflowresizewithratio (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowResizeWithRatio", false]], "tensorflowsavedmodelmodel (class in neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.TensorflowSavedModelModel", false]], "tensorflowsavedmodelmodel (class in neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.TensorflowSavedModelModel", false]], "tensorflowsgd (class in neural_compressor.compression.distillation.optimizers)": [[165, "neural_compressor.compression.distillation.optimizers.TensorFlowSGD", false]], "tensorflowshiftrescale (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.TensorflowShiftRescale", false]], "tensorflowsparsecategoricalcrossentropy (class in neural_compressor.compression.distillation.criterions)": [[163, "neural_compressor.compression.distillation.criterions.TensorFlowSparseCategoricalCrossentropy", false]], "tensorflowtfrecorddataset (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowTFRecordDataset", false]], "tensorflowtopk (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.TensorflowTopK", false]], "tensorflowtransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowTransform", false]], "tensorflowtransforms (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowTransforms", false]], "tensorflowtranspose (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowTranspose", false]], "tensorflowtransposelastchannel (class in neural_compressor.data.transforms.imagenet_transform)": [[221, "neural_compressor.data.transforms.imagenet_transform.TensorflowTransposeLastChannel", false]], "tensorflowvocmap (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.TensorflowVOCMAP", false]], "tensorflowvocrecord (class in neural_compressor.data.datasets.dataset)": [[211, "neural_compressor.data.datasets.dataset.TensorflowVOCRecord", false]], "tensorflowwrapfunction (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TensorflowWrapFunction", false]], "teq_quantize_entry() (in module neural_compressor.torch.quantization.algorithm_entry)": [[437, "neural_compressor.torch.quantization.algorithm_entry.teq_quantize_entry", false]], "teqconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.TEQConfig", false]], "teqconfig (class in neural_compressor.transformers.utils.quantization_config)": [[451, "neural_compressor.transformers.utils.quantization_config.TeqConfig", false]], "teqlinearfakequant (class in neural_compressor.adaptor.torch_utils.model_wrapper)": [[142, "neural_compressor.adaptor.torch_utils.model_wrapper.TEQLinearFakeQuant", false]], "teqlinearfakequant (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.TEQLinearFakeQuant", false]], "tequantizer (class in neural_compressor.torch.algorithms.weight_only.teq)": [[432, "neural_compressor.torch.algorithms.weight_only.teq.TEQuantizer", false]], "tf2onnxconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.TF2ONNXConfig", false]], "tf_to_fp32_onnx() (in module neural_compressor.utils.export.tf2onnx)": [[457, "neural_compressor.utils.export.tf2onnx.tf_to_fp32_onnx", false]], "tf_to_int8_onnx() (in module neural_compressor.utils.export.tf2onnx)": [[457, "neural_compressor.utils.export.tf2onnx.tf_to_int8_onnx", false]], "tfdatadataloader (class in neural_compressor.data.dataloaders.tensorflow_dataloader)": [[208, "neural_compressor.data.dataloaders.tensorflow_dataloader.TFDataDataLoader", false]], "tfmodelzoocollecttransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TFModelZooCollectTransform", false]], "tfslimnetsfactory (class in neural_compressor.model.nets_factory)": [[241, "neural_compressor.model.nets_factory.TFSlimNetsFactory", false]], "tfslimnetsfactory (class in neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.TFSlimNetsFactory", false]], "tfsquadv1modelzooposttransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TFSquadV1ModelZooPostTransform", false]], "tfsquadv1posttransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TFSquadV1PostTransform", false]], "time_limit() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.time_limit", false]], "to_numpy() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.to_numpy", false]], "toarray (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ToArray", false]], "tondarraytransform (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.ToNDArrayTransform", false]], "torch2onnxconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.Torch2ONNXConfig", false]], "torch_to_fp32_onnx() (in module neural_compressor.utils.export.torch2onnx)": [[458, "neural_compressor.utils.export.torch2onnx.torch_to_fp32_onnx", false]], "torch_to_int8_onnx() (in module neural_compressor.utils.export.torch2onnx)": [[458, "neural_compressor.utils.export.torch2onnx.torch_to_int8_onnx", false]], "torchbaseconfig (class in neural_compressor.torch.quantization.config)": [[439, "neural_compressor.torch.quantization.config.TorchBaseConfig", false]], "torchsmoothquant (class in neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.TorchSmoothQuant", false]], "tpetunestrategy (class in neural_compressor.contrib.strategy.tpe)": [[199, "neural_compressor.contrib.strategy.tpe.TpeTuneStrategy", false]], "trace_and_fuse_sub_graph() (in module neural_compressor.adaptor.torch_utils.symbolic_trace)": [[144, "neural_compressor.adaptor.torch_utils.symbolic_trace.trace_and_fuse_sub_graph", false]], "trace_gptq_target_blocks() (in module neural_compressor.torch.algorithms.weight_only.gptq)": [[420, "neural_compressor.torch.algorithms.weight_only.gptq.trace_gptq_target_blocks", false]], "trainableequivalenttransformation (class in neural_compressor.torch.algorithms.weight_only.teq)": [[432, "neural_compressor.torch.algorithms.weight_only.teq.TrainableEquivalentTransformation", false]], "transform_registry() (in module neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.transform_registry", false]], "transformation() (in module neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter)": [[406, "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.transformation", false]], "transformerbasedmodelblockpatterndetector (class in neural_compressor.adaptor.torch_utils.pattern_detector)": [[143, "neural_compressor.adaptor.torch_utils.pattern_detector.TransformerBasedModelBlockPatternDetector", false]], "transformerbasedmodelblockpatterndetector (class in neural_compressor.torch.algorithms.static_quant.utility)": [[417, "neural_compressor.torch.algorithms.static_quant.utility.TransformerBasedModelBlockPatternDetector", false]], "transforms (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.TRANSFORMS", false], [225, "neural_compressor.data.transforms.transform.Transforms", false]], "transpose (class in neural_compressor.data.transforms.transform)": [[225, "neural_compressor.data.transforms.transform.Transpose", false]], "trt_env_setup() (in module neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.trt_env_setup", false]], "try_loading_keras() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.try_loading_keras", false]], "try_loading_keras() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.try_loading_keras", false]], "tunestrategy (class in neural_compressor.strategy.strategy)": [[274, "neural_compressor.strategy.strategy.TuneStrategy", false]], "tunestrategymeta (class in neural_compressor.strategy.strategy)": [[274, "neural_compressor.strategy.strategy.TuneStrategyMeta", false]], "tuningconfig (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.TuningConfig", false]], "tuningcriterion (class in neural_compressor.config)": [[195, "neural_compressor.config.TuningCriterion", false]], "tuningitem (class in neural_compressor.strategy.utils.tuning_space)": [[278, "neural_compressor.strategy.utils.tuning_space.TuningItem", false]], "tuninglogger (class in neural_compressor.common.utils.logger)": [[159, "neural_compressor.common.utils.logger.TuningLogger", false]], "tuningmonitor (class in neural_compressor.common.base_tuning)": [[153, "neural_compressor.common.base_tuning.TuningMonitor", false]], "tuningorder (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.TuningOrder", false]], "tuningparam (class in neural_compressor.common.tuning_param)": [[156, "neural_compressor.common.tuning_param.TuningParam", false]], "tuningsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.TuningSampler", false]], "tuningspace (class in neural_compressor.strategy.utils.tuning_space)": [[278, "neural_compressor.strategy.utils.tuning_space.TuningSpace", false]], "unarydirect8bitoperator (class in neural_compressor.adaptor.ox_utils.operators.unary_op)": [[27, "neural_compressor.adaptor.ox_utils.operators.unary_op.UnaryDirect8BitOperator", false]], "unaryoperator (class in neural_compressor.adaptor.ox_utils.operators.unary_op)": [[27, "neural_compressor.adaptor.ox_utils.operators.unary_op.UnaryOperator", false]], "unicoderegex (class in neural_compressor.metric.bleu)": [[227, "neural_compressor.metric.bleu.UnicodeRegex", false]], "unpackedweightonlylinearparams (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.UnpackedWeightOnlyLinearParams", false]], "unpicklingerror": [[138, "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle.UnpicklingError", false], [397, "neural_compressor.torch.algorithms.layer_wise.modified_pickle.UnpicklingError", false]], "update_module() (in module neural_compressor.adaptor.torch_utils.layer_wise_quant.utils)": [[141, "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils.update_module", false]], "update_module() (in module neural_compressor.torch.algorithms.layer_wise.utils)": [[398, "neural_compressor.torch.algorithms.layer_wise.utils.update_module", false]], "update_params() (in module neural_compressor.compression.pruner.utils)": [[192, "neural_compressor.compression.pruner.utils.update_params", false]], "update_sq_scale() (in module neural_compressor.adaptor.torch_utils.util)": [[145, "neural_compressor.adaptor.torch_utils.util.update_sq_scale", false]], "update_sq_scale() (in module neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.update_sq_scale", false]], "valid_keras_format() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.valid_keras_format", false]], "valid_reshape_inputs() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.valid_reshape_inputs", false]], "valid_reshape_inputs() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.valid_reshape_inputs", false]], "valid_reshape_inputs() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.valid_reshape_inputs", false]], "valid_reshape_inputs() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.valid_reshape_inputs", false]], "validate_and_inference_input_output() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.validate_and_inference_input_output", false]], "validate_and_inference_input_output() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.validate_and_inference_input_output", false]], "validate_graph_node() (in module neural_compressor.model.tensorflow_model)": [[243, "neural_compressor.model.tensorflow_model.validate_graph_node", false]], "validate_graph_node() (in module neural_compressor.tensorflow.utils.model_wrappers)": [[390, "neural_compressor.tensorflow.utils.model_wrappers.validate_graph_node", false]], "valueinfo (class in neural_compressor.adaptor.ox_utils.util)": [[30, "neural_compressor.adaptor.ox_utils.util.ValueInfo", false]], "values_from_const() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn)": [[52, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn.values_from_const", false]], "values_from_const() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in)": [[53, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in.values_from_const", false]], "values_from_const() (in module neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm)": [[55, "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm.values_from_const", false]], "values_from_const() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn)": [[324, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn.values_from_const", false]], "values_from_const() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in)": [[325, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in.values_from_const", false]], "values_from_const() (in module neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm)": [[327, "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm.values_from_const", false]], "version1_eq_version2() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.version1_eq_version2", false]], "version1_eq_version2() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.version1_eq_version2", false]], "version1_eq_version2() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.version1_eq_version2", false]], "version1_gt_version2() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.version1_gt_version2", false]], "version1_gt_version2() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.version1_gt_version2", false]], "version1_gt_version2() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.version1_gt_version2", false]], "version1_gte_version2() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.version1_gte_version2", false]], "version1_gte_version2() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.version1_gte_version2", false]], "version1_gte_version2() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.version1_gte_version2", false]], "version1_lt_version2() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.version1_lt_version2", false]], "version1_lt_version2() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.version1_lt_version2", false]], "version1_lt_version2() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.version1_lt_version2", false]], "version1_lte_version2() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.version1_lte_version2", false]], "version1_lte_version2() (in module neural_compressor.tensorflow.utils.utility)": [[391, "neural_compressor.tensorflow.utils.utility.version1_lte_version2", false]], "version1_lte_version2() (in module neural_compressor.utils.utility)": [[465, "neural_compressor.utils.utility.version1_lte_version2", false]], "w8a8pt2equantizer (class in neural_compressor.torch.algorithms.pt2e_quant.core)": [[405, "neural_compressor.torch.algorithms.pt2e_quant.core.W8A8PT2EQuantizer", false]], "warn() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.warn", false]], "warning() (in module neural_compressor.utils.logger)": [[462, "neural_compressor.utils.logger.warning", false]], "weightcorrection (class in neural_compressor.algorithm.weight_correction)": [[150, "neural_compressor.algorithm.weight_correction.WeightCorrection", false]], "weightonlylinear (class in neural_compressor.torch.algorithms.weight_only.modules)": [[429, "neural_compressor.torch.algorithms.weight_only.modules.WeightOnlyLinear", false]], "weightonlyquantsampler (class in neural_compressor.strategy.utils.tuning_sampler)": [[277, "neural_compressor.strategy.utils.tuning_sampler.WeightOnlyQuantSampler", false]], "weightpruningconfig (class in neural_compressor.config)": [[195, "neural_compressor.config.WeightPruningConfig", false]], "weightsdetails (class in neural_compressor.utils.weights_details)": [[466, "neural_compressor.utils.weights_details.WeightsDetails", false]], "weightsstatistics (class in neural_compressor.utils.weights_details)": [[466, "neural_compressor.utils.weights_details.WeightsStatistics", false]], "whitespace_tokenize() (in module neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.whitespace_tokenize", false]], "woqmodelloader (class in neural_compressor.torch.algorithms.weight_only.save_load)": [[431, "neural_compressor.torch.algorithms.weight_only.save_load.WOQModelLoader", false]], "wordpiecetokenizer (class in neural_compressor.data.transforms.tokenization)": [[224, "neural_compressor.data.transforms.tokenization.WordpieceTokenizer", false]], "wrapmxnetmetric (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.WrapMXNetMetric", false]], "wraponnxrtmetric (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.WrapONNXRTMetric", false]], "wrapperlayer (class in neural_compressor.torch.algorithms.smooth_quant.utility)": [[413, "neural_compressor.torch.algorithms.smooth_quant.utility.WrapperLayer", false]], "wrappytorchmetric (class in neural_compressor.metric.metric)": [[234, "neural_compressor.metric.metric.WrapPyTorchMetric", false]], "write_graph() (in module neural_compressor.adaptor.tf_utils.util)": [[133, "neural_compressor.adaptor.tf_utils.util.write_graph", false]], "write_graph() (in module neural_compressor.tensorflow.quantization.utils.utility)": [[385, "neural_compressor.tensorflow.quantization.utils.utility.write_graph", false]], "xpu_accelerator (class in neural_compressor.torch.utils.auto_accelerator)": [[443, "neural_compressor.torch.utils.auto_accelerator.XPU_Accelerator", false]]}, "objects": {"": [[226, 0, 0, "-", "neural_compressor"]], "neural_compressor": [[148, 0, 0, "-", "algorithm"], [151, 0, 0, "-", "benchmark"], [155, 0, 0, "-", "common"], [195, 0, 0, "-", "config"], [196, 0, 0, "-", "contrib"], [220, 0, 0, "-", "data"], [233, 0, 0, "-", "metric"], [235, 0, 0, "-", "mix_precision"], [237, 0, 0, "-", "model"], [245, 0, 0, "-", "objective"], [246, 0, 0, "-", "profiling"], [262, 0, 0, "-", "quantization"], [270, 0, 0, "-", "strategy"], [290, 0, 0, "-", "tensorflow"], [436, 0, 0, "-", "torch"], [448, 0, 0, "-", "training"], [459, 0, 0, "-", "utils"], [467, 0, 0, "-", "version"]], "neural_compressor.adaptor": [[0, 0, 0, "-", "mxnet_utils"], [4, 0, 0, "-", "ox_utils"], [32, 0, 0, "-", "tensorflow"], [96, 0, 0, "-", "tf_utils"], [136, 0, 0, "-", "torch_utils"]], "neural_compressor.adaptor.mxnet_utils": [[1, 0, 0, "-", "util"]], "neural_compressor.adaptor.mxnet_utils.util": [[1, 1, 1, "", "CalibCollector"], [1, 1, 1, "", "CalibData"], [1, 1, 1, "", "CollectorBase"], [1, 1, 1, "", "DataIterLoader"], [1, 1, 1, "", "DataLoaderWrap"], [1, 1, 1, "", "NameCollector"], [1, 1, 1, "", "OpType"], [1, 1, 1, "", "TensorCollector"], [1, 2, 1, "", "amp_convert"], [1, 2, 1, "", "calib_model"], [1, 2, 1, "", "check_mx_version"], [1, 2, 1, "", "combine_capabilities"], [1, 2, 1, "", "create_data_example"], [1, 2, 1, "", "distribute_calib_tensors"], [1, 2, 1, "", "ensure_list"], [1, 2, 1, "", "fuse"], [1, 2, 1, "", "get_framework_name"], [1, 2, 1, "", "is_model_quantized"], [1, 2, 1, "", "isiterable"], [1, 2, 1, "", "make_module"], [1, 2, 1, "", "make_nc_model"], [1, 2, 1, "", "make_symbol_block"], [1, 2, 1, "", "ndarray_to_device"], [1, 2, 1, "", "parse_tune_config"], [1, 2, 1, "", "prepare_dataloader"], [1, 2, 1, "", "prepare_model"], [1, 2, 1, "", "prepare_model_data"], [1, 2, 1, "", "quantize_sym_model"], [1, 2, 1, "", "query_quantizable_nodes"], [1, 2, 1, "", "run_forward"]], "neural_compressor.adaptor.ox_utils": [[2, 0, 0, "-", "calibration"], [3, 0, 0, "-", "calibrator"], [16, 0, 0, "-", "operators"], [28, 0, 0, "-", "quantizer"], [29, 0, 0, "-", "smooth_quant"], [30, 0, 0, "-", "util"], [31, 0, 0, "-", "weight_only"]], "neural_compressor.adaptor.ox_utils.calibration": [[2, 1, 1, "", "ONNXRTAugment"]], "neural_compressor.adaptor.ox_utils.calibrator": [[3, 1, 1, "", "CalibratorBase"], [3, 1, 1, "", "HistogramCollector"], [3, 1, 1, "", "KLCalibrator"], [3, 1, 1, "", "MinMaxCalibrator"], [3, 1, 1, "", "PercentileCalibrator"], [3, 2, 1, "", "calib_registry"], [3, 2, 1, "", "smooth_distribution"]], "neural_compressor.adaptor.ox_utils.operators": [[5, 0, 0, "-", "activation"], [6, 0, 0, "-", "argmax"], [7, 0, 0, "-", "attention"], [8, 0, 0, "-", "binary_op"], [9, 0, 0, "-", "concat"], [10, 0, 0, "-", "conv"], [11, 0, 0, "-", "direct_q8"], [12, 0, 0, "-", "embed_layernorm"], [13, 0, 0, "-", "gather"], [14, 0, 0, "-", "gavgpool"], [15, 0, 0, "-", "gemm"], [17, 0, 0, "-", "lstm"], [18, 0, 0, "-", "matmul"], [19, 0, 0, "-", "maxpool"], [20, 0, 0, "-", "norm"], [21, 0, 0, "-", "ops"], [22, 0, 0, "-", "pad"], [23, 0, 0, "-", "pooling"], [24, 0, 0, "-", "reduce"], [25, 0, 0, "-", "resize"], [26, 0, 0, "-", "split"], [27, 0, 0, "-", "unary_op"]], "neural_compressor.adaptor.ox_utils.operators.activation": [[5, 1, 1, "", "ActivationOperator"], [5, 1, 1, "", "Float16ActivationOperator"], [5, 1, 1, "", "QActivationOperator"], [5, 1, 1, "", "RemovableActivationOperator"]], "neural_compressor.adaptor.ox_utils.operators.argmax": [[6, 1, 1, "", "ArgMaxOperator"], [6, 1, 1, "", "QArgMaxOperator"]], "neural_compressor.adaptor.ox_utils.operators.attention": [[7, 1, 1, "", "AttentionOperator"], [7, 1, 1, "", "QAttentionOperator"]], "neural_compressor.adaptor.ox_utils.operators.binary_op": [[8, 1, 1, "", "BinaryDirect8BitOperator"], [8, 1, 1, "", "BinaryOperator"], [8, 1, 1, "", "Float16BinaryOperator"], [8, 1, 1, "", "QBinaryOperator"]], "neural_compressor.adaptor.ox_utils.operators.concat": [[9, 1, 1, "", "ConcatOperator"], [9, 1, 1, "", "QConcatOperator"]], "neural_compressor.adaptor.ox_utils.operators.conv": [[10, 1, 1, "", "ConvOperator"], [10, 1, 1, "", "QConvOperator"]], "neural_compressor.adaptor.ox_utils.operators.direct_q8": [[11, 1, 1, "", "Direct8BitOperator"], [11, 1, 1, "", "QDirectOperator"]], "neural_compressor.adaptor.ox_utils.operators.embed_layernorm": [[12, 1, 1, "", "EmbedLayerNormalizationOperator"], [12, 1, 1, "", "QEmbedLayerNormalizationOperator"]], "neural_compressor.adaptor.ox_utils.operators.gather": [[13, 1, 1, "", "GatherOperator"], [13, 1, 1, "", "QGatherOperator"]], "neural_compressor.adaptor.ox_utils.operators.gavgpool": [[14, 1, 1, "", "GlobalAveragePoolOperator"], [14, 1, 1, "", "QGlobalAveragePoolOperator"]], "neural_compressor.adaptor.ox_utils.operators.gemm": [[15, 1, 1, "", "GemmOperator"], [15, 1, 1, "", "QGemmOperator"]], "neural_compressor.adaptor.ox_utils.operators.lstm": [[17, 1, 1, "", "LSTMOperator"]], "neural_compressor.adaptor.ox_utils.operators.matmul": [[18, 1, 1, "", "FusedMatMulOperator"], [18, 1, 1, "", "MatMulOperator"], [18, 1, 1, "", "QMatMulOperator"]], "neural_compressor.adaptor.ox_utils.operators.maxpool": [[19, 1, 1, "", "MaxPoolOperator"], [19, 1, 1, "", "QMaxPoolOperator"]], "neural_compressor.adaptor.ox_utils.operators.norm": [[20, 1, 1, "", "BatchNormalizationOperator"], [20, 1, 1, "", "NormalizationOperator"]], "neural_compressor.adaptor.ox_utils.operators.ops": [[21, 1, 1, "", "Operator"], [21, 1, 1, "", "QOperator"], [21, 2, 1, "", "op_registry"], [21, 2, 1, "", "qop_registry"]], "neural_compressor.adaptor.ox_utils.operators.pad": [[22, 1, 1, "", "PadOperator"], [22, 1, 1, "", "QPadOperator"]], "neural_compressor.adaptor.ox_utils.operators.pooling": [[23, 1, 1, "", "PoolOperator"], [23, 1, 1, "", "QPoolOperator"]], "neural_compressor.adaptor.ox_utils.operators.reduce": [[24, 1, 1, "", "ReduceMinMaxOperator"], [24, 1, 1, "", "ReduceOperator"]], "neural_compressor.adaptor.ox_utils.operators.resize": [[25, 1, 1, "", "QResizeOperator"], [25, 1, 1, "", "ResizeOperator"]], "neural_compressor.adaptor.ox_utils.operators.split": [[26, 1, 1, "", "QSplitOperator"], [26, 1, 1, "", "SplitOperator"]], "neural_compressor.adaptor.ox_utils.operators.unary_op": [[27, 1, 1, "", "UnaryDirect8BitOperator"], [27, 1, 1, "", "UnaryOperator"]], "neural_compressor.adaptor.ox_utils.quantizer": [[28, 1, 1, "", "Quantizer"]], "neural_compressor.adaptor.ox_utils.smooth_quant": [[29, 1, 1, "", "ORTSmoothQuant"], [29, 2, 1, "", "get_quant_dequant_output"], [29, 2, 1, "", "make_sub_graph"], [29, 2, 1, "", "quant_dequant_data"]], "neural_compressor.adaptor.ox_utils.util": [[30, 1, 1, "", "QuantFormat"], [30, 1, 1, "", "QuantType"], [30, 1, 1, "", "QuantizationMode"], [30, 1, 1, "", "QuantizedInitializer"], [30, 1, 1, "", "QuantizedValue"], [30, 1, 1, "", "QuantizedValueType"], [30, 1, 1, "", "ValueInfo"], [30, 2, 1, "", "attribute_to_kwarg"], [30, 2, 1, "", "calculate_scale_zp"], [30, 2, 1, "", "cast_tensor"], [30, 2, 1, "", "collate_preds"], [30, 2, 1, "", "dequantize_data"], [30, 2, 1, "", "dequantize_data_with_scale_zero"], [30, 2, 1, "", "dtype_to_name"], [30, 2, 1, "", "find_by_name"], [30, 2, 1, "", "float_to_bfloat16"], [30, 2, 1, "", "float_to_float16"], [30, 2, 1, "", "get_node_original_name"], [30, 2, 1, "", "infer_shapes"], [30, 2, 1, "", "is_B_transposed"], [30, 2, 1, "", "make_dquant_node"], [30, 2, 1, "", "make_quant_node"], [30, 2, 1, "", "quantize_data"], [30, 2, 1, "", "quantize_data_per_channel"], [30, 2, 1, "", "quantize_data_with_scale_zero"], [30, 2, 1, "", "quantize_nparray"], [30, 2, 1, "", "remove_init_from_model_input"], [30, 2, 1, "", "simple_progress_bar"], [30, 2, 1, "", "split_shared_bias"], [30, 2, 1, "", "to_numpy"], [30, 2, 1, "", "trt_env_setup"]], "neural_compressor.adaptor.ox_utils.weight_only": [[31, 2, 1, "", "apply_awq_clip"], [31, 2, 1, "", "apply_awq_scale"], [31, 2, 1, "", "awq_quantize"], [31, 2, 1, "", "get_blob_size"], [31, 2, 1, "", "get_weight_scale"], [31, 2, 1, "", "gptq"], [31, 2, 1, "", "gptq_quantize"], [31, 2, 1, "", "make_matmul_weight_only_node"], [31, 2, 1, "", "pad_tensor"], [31, 2, 1, "", "prepare_inputs"], [31, 2, 1, "", "qdq_tensor"], [31, 2, 1, "", "quant_tensor"], [31, 2, 1, "", "rtn_quantize"]], "neural_compressor.adaptor.tensorflow": [[32, 1, 1, "", "TensorFlowAdaptor"], [32, 1, 1, "", "TensorflowQuery"], [32, 1, 1, "", "Tensorflow_ITEXAdaptor"]], "neural_compressor.adaptor.tf_utils": [[33, 0, 0, "-", "graph_converter"], [34, 0, 0, "-", "graph_converter_without_calib"], [72, 0, 0, "-", "graph_rewriter"], [95, 0, 0, "-", "graph_util"], [97, 0, 0, "-", "quantize_graph"], [124, 0, 0, "-", "quantize_graph_common"], [125, 0, 0, "-", "smooth_quant_calibration"], [126, 0, 0, "-", "smooth_quant_scaler"], [127, 0, 0, "-", "tf2onnx_converter"], [130, 0, 0, "-", "transform_graph"], [133, 0, 0, "-", "util"]], "neural_compressor.adaptor.tf_utils.graph_converter": [[33, 1, 1, "", "GraphConverter"]], "neural_compressor.adaptor.tf_utils.graph_converter_without_calib": [[34, 1, 1, "", "GraphConverterWithoutCalib"]], "neural_compressor.adaptor.tf_utils.graph_rewriter": [[37, 0, 0, "-", "bf16"], [61, 0, 0, "-", "generic"], [71, 0, 0, "-", "graph_base"], [80, 0, 0, "-", "int8"], [86, 0, 0, "-", "onnx"], [91, 0, 0, "-", "qdq"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16": [[35, 0, 0, "-", "bf16_convert"], [36, 0, 0, "-", "dequantize_cast_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert": [[35, 1, 1, "", "BF16Convert"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer": [[36, 1, 1, "", "DequantizeCastOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic": [[38, 0, 0, "-", "convert_add_to_biasadd"], [39, 0, 0, "-", "convert_layout"], [40, 0, 0, "-", "convert_leakyrelu"], [41, 0, 0, "-", "convert_nan_to_random"], [42, 0, 0, "-", "convert_placeholder_to_const"], [43, 0, 0, "-", "dilated_contraction"], [44, 0, 0, "-", "dummy_biasadd"], [45, 0, 0, "-", "expanddims_optimizer"], [46, 0, 0, "-", "fetch_weight_from_reshape"], [47, 0, 0, "-", "fold_batch_norm"], [48, 0, 0, "-", "fold_constant"], [49, 0, 0, "-", "fuse_biasadd_add"], [50, 0, 0, "-", "fuse_column_wise_mul"], [51, 0, 0, "-", "fuse_conv_with_math"], [52, 0, 0, "-", "fuse_decomposed_bn"], [53, 0, 0, "-", "fuse_decomposed_in"], [54, 0, 0, "-", "fuse_gelu"], [55, 0, 0, "-", "fuse_layer_norm"], [56, 0, 0, "-", "fuse_pad_with_conv"], [57, 0, 0, "-", "fuse_pad_with_fp32_conv"], [58, 0, 0, "-", "fuse_reshape_transpose"], [59, 0, 0, "-", "graph_cse_optimizer"], [60, 0, 0, "-", "grappler_pass"], [62, 0, 0, "-", "insert_print_node"], [63, 0, 0, "-", "move_squeeze_after_relu"], [64, 0, 0, "-", "pre_optimize"], [65, 0, 0, "-", "remove_training_nodes"], [66, 0, 0, "-", "rename_batch_norm"], [67, 0, 0, "-", "split_shared_input"], [68, 0, 0, "-", "strip_equivalent_nodes"], [69, 0, 0, "-", "strip_unused_nodes"], [70, 0, 0, "-", "switch_optimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd": [[38, 1, 1, "", "ConvertAddToBiasAddOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout": [[39, 1, 1, "", "ConvertLayoutOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu": [[40, 1, 1, "", "ConvertLeakyReluOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random": [[41, 1, 1, "", "ConvertNanToRandom"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const": [[42, 1, 1, "", "ConvertPlaceholderToConst"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction": [[43, 1, 1, "", "DilatedContraction"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd": [[44, 1, 1, "", "InjectDummyBiasAddOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer": [[45, 1, 1, "", "ExpandDimsOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape": [[46, 1, 1, "", "FetchWeightFromReshapeOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm": [[47, 1, 1, "", "FoldBatchNormNodesOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant": [[48, 1, 1, "", "GraphFoldConstantOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add": [[49, 1, 1, "", "FuseBiasAddAndAddOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul": [[50, 1, 1, "", "FuseColumnWiseMulOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math": [[51, 1, 1, "", "FuseConvWithMathOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn": [[52, 1, 1, "", "FuseDecomposedBNOptimizer"], [52, 2, 1, "", "bypass_reshape"], [52, 2, 1, "", "get_const_dim_count"], [52, 2, 1, "", "node_from_map"], [52, 2, 1, "", "node_name_from_input"], [52, 2, 1, "", "valid_reshape_inputs"], [52, 2, 1, "", "values_from_const"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in": [[53, 1, 1, "", "FuseDecomposedINOptimizer"], [53, 2, 1, "", "bypass_reshape"], [53, 2, 1, "", "get_const_dim_count"], [53, 2, 1, "", "node_from_map"], [53, 2, 1, "", "node_name_from_input"], [53, 2, 1, "", "valid_reshape_inputs"], [53, 2, 1, "", "values_from_const"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu": [[54, 1, 1, "", "FuseGeluOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm": [[55, 1, 1, "", "FuseLayerNormOptimizer"], [55, 2, 1, "", "node_from_map"], [55, 2, 1, "", "node_name_from_input"], [55, 2, 1, "", "values_from_const"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv": [[56, 1, 1, "", "FusePadWithConv2DOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv": [[57, 1, 1, "", "FusePadWithFP32Conv2DOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose": [[58, 1, 1, "", "FuseTransposeReshapeOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer": [[59, 1, 1, "", "GraphCseOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass": [[60, 1, 1, "", "GrapplerOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node": [[62, 1, 1, "", "InsertPrintMinMaxNode"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu": [[63, 1, 1, "", "MoveSqueezeAfterReluOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize": [[64, 1, 1, "", "PreOptimization"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes": [[65, 1, 1, "", "RemoveTrainingNodesOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm": [[66, 1, 1, "", "RenameBatchNormOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input": [[67, 1, 1, "", "SplitSharedInputOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes": [[68, 1, 1, "", "StripEquivalentNodesOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes": [[69, 1, 1, "", "StripUnusedNodesOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer": [[70, 1, 1, "", "SwitchOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base": [[71, 1, 1, "", "GraphRewriterBase"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8": [[73, 0, 0, "-", "freeze_fake_quant"], [74, 0, 0, "-", "freeze_value"], [75, 0, 0, "-", "freeze_value_without_calib"], [76, 0, 0, "-", "fuse_conv_redundant_dequantize"], [77, 0, 0, "-", "fuse_conv_requantize"], [78, 0, 0, "-", "fuse_matmul_redundant_dequantize"], [79, 0, 0, "-", "fuse_matmul_requantize"], [81, 0, 0, "-", "meta_op_optimizer"], [82, 0, 0, "-", "post_hostconst_converter"], [83, 0, 0, "-", "post_quantized_op_cse"], [84, 0, 0, "-", "rnn_convert"], [85, 0, 0, "-", "scale_propagation"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant": [[73, 1, 1, "", "FreezeFakeQuantOpOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value": [[74, 1, 1, "", "FreezeValueTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib": [[75, 1, 1, "", "FreezeValueWithoutCalibTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize": [[76, 1, 1, "", "FuseConvRedundantDequantizeTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize": [[77, 1, 1, "", "FuseConvRequantizeTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize": [[78, 1, 1, "", "FuseMatMulRedundantDequantizeTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize": [[79, 1, 1, "", "FuseMatMulRequantizeDequantizeNewAPITransformer"], [79, 1, 1, "", "FuseMatMulRequantizeDequantizeTransformer"], [79, 1, 1, "", "FuseMatMulRequantizeNewAPITransformer"], [79, 1, 1, "", "FuseMatMulRequantizeTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer": [[81, 1, 1, "", "MetaInfoChangingMemOpOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter": [[82, 1, 1, "", "PostHostConstConverter"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse": [[83, 1, 1, "", "PostCseOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert": [[84, 1, 1, "", "QuantizedRNNConverter"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation": [[85, 1, 1, "", "ScaleProPagationTransformer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx": [[87, 0, 0, "-", "onnx_graph"], [88, 0, 0, "-", "onnx_node"], [89, 0, 0, "-", "onnx_schema"], [90, 0, 0, "-", "tf2onnx_utils"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph": [[87, 1, 1, "", "OnnxGraph"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node": [[88, 1, 1, "", "OnnxNode"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema": [[89, 1, 1, "", "OnnxOpSchema"], [89, 2, 1, "", "get_max_supported_opset_version"], [89, 2, 1, "", "get_schema"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils": [[90, 1, 1, "", "SeqType"], [90, 2, 1, "", "add_port_to_name"], [90, 2, 1, "", "are_shapes_equal"], [90, 2, 1, "", "assert_error"], [90, 2, 1, "", "compute_const_folding_using_tf"], [90, 2, 1, "", "convert_tensorflow_tensor_to_onnx"], [90, 2, 1, "", "find_opset"], [90, 2, 1, "", "get_index_from_strided_slice_of_shape"], [90, 2, 1, "", "get_subgraphs_from_onnx"], [90, 2, 1, "", "get_tensorflow_node_attr"], [90, 2, 1, "", "get_tensorflow_node_shape_attr"], [90, 2, 1, "", "get_tensorflow_tensor_data"], [90, 2, 1, "", "get_tensorflow_tensor_shape"], [90, 2, 1, "", "infer_onnx_shape_dtype"], [90, 2, 1, "", "initialize_name_counter"], [90, 2, 1, "", "is_list_or_tuple"], [90, 2, 1, "", "is_onnx_domain"], [90, 2, 1, "", "make_onnx_inputs_outputs"], [90, 2, 1, "", "make_onnx_shape"], [90, 2, 1, "", "map_numpy_to_onnx_dtype"], [90, 2, 1, "", "map_onnx_to_numpy_type"], [90, 2, 1, "", "map_tensorflow_dtype"], [90, 2, 1, "", "read_tensorflow_node_attrs"], [90, 2, 1, "", "save_protobuf"], [90, 2, 1, "", "set_name"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq": [[92, 0, 0, "-", "insert_qdq_pattern"], [93, 0, 0, "-", "merge_duplicated_qdq"], [94, 0, 0, "-", "share_qdq_y_pattern"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern": [[92, 1, 1, "", "GenerateGraphWithQDQPattern"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq": [[93, 1, 1, "", "MergeDuplicatedQDQOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern": [[94, 1, 1, "", "ShareQDQForItexYPatternOptimizer"]], "neural_compressor.adaptor.tf_utils.graph_util": [[95, 1, 1, "", "GraphAnalyzer"], [95, 1, 1, "", "GraphRewriterHelper"]], "neural_compressor.adaptor.tf_utils.quantize_graph": [[99, 0, 0, "-", "qat"], [115, 0, 0, "-", "qdq"], [117, 0, 0, "-", "quantize_graph_base"], [118, 0, 0, "-", "quantize_graph_bn"], [119, 0, 0, "-", "quantize_graph_concatv2"], [120, 0, 0, "-", "quantize_graph_conv"], [121, 0, 0, "-", "quantize_graph_for_intel_cpu"], [122, 0, 0, "-", "quantize_graph_matmul"], [123, 0, 0, "-", "quantize_graph_pooling"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat": [[98, 0, 0, "-", "fake_quantize"], [100, 0, 0, "-", "quantize_config"], [101, 0, 0, "-", "quantize_helper"], [102, 0, 0, "-", "quantize_layers"], [107, 0, 0, "-", "quantize_wrapper"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize": [[98, 1, 1, "", "FakeQuantize"], [98, 1, 1, "", "FakeQuantizeBase"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config": [[100, 1, 1, "", "QuantizeConfig"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper": [[101, 2, 1, "", "init_quantize_config"], [101, 2, 1, "", "qat_clone_function"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers": [[103, 0, 0, "-", "optimize_layer"], [104, 0, 0, "-", "quantize_layer_add"], [105, 0, 0, "-", "quantize_layer_base"], [106, 0, 0, "-", "quantize_layer_bn"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer": [[103, 2, 1, "", "config_quantizable_layers"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add": [[104, 1, 1, "", "QuantizeLayerAdd"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base": [[105, 1, 1, "", "QuantizeLayerBase"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn": [[106, 1, 1, "", "QuantizeLayerBatchNormalization"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper": [[107, 1, 1, "", "QuantizeWrapper"], [107, 1, 1, "", "QuantizeWrapperBase"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq": [[108, 0, 0, "-", "fuse_qdq_bn"], [109, 0, 0, "-", "fuse_qdq_concatv2"], [110, 0, 0, "-", "fuse_qdq_conv"], [111, 0, 0, "-", "fuse_qdq_deconv"], [112, 0, 0, "-", "fuse_qdq_in"], [113, 0, 0, "-", "fuse_qdq_matmul"], [114, 0, 0, "-", "fuse_qdq_pooling"], [116, 0, 0, "-", "optimize_qdq"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn": [[108, 1, 1, "", "FuseNodeStartWithFusedBatchNormV3"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2": [[109, 1, 1, "", "FuseNodeStartWithConcatV2"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv": [[110, 1, 1, "", "FuseNodeStartWithConv2d"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv": [[111, 1, 1, "", "FuseNodeStartWithDeconv2d"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in": [[112, 1, 1, "", "FuseNodeStartWithFusedInstanceNorm"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul": [[113, 1, 1, "", "FuseNodeStartWithMatmul"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling": [[114, 1, 1, "", "FuseNodeStartWithPooling"]], "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq": [[116, 1, 1, "", "OptimizeQDQGraph"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base": [[117, 1, 1, "", "QuantizeGraphBase"], [117, 1, 1, "", "QuantizeNodeBase"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn": [[118, 1, 1, "", "FuseNodeStartWithFusedBatchNormV3"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2": [[119, 1, 1, "", "FuseNodeStartWithConcatV2"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv": [[120, 1, 1, "", "FuseNodeStartWithConv2d"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu": [[121, 1, 1, "", "QuantizeGraphForIntel"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul": [[122, 1, 1, "", "FuseNodeStartWithMatmul"]], "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling": [[123, 1, 1, "", "FuseNodeStartWithPooling"]], "neural_compressor.adaptor.tf_utils.quantize_graph_common": [[124, 1, 1, "", "QuantizeGraphHelper"]], "neural_compressor.adaptor.tf_utils.smooth_quant_calibration": [[125, 1, 1, "", "SmoothQuantCalibration"], [125, 1, 1, "", "SmoothQuantCalibrationLLM"]], "neural_compressor.adaptor.tf_utils.smooth_quant_scaler": [[126, 1, 1, "", "SmoothQuantScaler"], [126, 1, 1, "", "SmoothQuantScalerLLM"]], "neural_compressor.adaptor.tf_utils.tf2onnx_converter": [[127, 1, 1, "", "TensorflowQDQToOnnxQDQConverter"]], "neural_compressor.adaptor.tf_utils.transform_graph": [[128, 0, 0, "-", "bias_correction"], [129, 0, 0, "-", "graph_transform_base"], [131, 0, 0, "-", "insert_logging"], [132, 0, 0, "-", "rerange_quantized_concat"]], "neural_compressor.adaptor.tf_utils.transform_graph.bias_correction": [[128, 1, 1, "", "BiasCorrection"]], "neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base": [[129, 1, 1, "", "GraphTransformBase"]], "neural_compressor.adaptor.tf_utils.transform_graph.insert_logging": [[131, 1, 1, "", "InsertLogging"]], "neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat": [[132, 1, 1, "", "RerangeQuantizedConcat"]], "neural_compressor.adaptor.tf_utils.util": [[133, 2, 1, "", "apply_inlining"], [133, 2, 1, "", "collate_tf_preds"], [133, 2, 1, "", "construct_function_from_graph_def"], [133, 2, 1, "", "disable_random"], [133, 2, 1, "", "fix_ref_type_of_graph_def"], [133, 2, 1, "", "generate_feed_dict"], [133, 2, 1, "", "get_estimator_graph"], [133, 2, 1, "", "get_graph_def"], [133, 2, 1, "", "get_input_output_node_names"], [133, 2, 1, "", "get_model_input_shape"], [133, 2, 1, "", "get_tensor_by_name"], [133, 2, 1, "", "get_tensor_val_from_graph_node"], [133, 2, 1, "", "get_weight_from_input_tensor"], [133, 2, 1, "", "int8_node_name_reverse"], [133, 2, 1, "", "is_ckpt_format"], [133, 2, 1, "", "is_saved_model_format"], [133, 2, 1, "", "iterator_sess_run"], [133, 2, 1, "", "parse_saved_model"], [133, 2, 1, "", "read_graph"], [133, 2, 1, "", "reconstruct_saved_model"], [133, 2, 1, "", "strip_equivalent_nodes"], [133, 2, 1, "", "strip_unused_nodes"], [133, 2, 1, "", "version1_eq_version2"], [133, 2, 1, "", "version1_gt_version2"], [133, 2, 1, "", "version1_gte_version2"], [133, 2, 1, "", "version1_lt_version2"], [133, 2, 1, "", "version1_lte_version2"], [133, 2, 1, "", "write_graph"]], "neural_compressor.adaptor.torch_utils": [[134, 0, 0, "-", "bf16_convert"], [135, 0, 0, "-", "hawq_metric"], [137, 0, 0, "-", "layer_wise_quant"], [142, 0, 0, "-", "model_wrapper"], [143, 0, 0, "-", "pattern_detector"], [144, 0, 0, "-", "symbolic_trace"], [145, 0, 0, "-", "util"]], "neural_compressor.adaptor.torch_utils.bf16_convert": [[134, 1, 1, "", "BF16ModuleWrapper"], [134, 2, 1, "", "Convert"]], "neural_compressor.adaptor.torch_utils.hawq_metric": [[135, 1, 1, "", "HessianTrace"], [135, 1, 1, "", "Node_collector"], [135, 2, 1, "", "compare_weights"], [135, 2, 1, "", "hawq_top"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant": [[138, 0, 0, "-", "modified_pickle"], [139, 0, 0, "-", "quantize"], [140, 0, 0, "-", "torch_load"], [141, 0, 0, "-", "utils"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle": [[138, 3, 1, "", "PickleError"], [138, 3, 1, "", "PicklingError"], [138, 3, 1, "", "UnpicklingError"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize": [[139, 1, 1, "", "LayerWiseQuant"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load": [[140, 2, 1, "", "load"]], "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils": [[141, 2, 1, "", "dowload_hf_model"], [141, 2, 1, "", "get_children"], [141, 2, 1, "", "get_module"], [141, 2, 1, "", "get_named_children"], [141, 2, 1, "", "get_super_module_by_name"], [141, 2, 1, "", "load_empty_model"], [141, 2, 1, "", "load_layer_wise_quantized_model"], [141, 2, 1, "", "load_tensor"], [141, 2, 1, "", "load_tensor_from_shard"], [141, 2, 1, "", "update_module"]], "neural_compressor.adaptor.torch_utils.model_wrapper": [[142, 1, 1, "", "FakeAffineTensorQuantFunction"], [142, 1, 1, "", "MulLinear"], [142, 1, 1, "", "TEQLinearFakeQuant"]], "neural_compressor.adaptor.torch_utils.pattern_detector": [[143, 1, 1, "", "TransformerBasedModelBlockPatternDetector"]], "neural_compressor.adaptor.torch_utils.symbolic_trace": [[144, 2, 1, "", "symbolic_trace"], [144, 2, 1, "", "trace_and_fuse_sub_graph"]], "neural_compressor.adaptor.torch_utils.util": [[145, 2, 1, "", "append_attr"], [145, 2, 1, "", "auto_copy"], [145, 2, 1, "", "calculate_quant_min_max"], [145, 2, 1, "", "calibration"], [145, 2, 1, "", "check_cfg_and_qconfig"], [145, 2, 1, "", "collate_torch_preds"], [145, 2, 1, "", "collect_weight_info"], [145, 2, 1, "", "fetch_module"], [145, 2, 1, "", "forward_wrapper"], [145, 2, 1, "", "generate_activation_observer"], [145, 2, 1, "", "get_absorb_layers"], [145, 2, 1, "", "get_block_prefix"], [145, 2, 1, "", "get_depth"], [145, 2, 1, "", "get_dict_at_depth"], [145, 2, 1, "", "get_element_under_depth"], [145, 2, 1, "", "get_embedding_contiguous"], [145, 2, 1, "", "get_example_input"], [145, 2, 1, "", "get_fallback_order"], [145, 2, 1, "", "get_hidden_states"], [145, 2, 1, "", "get_module_input_output"], [145, 2, 1, "", "get_mse_order_per_fp32"], [145, 2, 1, "", "get_mse_order_per_int8"], [145, 2, 1, "", "get_op_type_by_name"], [145, 2, 1, "", "get_quantizable_ops_from_cfgs"], [145, 2, 1, "", "get_torch_version"], [145, 2, 1, "", "input2tuple"], [145, 2, 1, "", "is_fused_module"], [145, 2, 1, "", "match_datatype_pattern"], [145, 2, 1, "", "move_input_device"], [145, 2, 1, "", "paser_cfgs"], [145, 2, 1, "", "set_module"], [145, 2, 1, "", "simple_inference"], [145, 2, 1, "", "update_sq_scale"]], "neural_compressor.algorithm": [[146, 0, 0, "-", "algorithm"], [147, 0, 0, "-", "fast_bias_correction"], [149, 0, 0, "-", "smooth_quant"], [150, 0, 0, "-", "weight_correction"]], "neural_compressor.algorithm.algorithm": [[146, 1, 1, "", "ALGORITHMS"], [146, 1, 1, "", "Algorithm"], [146, 1, 1, "", "AlgorithmScheduler"], [146, 2, 1, "", "algorithm_registry"]], "neural_compressor.algorithm.fast_bias_correction": [[147, 1, 1, "", "FastBiasCorrection"]], "neural_compressor.algorithm.smooth_quant": [[149, 1, 1, "", "SmoothQuant"]], "neural_compressor.algorithm.weight_correction": [[150, 1, 1, "", "WeightCorrection"]], "neural_compressor.benchmark": [[151, 2, 1, "", "benchmark_with_raw_cmd"], [151, 2, 1, "", "call_one"], [151, 2, 1, "", "config_instance"], [151, 2, 1, "", "fit"], [151, 2, 1, "", "generate_prefix"], [151, 2, 1, "", "get_architecture"], [151, 2, 1, "", "get_bounded_threads"], [151, 2, 1, "", "get_core_ids"], [151, 2, 1, "", "get_physical_ids"], [151, 2, 1, "", "get_threads"], [151, 2, 1, "", "get_threads_per_core"], [151, 2, 1, "", "profile"], [151, 2, 1, "", "run_instance"], [151, 2, 1, "", "set_all_env_var"], [151, 2, 1, "", "set_env_var"], [151, 2, 1, "", "summary_benchmark"]], "neural_compressor.common": [[152, 0, 0, "-", "base_config"], [153, 0, 0, "-", "base_tuning"], [154, 0, 0, "-", "benchmark"], [156, 0, 0, "-", "tuning_param"], [158, 0, 0, "-", "utils"]], "neural_compressor.common.base_config": [[152, 1, 1, "", "BaseConfig"], [152, 1, 1, "", "ComposableConfig"], [152, 1, 1, "", "ConfigRegistry"], [152, 2, 1, "", "get_all_config_set_from_config_registry"], [152, 2, 1, "", "register_config"], [152, 2, 1, "", "register_supported_configs_for_fwk"]], "neural_compressor.common.base_config.BaseConfig": [[152, 4, 1, "", "name"], [152, 4, 1, "", "params_list"]], "neural_compressor.common.base_config.ComposableConfig": [[152, 4, 1, "", "config_list"]], "neural_compressor.common.base_tuning": [[153, 1, 1, "", "ConfigLoader"], [153, 1, 1, "", "ConfigSet"], [153, 1, 1, "", "EvaluationFuncWrapper"], [153, 1, 1, "", "Evaluator"], [153, 1, 1, "", "Sampler"], [153, 1, 1, "", "SequentialSampler"], [153, 1, 1, "", "TuningConfig"], [153, 1, 1, "", "TuningMonitor"], [153, 2, 1, "", "init_tuning"]], "neural_compressor.common.base_tuning.ConfigSet": [[153, 4, 1, "", "config_list"]], "neural_compressor.common.benchmark": [[154, 2, 1, "", "benchmark"], [154, 2, 1, "", "dump_numa_info"], [154, 2, 1, "", "format_list2str"], [154, 2, 1, "", "generate_prefix"], [154, 2, 1, "", "get_linux_numa_info"], [154, 2, 1, "", "get_numa_node"], [154, 2, 1, "", "get_reversed_numa_info"], [154, 2, 1, "", "get_windows_numa_info"], [154, 2, 1, "", "parse_str2list"], [154, 2, 1, "", "run_multi_instance_command"], [154, 2, 1, "", "set_cores_for_instance"], [154, 2, 1, "", "summary_latency_throughput"]], "neural_compressor.common.tuning_param": [[156, 1, 1, "", "ParamLevel"], [156, 1, 1, "", "TuningParam"]], "neural_compressor.common.tuning_param.ParamLevel": [[156, 4, 1, "", "MODEL_LEVEL"], [156, 4, 1, "", "OP_LEVEL"], [156, 4, 1, "", "OP_TYPE_LEVEL"]], "neural_compressor.common.utils": [[157, 0, 0, "-", "constants"], [159, 0, 0, "-", "logger"], [160, 0, 0, "-", "save_load"], [161, 0, 0, "-", "utility"]], "neural_compressor.common.utils.constants": [[157, 1, 1, "", "Mode"]], "neural_compressor.common.utils.logger": [[159, 1, 1, "", "Logger"], [159, 1, 1, "", "TuningLogger"]], "neural_compressor.common.utils.save_load": [[160, 2, 1, "", "load_config_mapping"], [160, 2, 1, "", "save_config_mapping"]], "neural_compressor.common.utils.utility": [[161, 1, 1, "", "CpuInfo"], [161, 1, 1, "", "LazyImport"], [161, 1, 1, "", "ProcessorType"], [161, 1, 1, "", "Statistics"], [161, 2, 1, "", "call_counter"], [161, 2, 1, "", "detect_processor_type_based_on_hw"], [161, 2, 1, "", "dump_elapsed_time"], [161, 2, 1, "", "get_workspace"], [161, 2, 1, "", "log_process"], [161, 2, 1, "", "set_random_seed"], [161, 2, 1, "", "set_resume_from"], [161, 2, 1, "", "set_tensorboard"], [161, 2, 1, "", "set_workspace"], [161, 2, 1, "", "singleton"]], "neural_compressor.compression": [[162, 0, 0, "-", "callbacks"], [164, 0, 0, "-", "distillation"], [167, 0, 0, "-", "hpo"], [170, 0, 0, "-", "pruner"]], "neural_compressor.compression.callbacks": [[162, 1, 1, "", "BaseCallbacks"], [162, 1, 1, "", "DistillationCallbacks"], [162, 1, 1, "", "PruningCallbacks"], [162, 1, 1, "", "QuantizationAwareTrainingCallbacks"]], "neural_compressor.compression.callbacks.DistillationCallbacks": [[162, 4, 1, "", "_epoch_ran"], [162, 4, 1, "", "best_model"], [162, 4, 1, "", "best_score"], [162, 4, 1, "", "eval_frequency"]], "neural_compressor.compression.distillation": [[163, 0, 0, "-", "criterions"], [165, 0, 0, "-", "optimizers"], [166, 0, 0, "-", "utility"]], "neural_compressor.compression.distillation.criterions": [[163, 1, 1, "", "Criterions"], [163, 1, 1, "", "IntermediateLayersKnowledgeDistillationLoss"], [163, 1, 1, "", "KnowledgeDistillationFramework"], [163, 1, 1, "", "KnowledgeDistillationLoss"], [163, 1, 1, "", "PyTorchCriterions"], [163, 1, 1, "", "PyTorchCrossEntropyLoss"], [163, 1, 1, "", "PyTorchIntermediateLayersKnowledgeDistillationLoss"], [163, 1, 1, "", "PyTorchIntermediateLayersKnowledgeDistillationLossWrapper"], [163, 1, 1, "", "PyTorchKnowledgeDistillationLoss"], [163, 1, 1, "", "PyTorchKnowledgeDistillationLossWrapper"], [163, 1, 1, "", "PyTorchSelfKnowledgeDistillationLoss"], [163, 1, 1, "", "PyTorchSelfKnowledgeDistillationLossWrapper"], [163, 1, 1, "", "SelfKnowledgeDistillationLoss"], [163, 1, 1, "", "TensorFlowCrossEntropyLoss"], [163, 1, 1, "", "TensorFlowSparseCategoricalCrossentropy"], [163, 1, 1, "", "TensorflowCriterions"], [163, 1, 1, "", "TensorflowKnowledgeDistillationLoss"], [163, 1, 1, "", "TensorflowKnowledgeDistillationLossExternal"], [163, 1, 1, "", "TensorflowKnowledgeDistillationLossWrapper"], [163, 2, 1, "", "criterion_registry"]], "neural_compressor.compression.distillation.optimizers": [[165, 1, 1, "", "Optimizers"], [165, 1, 1, "", "PyTorchOptimizers"], [165, 1, 1, "", "PyTorchSGD"], [165, 1, 1, "", "TensorFlowAdam"], [165, 1, 1, "", "TensorFlowAdamW"], [165, 1, 1, "", "TensorFlowSGD"], [165, 1, 1, "", "TensorflowOptimizers"], [165, 2, 1, "", "optimizer_registry"]], "neural_compressor.compression.distillation.utility": [[166, 2, 1, "", "get_activation"], [166, 2, 1, "", "record_output"]], "neural_compressor.compression.hpo": [[168, 0, 0, "-", "sa_optimizer"]], "neural_compressor.compression.pruner": [[169, 0, 0, "-", "criteria"], [172, 0, 0, "-", "model_slim"], [176, 0, 0, "-", "patterns"], [170, 2, 1, "", "prepare_pruning"], [183, 0, 0, "-", "pruners"], [188, 0, 0, "-", "pruning"], [189, 0, 0, "-", "regs"], [170, 2, 1, "", "save"], [190, 0, 0, "-", "schedulers"], [191, 0, 0, "-", "tf_criteria"], [192, 0, 0, "-", "utils"], [193, 0, 0, "-", "wanda"]], "neural_compressor.compression.pruner.criteria": [[169, 1, 1, "", "BlockMaskCriterion"], [169, 1, 1, "", "GradientCriterion"], [169, 1, 1, "", "MagnitudeCriterion"], [169, 1, 1, "", "PruningCriterion"], [169, 1, 1, "", "RetrainFreeCriterion"], [169, 1, 1, "", "SnipCriterion"], [169, 1, 1, "", "SnipMomentumCriterion"], [169, 2, 1, "", "get_criterion"], [169, 2, 1, "", "register_criterion"]], "neural_compressor.compression.pruner.criteria.BlockMaskCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.criteria.GradientCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.criteria.MagnitudeCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.criteria.PruningCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.criteria.RetrainFreeCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.criteria.SnipCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.criteria.SnipMomentumCriterion": [[169, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.model_slim": [[171, 0, 0, "-", "auto_slim"], [173, 0, 0, "-", "pattern_analyzer"], [174, 0, 0, "-", "weight_slim"]], "neural_compressor.compression.pruner.model_slim.auto_slim": [[171, 2, 1, "", "generate_ffn2_pruning_config"], [171, 2, 1, "", "generate_mha_pruning_config"], [171, 2, 1, "", "model_slim"], [171, 2, 1, "", "model_slim_ffn2"], [171, 2, 1, "", "model_slim_mha"], [171, 2, 1, "", "parse_auto_slim_config"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer": [[173, 1, 1, "", "ClassifierHeadSearcher"], [173, 1, 1, "", "ClassifierHeadSearcherTF"], [173, 1, 1, "", "JitBasicSearcher"], [173, 1, 1, "", "Linear2LinearSearcher"], [173, 1, 1, "", "RecipeSearcher"], [173, 1, 1, "", "SelfMHASearcher"], [173, 2, 1, "", "get_attributes"], [173, 2, 1, "", "get_common_module"], [173, 2, 1, "", "print_iterables"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcher": [[173, 4, 1, "", "device"], [173, 4, 1, "", "flatten_static_graph"], [173, 4, 1, "", "model"], [173, 4, 1, "", "static_graph"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer.ClassifierHeadSearcherTF": [[173, 4, 1, "", "device"], [173, 4, 1, "", "flatten_static_graph"], [173, 4, 1, "", "model"], [173, 4, 1, "", "static_graph"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer.JitBasicSearcher": [[173, 4, 1, "", "device"], [173, 4, 1, "", "flatten_static_graph"], [173, 4, 1, "", "model"], [173, 4, 1, "", "searching_results"], [173, 4, 1, "", "static_graph"], [173, 4, 1, "", "target_layers"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer.Linear2LinearSearcher": [[173, 4, 1, "", "current_pattern"], [173, 4, 1, "", "device"], [173, 4, 1, "", "flatten_static_graph"], [173, 4, 1, "", "model"], [173, 4, 1, "", "searching_results"], [173, 4, 1, "", "static_graph"], [173, 4, 1, "", "target_layers"], [173, 4, 1, "", "target_op_lut"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer.RecipeSearcher": [[173, 4, 1, "", "model"], [173, 4, 1, "", "recipe"], [173, 4, 1, "", "searching_results"], [173, 4, 1, "", "targets"]], "neural_compressor.compression.pruner.model_slim.pattern_analyzer.SelfMHASearcher": [[173, 4, 1, "", "device"], [173, 4, 1, "", "flatten_static_graph"], [173, 4, 1, "", "model"], [173, 4, 1, "", "static_graph"]], "neural_compressor.compression.pruner.model_slim.weight_slim": [[174, 1, 1, "", "LinearCompression"], [174, 1, 1, "", "LinearCompressionIterator"], [174, 1, 1, "", "PostCompressionUtils"]], "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompression": [[174, 4, 1, "", "device"], [174, 4, 1, "", "layer_1"], [174, 4, 1, "", "layer_2"]], "neural_compressor.compression.pruner.model_slim.weight_slim.LinearCompressionIterator": [[174, 4, 1, "", "linear_patterns"]], "neural_compressor.compression.pruner.patterns": [[175, 0, 0, "-", "base"], [176, 2, 1, "", "get_pattern"], [177, 0, 0, "-", "mha"], [178, 0, 0, "-", "ninm"], [179, 0, 0, "-", "nxm"]], "neural_compressor.compression.pruner.patterns.base": [[175, 1, 1, "", "BasePattern"], [175, 1, 1, "", "KerasBasePattern"], [175, 1, 1, "", "PytorchBasePattern"], [175, 2, 1, "", "register_pattern"]], "neural_compressor.compression.pruner.patterns.base.BasePattern": [[175, 4, 1, "", "config"], [175, 4, 1, "", "invalid_layers"], [175, 4, 1, "", "is_global"], [175, 4, 1, "", "keep_mask_layers"], [175, 4, 1, "", "max_sparsity_ratio_per_op"], [175, 4, 1, "", "min_sparsity_ratio_per_op"], [175, 4, 1, "", "modules"], [175, 4, 1, "", "pattern"], [175, 4, 1, "", "target_sparsity"]], "neural_compressor.compression.pruner.patterns.base.KerasBasePattern": [[175, 4, 1, "", "config"], [175, 4, 1, "", "invalid_layers"], [175, 4, 1, "", "is_global"], [175, 4, 1, "", "keep_mask_layers"], [175, 4, 1, "", "max_sparsity_ratio_per_op"], [175, 4, 1, "", "min_sparsity_ratio_per_op"], [175, 4, 1, "", "modules"], [175, 4, 1, "", "pattern"], [175, 4, 1, "", "target_sparsity"]], "neural_compressor.compression.pruner.patterns.base.PytorchBasePattern": [[175, 4, 1, "", "config"], [175, 4, 1, "", "invalid_layers"], [175, 4, 1, "", "is_global"], [175, 4, 1, "", "keep_mask_layers"], [175, 4, 1, "", "max_sparsity_ratio_per_op"], [175, 4, 1, "", "min_sparsity_ratio_per_op"], [175, 4, 1, "", "modules"], [175, 4, 1, "", "pattern"], [175, 4, 1, "", "target_sparsity"]], "neural_compressor.compression.pruner.patterns.mha": [[177, 1, 1, "", "PatternMHA"]], "neural_compressor.compression.pruner.patterns.mha.PatternMHA": [[177, 4, 1, "", "M"], [177, 4, 1, "", "N"]], "neural_compressor.compression.pruner.patterns.ninm": [[178, 1, 1, "", "PytorchPatternNInM"]], "neural_compressor.compression.pruner.patterns.ninm.PytorchPatternNInM": [[178, 4, 1, "", "M"], [178, 4, 1, "", "N"]], "neural_compressor.compression.pruner.patterns.nxm": [[179, 1, 1, "", "KerasPatternNxM"], [179, 1, 1, "", "PytorchPatternNxM"]], "neural_compressor.compression.pruner.patterns.nxm.KerasPatternNxM": [[179, 4, 1, "", "block_size"]], "neural_compressor.compression.pruner.patterns.nxm.PytorchPatternNxM": [[179, 4, 1, "", "block_size"]], "neural_compressor.compression.pruner.pruners": [[180, 0, 0, "-", "base"], [181, 0, 0, "-", "basic"], [182, 0, 0, "-", "block_mask"], [183, 2, 1, "", "get_pruner"], [184, 0, 0, "-", "mha"], [183, 2, 1, "", "parse_valid_pruner_types"], [185, 0, 0, "-", "pattern_lock"], [186, 0, 0, "-", "progressive"], [187, 0, 0, "-", "retrain_free"]], "neural_compressor.compression.pruner.pruners.base": [[180, 1, 1, "", "BasePruner"], [180, 1, 1, "", "KerasBasePruner"], [180, 1, 1, "", "PytorchBasePruner"], [180, 2, 1, "", "register_pruner"]], "neural_compressor.compression.pruner.pruners.base.BasePruner": [[180, 4, 1, "", "config"], [180, 4, 1, "", "current_sparsity_ratio"], [180, 4, 1, "", "end_step"], [180, 4, 1, "", "global_step"], [180, 4, 1, "", "masks"], [180, 4, 1, "", "max_sparsity_ratio_per_op"], [180, 4, 1, "", "modules"], [180, 4, 1, "", "pattern"], [180, 4, 1, "", "pruning_frequency"], [180, 4, 1, "", "scheduler"], [180, 4, 1, "", "scores"], [180, 4, 1, "", "start_step"], [180, 4, 1, "", "target_sparsity_ratio"]], "neural_compressor.compression.pruner.pruners.base.KerasBasePruner": [[180, 4, 1, "", "config"], [180, 4, 1, "", "current_sparsity_ratio"], [180, 4, 1, "", "end_step"], [180, 4, 1, "", "global_step"], [180, 4, 1, "", "masks"], [180, 4, 1, "", "max_sparsity_ratio_per_op"], [180, 4, 1, "", "modules"], [180, 4, 1, "", "pattern"], [180, 4, 1, "", "pruning_frequency"], [180, 4, 1, "", "scheduler"], [180, 4, 1, "", "scores"], [180, 4, 1, "", "start_step"], [180, 4, 1, "", "target_sparsity_ratio"]], "neural_compressor.compression.pruner.pruners.base.PytorchBasePruner": [[180, 4, 1, "", "config"], [180, 4, 1, "", "current_sparsity_ratio"], [180, 4, 1, "", "end_step"], [180, 4, 1, "", "global_step"], [180, 4, 1, "", "masks"], [180, 4, 1, "", "max_sparsity_ratio_per_op"], [180, 4, 1, "", "modules"], [180, 4, 1, "", "pattern"], [180, 4, 1, "", "pruning_frequency"], [180, 4, 1, "", "scheduler"], [180, 4, 1, "", "scores"], [180, 4, 1, "", "start_step"], [180, 4, 1, "", "target_sparsity_ratio"]], "neural_compressor.compression.pruner.pruners.basic": [[181, 1, 1, "", "KerasBasicPruner"], [181, 1, 1, "", "PytorchBasicPruner"]], "neural_compressor.compression.pruner.pruners.basic.KerasBasicPruner": [[181, 4, 1, "", "criterion"], [181, 4, 1, "", "pattern"], [181, 4, 1, "", "reg"], [181, 4, 1, "", "scheduler"]], "neural_compressor.compression.pruner.pruners.basic.PytorchBasicPruner": [[181, 4, 1, "", "criterion"], [181, 4, 1, "", "pattern"], [181, 4, 1, "", "reg"], [181, 4, 1, "", "scheduler"]], "neural_compressor.compression.pruner.pruners.block_mask": [[182, 1, 1, "", "PytorchBlockMaskPruner"]], "neural_compressor.compression.pruner.pruners.block_mask.PytorchBlockMaskPruner": [[182, 4, 1, "", "criterion"], [182, 4, 1, "", "pattern"], [182, 4, 1, "", "reg"], [182, 4, 1, "", "scheduler"]], "neural_compressor.compression.pruner.pruners.mha": [[184, 1, 1, "", "PythonMultiheadAttentionPruner"]], "neural_compressor.compression.pruner.pruners.mha.PythonMultiheadAttentionPruner": [[184, 4, 1, "", "head_masks"], [184, 4, 1, "", "linear_layers"], [184, 4, 1, "", "mha_compressions"], [184, 4, 1, "", "mha_scores"]], "neural_compressor.compression.pruner.pruners.pattern_lock": [[185, 1, 1, "", "PytorchPatternLockPruner"]], "neural_compressor.compression.pruner.pruners.progressive": [[186, 1, 1, "", "PytorchProgressivePruner"]], "neural_compressor.compression.pruner.pruners.retrain_free": [[187, 1, 1, "", "PytorchRetrainFreePruner"]], "neural_compressor.compression.pruner.pruners.retrain_free.PytorchRetrainFreePruner": [[187, 4, 1, "", "criterion"], [187, 4, 1, "", "pattern"], [187, 4, 1, "", "reg"], [187, 4, 1, "", "scheduler"]], "neural_compressor.compression.pruner.pruning": [[188, 1, 1, "", "BasePruning"], [188, 1, 1, "", "BasicPruning"], [188, 1, 1, "", "RetrainFreePruning"], [188, 1, 1, "", "SparseGPTPruning"], [188, 2, 1, "", "register_pruning"]], "neural_compressor.compression.pruner.pruning.BasePruning": [[188, 4, 1, "", "config_file_path"], [188, 4, 1, "", "model"], [188, 4, 1, "", "pruner_info"], [188, 4, 1, "", "pruners"]], "neural_compressor.compression.pruner.pruning.BasicPruning": [[188, 4, 1, "", "config_file_path"], [188, 4, 1, "", "model"], [188, 4, 1, "", "pruner_info"], [188, 4, 1, "", "pruners"]], "neural_compressor.compression.pruner.pruning.RetrainFreePruning": [[188, 4, 1, "", "config_file_path"], [188, 4, 1, "", "model"], [188, 4, 1, "", "pruner_info"], [188, 4, 1, "", "pruners"]], "neural_compressor.compression.pruner.regs": [[189, 1, 1, "", "BaseReg"], [189, 1, 1, "", "GroupLasso"], [189, 2, 1, "", "get_reg"], [189, 2, 1, "", "get_reg_type"], [189, 2, 1, "", "register_reg"]], "neural_compressor.compression.pruner.regs.GroupLasso": [[189, 4, 1, "", "alpha"], [189, 4, 1, "", "reg_terms"]], "neural_compressor.compression.pruner.schedulers": [[190, 1, 1, "", "IterativeScheduler"], [190, 1, 1, "", "OneshotScheduler"], [190, 1, 1, "", "PruningScheduler"], [190, 2, 1, "", "get_scheduler"], [190, 2, 1, "", "register_scheduler"]], "neural_compressor.compression.pruner.schedulers.PruningScheduler": [[190, 4, 1, "", "config"]], "neural_compressor.compression.pruner.tf_criteria": [[191, 1, 1, "", "MagnitudeCriterion"], [191, 1, 1, "", "PruningCriterion"], [191, 2, 1, "", "get_tf_criterion"], [191, 2, 1, "", "register_criterion"]], "neural_compressor.compression.pruner.tf_criteria.MagnitudeCriterion": [[191, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.tf_criteria.PruningCriterion": [[191, 4, 1, "", "scores"]], "neural_compressor.compression.pruner.utils": [[192, 2, 1, "", "check_config"], [192, 2, 1, "", "check_key_validity"], [192, 2, 1, "", "collect_layer_inputs"], [192, 2, 1, "", "get_layers"], [192, 2, 1, "", "get_sparsity_ratio"], [192, 2, 1, "", "get_sparsity_ratio_tf"], [192, 2, 1, "", "parse_last_linear"], [192, 2, 1, "", "parse_last_linear_tf"], [192, 2, 1, "", "parse_to_prune"], [192, 2, 1, "", "parse_to_prune_tf"], [192, 2, 1, "", "process_and_check_config"], [192, 2, 1, "", "process_config"], [192, 2, 1, "", "process_weight_config"], [192, 2, 1, "", "process_yaml_config"], [192, 2, 1, "", "reset_none_to_default"], [192, 2, 1, "", "update_params"]], "neural_compressor.compression.pruner.wanda": [[194, 0, 0, "-", "utils"]], "neural_compressor.compression.pruner.wanda.utils": [[194, 2, 1, "", "find_layers"]], "neural_compressor.config": [[195, 1, 1, "", "AccuracyCriterion"], [195, 1, 1, "", "BenchmarkConfig"], [195, 1, 1, "", "DistillationConfig"], [195, 1, 1, "", "DotDict"], [195, 1, 1, "", "ExportConfig"], [195, 1, 1, "", "HPOConfig"], [195, 1, 1, "", "IntermediateLayersKnowledgeDistillationLossConfig"], [195, 1, 1, "", "Keras"], [195, 1, 1, "", "KnowledgeDistillationLossConfig"], [195, 1, 1, "", "MXNet"], [195, 1, 1, "", "MixedPrecisionConfig"], [195, 1, 1, "", "NASConfig"], [195, 1, 1, "", "ONNX"], [195, 1, 1, "", "ONNXQlinear2QDQConfig"], [195, 1, 1, "", "Options"], [195, 1, 1, "", "PostTrainingQuantConfig"], [195, 1, 1, "", "PyTorch"], [195, 1, 1, "", "QuantizationAwareTrainingConfig"], [195, 1, 1, "", "SelfKnowledgeDistillationLossConfig"], [195, 1, 1, "", "TF2ONNXConfig"], [195, 1, 1, "", "TensorFlow"], [195, 1, 1, "", "Torch2ONNXConfig"], [195, 1, 1, "", "TuningCriterion"], [195, 1, 1, "", "WeightPruningConfig"]], "neural_compressor.contrib": [[197, 0, 0, "-", "strategy"]], "neural_compressor.contrib.strategy": [[198, 0, 0, "-", "sigopt"], [199, 0, 0, "-", "tpe"]], "neural_compressor.contrib.strategy.sigopt": [[198, 1, 1, "", "SigOptTuneStrategy"]], "neural_compressor.contrib.strategy.tpe": [[199, 1, 1, "", "TpeTuneStrategy"]], "neural_compressor.data": [[215, 0, 0, "-", "datasets"], [219, 0, 0, "-", "filters"], [222, 0, 0, "-", "transforms"]], "neural_compressor.data.dataloaders": [[200, 0, 0, "-", "base_dataloader"], [201, 0, 0, "-", "dataloader"], [202, 0, 0, "-", "default_dataloader"], [203, 0, 0, "-", "fetcher"], [204, 0, 0, "-", "mxnet_dataloader"], [205, 0, 0, "-", "onnxrt_dataloader"], [206, 0, 0, "-", "pytorch_dataloader"], [207, 0, 0, "-", "sampler"], [208, 0, 0, "-", "tensorflow_dataloader"]], "neural_compressor.data.dataloaders.base_dataloader": [[200, 1, 1, "", "BaseDataLoader"]], "neural_compressor.data.dataloaders.dataloader": [[201, 1, 1, "", "DataLoader"], [201, 2, 1, "", "check_dataloader"]], "neural_compressor.data.dataloaders.default_dataloader": [[202, 1, 1, "", "DefaultDataLoader"], [202, 2, 1, "", "default_collate"]], "neural_compressor.data.dataloaders.fetcher": [[203, 1, 1, "", "Fetcher"], [203, 1, 1, "", "IndexFetcher"], [203, 1, 1, "", "IterableFetcher"]], "neural_compressor.data.dataloaders.mxnet_dataloader": [[204, 1, 1, "", "MXNetDataLoader"]], "neural_compressor.data.dataloaders.onnxrt_dataloader": [[205, 1, 1, "", "ONNXRTBertDataLoader"], [205, 1, 1, "", "ONNXRTDataLoader"]], "neural_compressor.data.dataloaders.pytorch_dataloader": [[206, 1, 1, "", "PyTorchDataLoader"]], "neural_compressor.data.dataloaders.sampler": [[207, 1, 1, "", "BatchSampler"], [207, 1, 1, "", "IterableSampler"], [207, 1, 1, "", "Sampler"], [207, 1, 1, "", "SequentialSampler"]], "neural_compressor.data.dataloaders.tensorflow_dataloader": [[208, 1, 1, "", "TFDataDataLoader"], [208, 1, 1, "", "TensorflowBertDataLoader"], [208, 1, 1, "", "TensorflowDataLoader"], [208, 1, 1, "", "TensorflowModelZooBertDataLoader"]], "neural_compressor.data.datasets": [[209, 0, 0, "-", "bert_dataset"], [210, 0, 0, "-", "coco_dataset"], [211, 0, 0, "-", "dataset"], [212, 0, 0, "-", "dummy_dataset"], [213, 0, 0, "-", "dummy_dataset_v2"], [214, 0, 0, "-", "imagenet_dataset"], [216, 0, 0, "-", "style_transfer_dataset"]], "neural_compressor.data.datasets.bert_dataset": [[209, 1, 1, "", "InputFeatures"], [209, 1, 1, "", "ONNXRTBertDataset"], [209, 1, 1, "", "ParseDecodeBert"], [209, 1, 1, "", "PytorchBertDataset"], [209, 1, 1, "", "TensorflowBertDataset"], [209, 1, 1, "", "TensorflowModelZooBertDataset"], [209, 2, 1, "", "convert_examples_to_features"], [209, 2, 1, "", "load_and_cache_examples"]], "neural_compressor.data.datasets.coco_dataset": [[210, 1, 1, "", "COCONpy"], [210, 1, 1, "", "COCORaw"], [210, 1, 1, "", "COCORecordDataset"], [210, 1, 1, "", "ParseDecodeCoco"]], "neural_compressor.data.datasets.dataset": [[211, 1, 1, "", "CIFAR10"], [211, 1, 1, "", "CIFAR100"], [211, 1, 1, "", "Dataset"], [211, 1, 1, "", "Datasets"], [211, 1, 1, "", "FashionMNIST"], [211, 1, 1, "", "ImageFolder"], [211, 1, 1, "", "IterableDataset"], [211, 1, 1, "", "MNIST"], [211, 1, 1, "", "MXNetCIFAR10"], [211, 1, 1, "", "MXNetCIFAR100"], [211, 1, 1, "", "MXNetDatasets"], [211, 1, 1, "", "MXNetFashionMNIST"], [211, 1, 1, "", "MXNetImageFolder"], [211, 1, 1, "", "MXNetMNIST"], [211, 1, 1, "", "ONNXRTITDatasets"], [211, 1, 1, "", "ONNXRTQLDatasets"], [211, 1, 1, "", "PyTorchDatasets"], [211, 1, 1, "", "PytorchCIFAR10"], [211, 1, 1, "", "PytorchCIFAR100"], [211, 1, 1, "", "PytorchFashionMNIST"], [211, 1, 1, "", "PytorchMNIST"], [211, 1, 1, "", "PytorchMxnetWrapDataset"], [211, 1, 1, "", "PytorchMxnetWrapFunction"], [211, 1, 1, "", "Tensorflow"], [211, 1, 1, "", "TensorflowCIFAR10"], [211, 1, 1, "", "TensorflowCIFAR100"], [211, 1, 1, "", "TensorflowDatasets"], [211, 1, 1, "", "TensorflowFashionMNIST"], [211, 1, 1, "", "TensorflowImageRecord"], [211, 1, 1, "", "TensorflowMNIST"], [211, 1, 1, "", "TensorflowTFRecordDataset"], [211, 1, 1, "", "TensorflowVOCRecord"], [211, 2, 1, "", "calculate_md5"], [211, 2, 1, "", "check_integrity"], [211, 2, 1, "", "dataset_registry"], [211, 2, 1, "", "download_url"], [211, 5, 1, "", "framework_datasets"], [211, 2, 1, "", "gen_bar_updater"]], "neural_compressor.data.datasets.dummy_dataset": [[212, 1, 1, "", "DummyDataset"]], "neural_compressor.data.datasets.dummy_dataset_v2": [[213, 1, 1, "", "DummyDataset"], [213, 1, 1, "", "SparseDummyDataset"]], "neural_compressor.data.datasets.imagenet_dataset": [[214, 1, 1, "", "ImagenetRaw"], [214, 1, 1, "", "MXNetImagenetRaw"], [214, 1, 1, "", "ONNXRTImagenetDataset"], [214, 1, 1, "", "PytorchImagenetRaw"], [214, 1, 1, "", "TensorflowImagenetDataset"], [214, 1, 1, "", "TensorflowImagenetRaw"]], "neural_compressor.data.datasets.style_transfer_dataset": [[216, 1, 1, "", "StyleTransferDataset"]], "neural_compressor.data.filters": [[217, 0, 0, "-", "coco_filter"], [218, 0, 0, "-", "filter"]], "neural_compressor.data.filters.coco_filter": [[217, 1, 1, "", "LabelBalanceCOCORawFilter"], [217, 1, 1, "", "LabelBalanceCOCORecordFilter"]], "neural_compressor.data.filters.filter": [[218, 1, 1, "", "FILTERS"], [218, 1, 1, "", "Filter"], [218, 1, 1, "", "MXNetFilters"], [218, 1, 1, "", "ONNXRTITFilters"], [218, 1, 1, "", "ONNXRTQLFilters"], [218, 1, 1, "", "PyTorchFilters"], [218, 1, 1, "", "TensorflowFilters"], [218, 2, 1, "", "filter_registry"]], "neural_compressor.data.transforms": [[221, 0, 0, "-", "imagenet_transform"], [223, 0, 0, "-", "postprocess"], [224, 0, 0, "-", "tokenization"], [225, 0, 0, "-", "transform"]], "neural_compressor.data.transforms.imagenet_transform": [[221, 1, 1, "", "BilinearImagenetTransform"], [221, 1, 1, "", "LabelShift"], [221, 1, 1, "", "ONNXResizeCropImagenetTransform"], [221, 1, 1, "", "OnnxBilinearImagenetTransform"], [221, 1, 1, "", "ParseDecodeImagenet"], [221, 1, 1, "", "ParseDecodeImagenetTransform"], [221, 1, 1, "", "QuantizedInput"], [221, 1, 1, "", "ResizeWithAspectRatio"], [221, 1, 1, "", "TensorflowResizeCropImagenetTransform"], [221, 1, 1, "", "TensorflowShiftRescale"], [221, 1, 1, "", "TensorflowTransposeLastChannel"]], "neural_compressor.data.transforms.postprocess": [[223, 1, 1, "", "Postprocess"]], "neural_compressor.data.transforms.tokenization": [[224, 1, 1, "", "BasicTokenizer"], [224, 1, 1, "", "FullTokenizer"], [224, 1, 1, "", "WordpieceTokenizer"], [224, 2, 1, "", "convert_by_vocab"], [224, 2, 1, "", "convert_to_unicode"], [224, 2, 1, "", "load_vocab"], [224, 2, 1, "", "whitespace_tokenize"]], "neural_compressor.data.transforms.transform": [[225, 1, 1, "", "AlignImageChannelTransform"], [225, 1, 1, "", "BaseTransform"], [225, 1, 1, "", "CastONNXTransform"], [225, 1, 1, "", "CastPyTorchTransform"], [225, 1, 1, "", "CastTFTransform"], [225, 1, 1, "", "CenterCropTFTransform"], [225, 1, 1, "", "CenterCropTransform"], [225, 1, 1, "", "CollectTransform"], [225, 1, 1, "", "ComposeTransform"], [225, 1, 1, "", "CropResizeTFTransform"], [225, 1, 1, "", "CropResizeTransform"], [225, 1, 1, "", "CropToBoundingBox"], [225, 1, 1, "", "InputFeatures"], [225, 1, 1, "", "MXNetCropResizeTransform"], [225, 1, 1, "", "MXNetCropToBoundingBox"], [225, 1, 1, "", "MXNetNormalizeTransform"], [225, 1, 1, "", "MXNetTransforms"], [225, 1, 1, "", "MXNetTranspose"], [225, 1, 1, "", "NormalizeTFTransform"], [225, 1, 1, "", "NormalizeTransform"], [225, 1, 1, "", "ONNXRTCropToBoundingBox"], [225, 1, 1, "", "ONNXRTITTransforms"], [225, 1, 1, "", "ONNXRTQLTransforms"], [225, 1, 1, "", "PaddedCenterCropTransform"], [225, 1, 1, "", "ParseDecodeVocTransform"], [225, 1, 1, "", "PyTorchAlignImageChannel"], [225, 1, 1, "", "PyTorchCropResizeTransform"], [225, 1, 1, "", "PyTorchNormalizeTransform"], [225, 1, 1, "", "PyTorchTransforms"], [225, 1, 1, "", "PyTorchTranspose"], [225, 1, 1, "", "PytorchMxnetTransform"], [225, 1, 1, "", "PytorchMxnetWrapFunction"], [225, 1, 1, "", "RandomCropTFTransform"], [225, 1, 1, "", "RandomCropTransform"], [225, 1, 1, "", "RandomHorizontalFlip"], [225, 1, 1, "", "RandomResizedCropMXNetTransform"], [225, 1, 1, "", "RandomResizedCropPytorchTransform"], [225, 1, 1, "", "RandomResizedCropTFTransform"], [225, 1, 1, "", "RandomResizedCropTransform"], [225, 1, 1, "", "RandomVerticalFlip"], [225, 1, 1, "", "RescaleKerasPretrainTransform"], [225, 1, 1, "", "RescaleTFTransform"], [225, 1, 1, "", "RescaleTransform"], [225, 1, 1, "", "ResizeMXNetTransform"], [225, 1, 1, "", "ResizePytorchTransform"], [225, 1, 1, "", "ResizeTFTransform"], [225, 1, 1, "", "ResizeTransform"], [225, 1, 1, "", "ResizeWithRatio"], [225, 1, 1, "", "SquadExample"], [225, 1, 1, "", "TFModelZooCollectTransform"], [225, 1, 1, "", "TFSquadV1ModelZooPostTransform"], [225, 1, 1, "", "TFSquadV1PostTransform"], [225, 1, 1, "", "TRANSFORMS"], [225, 1, 1, "", "TensorflowCropToBoundingBox"], [225, 1, 1, "", "TensorflowRandomHorizontalFlip"], [225, 1, 1, "", "TensorflowRandomVerticalFlip"], [225, 1, 1, "", "TensorflowResizeWithRatio"], [225, 1, 1, "", "TensorflowTransform"], [225, 1, 1, "", "TensorflowTransforms"], [225, 1, 1, "", "TensorflowTranspose"], [225, 1, 1, "", "TensorflowWrapFunction"], [225, 1, 1, "", "ToArray"], [225, 1, 1, "", "ToNDArrayTransform"], [225, 1, 1, "", "Transforms"], [225, 1, 1, "", "Transpose"], [225, 2, 1, "", "convert_examples_to_features"], [225, 2, 1, "", "get_final_text"], [225, 2, 1, "", "get_torchvision_map"], [225, 2, 1, "", "read_squad_examples"], [225, 2, 1, "", "transform_registry"]], "neural_compressor.metric": [[227, 0, 0, "-", "bleu"], [228, 0, 0, "-", "bleu_util"], [229, 0, 0, "-", "coco_label_map"], [230, 0, 0, "-", "coco_tools"], [231, 0, 0, "-", "evaluate_squad"], [232, 0, 0, "-", "f1"], [234, 0, 0, "-", "metric"]], "neural_compressor.metric.bleu": [[227, 1, 1, "", "BLEU"], [227, 1, 1, "", "UnicodeRegex"], [227, 2, 1, "", "bleu_tokenize"]], "neural_compressor.metric.bleu.BLEU": [[227, 4, 1, "", "labels"], [227, 4, 1, "", "predictions"]], "neural_compressor.metric.bleu.UnicodeRegex": [[227, 4, 1, "", "nondigit_punct_re"], [227, 4, 1, "", "punct_nondigit_re"], [227, 4, 1, "", "symbol_re"]], "neural_compressor.metric.bleu_util": [[228, 2, 1, "", "compute_bleu"]], "neural_compressor.metric.coco_tools": [[230, 1, 1, "", "COCOEvalWrapper"], [230, 1, 1, "", "COCOWrapper"], [230, 2, 1, "", "ExportSingleImageDetectionBoxesToCoco"], [230, 2, 1, "", "ExportSingleImageDetectionMasksToCoco"], [230, 2, 1, "", "ExportSingleImageGroundtruthToCoco"]], "neural_compressor.metric.coco_tools.COCOWrapper": [[230, 4, 1, "", "dataset"], [230, 4, 1, "", "detection_type"]], "neural_compressor.metric.evaluate_squad": [[231, 2, 1, "", "evaluate"], [231, 2, 1, "", "exact_match_score"], [231, 2, 1, "", "f1_score"], [231, 2, 1, "", "metric_max_over_ground_truths"]], "neural_compressor.metric.f1": [[232, 2, 1, "", "evaluate"], [232, 2, 1, "", "f1_score"], [232, 2, 1, "", "metric_max_over_ground_truths"], [232, 2, 1, "", "normalize_answer"]], "neural_compressor.metric.metric": [[234, 1, 1, "", "Accuracy"], [234, 1, 1, "", "BaseMetric"], [234, 1, 1, "", "COCOmAPv2"], [234, 1, 1, "", "F1"], [234, 1, 1, "", "GeneralTopK"], [234, 1, 1, "", "Loss"], [234, 1, 1, "", "MAE"], [234, 1, 1, "", "METRICS"], [234, 1, 1, "", "MSE"], [234, 1, 1, "", "MXNetMetrics"], [234, 1, 1, "", "Metric"], [234, 1, 1, "", "ONNXRTGLUE"], [234, 1, 1, "", "ONNXRTITMetrics"], [234, 1, 1, "", "ONNXRTQLMetrics"], [234, 1, 1, "", "PyTorchLoss"], [234, 1, 1, "", "PyTorchMetrics"], [234, 1, 1, "", "RMSE"], [234, 1, 1, "", "ROC"], [234, 1, 1, "", "SquadF1"], [234, 1, 1, "", "TensorflowCOCOMAP"], [234, 1, 1, "", "TensorflowMAP"], [234, 1, 1, "", "TensorflowMetrics"], [234, 1, 1, "", "TensorflowTopK"], [234, 1, 1, "", "TensorflowVOCMAP"], [234, 1, 1, "", "WrapMXNetMetric"], [234, 1, 1, "", "WrapONNXRTMetric"], [234, 1, 1, "", "WrapPyTorchMetric"], [234, 1, 1, "", "mIOU"], [234, 2, 1, "", "metric_registry"], [234, 2, 1, "", "register_customer_metric"]], "neural_compressor.metric.metric.Accuracy": [[234, 4, 1, "", "label_list"], [234, 4, 1, "", "pred_list"], [234, 4, 1, "", "sample"]], "neural_compressor.metric.metric.GeneralTopK": [[234, 4, 1, "", "k"], [234, 4, 1, "", "num_correct"], [234, 4, 1, "", "num_sample"]], "neural_compressor.metric.metric.Loss": [[234, 4, 1, "", "sample"], [234, 4, 1, "", "sum"]], "neural_compressor.metric.metric.MAE": [[234, 4, 1, "", "compare_label"], [234, 4, 1, "", "label_list"], [234, 4, 1, "", "pred_list"]], "neural_compressor.metric.metric.METRICS": [[234, 4, 1, "", "metrics"]], "neural_compressor.metric.metric.MSE": [[234, 4, 1, "", "compare_label"], [234, 4, 1, "", "label_list"], [234, 4, 1, "", "pred_list"]], "neural_compressor.metric.metric.MXNetMetrics": [[234, 4, 1, "", "metrics"]], "neural_compressor.metric.metric.ONNXRTITMetrics": [[234, 4, 1, "", "metrics"]], "neural_compressor.metric.metric.ONNXRTQLMetrics": [[234, 4, 1, "", "metrics"]], "neural_compressor.metric.metric.PyTorchMetrics": [[234, 4, 1, "", "metrics"]], "neural_compressor.metric.metric.RMSE": [[234, 4, 1, "", "mse"]], "neural_compressor.metric.metric.TensorflowMetrics": [[234, 4, 1, "", "metrics"]], "neural_compressor.metric.metric.TensorflowTopK": [[234, 4, 1, "", "k"], [234, 4, 1, "", "num_correct"], [234, 4, 1, "", "num_sample"]], "neural_compressor.mix_precision": [[235, 2, 1, "", "fit"]], "neural_compressor.model": [[236, 0, 0, "-", "base_model"], [238, 0, 0, "-", "keras_model"], [239, 0, 0, "-", "model"], [240, 0, 0, "-", "mxnet_model"], [241, 0, 0, "-", "nets_factory"], [242, 0, 0, "-", "onnx_model"], [243, 0, 0, "-", "tensorflow_model"], [244, 0, 0, "-", "torch_model"]], "neural_compressor.model.base_model": [[236, 1, 1, "", "BaseModel"]], "neural_compressor.model.keras_model": [[238, 1, 1, "", "KerasModel"]], "neural_compressor.model.model": [[239, 1, 1, "", "Model"], [239, 2, 1, "", "get_model_fwk_name"]], "neural_compressor.model.mxnet_model": [[240, 1, 1, "", "MXNetModel"]], "neural_compressor.model.nets_factory": [[241, 1, 1, "", "TFSlimNetsFactory"]], "neural_compressor.model.onnx_model": [[242, 1, 1, "", "ONNXModel"]], "neural_compressor.model.tensorflow_model": [[243, 1, 1, "", "TensorflowBaseModel"], [243, 1, 1, "", "TensorflowCheckpointModel"], [243, 1, 1, "", "TensorflowLLMModel"], [243, 1, 1, "", "TensorflowModel"], [243, 1, 1, "", "TensorflowQATModel"], [243, 1, 1, "", "TensorflowSavedModelModel"], [243, 2, 1, "", "checkpoint_session"], [243, 2, 1, "", "estimator_session"], [243, 2, 1, "", "frozen_pb_session"], [243, 2, 1, "", "get_model_type"], [243, 2, 1, "", "graph_def_session"], [243, 2, 1, "", "graph_session"], [243, 2, 1, "", "keras_session"], [243, 2, 1, "", "load_saved_model"], [243, 2, 1, "", "saved_model_session"], [243, 2, 1, "", "slim_session"], [243, 2, 1, "", "try_loading_keras"], [243, 2, 1, "", "validate_and_inference_input_output"], [243, 2, 1, "", "validate_graph_node"]], "neural_compressor.model.torch_model": [[244, 1, 1, "", "IPEXModel"], [244, 1, 1, "", "PyTorchBaseModel"], [244, 1, 1, "", "PyTorchFXModel"], [244, 1, 1, "", "PyTorchModel"]], "neural_compressor.objective": [[245, 1, 1, "", "Accuracy"], [245, 1, 1, "", "Footprint"], [245, 1, 1, "", "ModelSize"], [245, 1, 1, "", "MultiObjective"], [245, 1, 1, "", "Objective"], [245, 1, 1, "", "Performance"], [245, 2, 1, "", "objective_custom_registry"], [245, 2, 1, "", "objective_registry"]], "neural_compressor.profiling.parser": [[247, 0, 0, "-", "factory"], [250, 0, 0, "-", "parser"], [251, 0, 0, "-", "result"]], "neural_compressor.profiling.parser.factory": [[247, 1, 1, "", "ParserFactory"]], "neural_compressor.profiling.parser.onnx_parser": [[248, 0, 0, "-", "factory"], [249, 0, 0, "-", "parser"]], "neural_compressor.profiling.parser.onnx_parser.factory": [[248, 1, 1, "", "OnnxrtParserFactory"]], "neural_compressor.profiling.parser.onnx_parser.parser": [[249, 1, 1, "", "OnnxProfilingParser"]], "neural_compressor.profiling.parser.parser": [[250, 1, 1, "", "ProfilingParser"]], "neural_compressor.profiling.parser.result": [[251, 1, 1, "", "ProfilingResult"]], "neural_compressor.profiling.parser.tensorflow_parser": [[252, 0, 0, "-", "factory"], [253, 0, 0, "-", "parser"]], "neural_compressor.profiling.parser.tensorflow_parser.factory": [[252, 1, 1, "", "TensorFlowParserFactory"]], "neural_compressor.profiling.parser.tensorflow_parser.parser": [[253, 1, 1, "", "TensorFlowProfilingParser"]], "neural_compressor.profiling.profiler": [[254, 0, 0, "-", "factory"], [258, 0, 0, "-", "profiler"]], "neural_compressor.profiling.profiler.factory": [[254, 1, 1, "", "ProfilerFactory"]], "neural_compressor.profiling.profiler.onnxrt_profiler": [[255, 0, 0, "-", "factory"], [256, 0, 0, "-", "profiler"], [257, 0, 0, "-", "utils"]], "neural_compressor.profiling.profiler.onnxrt_profiler.factory": [[255, 1, 1, "", "ProfilerFactory"]], "neural_compressor.profiling.profiler.onnxrt_profiler.profiler": [[256, 1, 1, "", "Profiler"]], "neural_compressor.profiling.profiler.onnxrt_profiler.utils": [[257, 2, 1, "", "create_onnx_config"]], "neural_compressor.profiling.profiler.profiler": [[258, 1, 1, "", "Profiler"]], "neural_compressor.profiling.profiler.tensorflow_profiler": [[259, 0, 0, "-", "factory"], [260, 0, 0, "-", "profiler"], [261, 0, 0, "-", "utils"]], "neural_compressor.profiling.profiler.tensorflow_profiler.factory": [[259, 1, 1, "", "ProfilerFactory"]], "neural_compressor.profiling.profiler.tensorflow_profiler.profiler": [[260, 1, 1, "", "Profiler"]], "neural_compressor.profiling.profiler.tensorflow_profiler.utils": [[261, 2, 1, "", "create_tf_config"], [261, 2, 1, "", "delete_assign"], [261, 2, 1, "", "set_eager_execution"]], "neural_compressor.quantization": [[262, 2, 1, "", "fit"]], "neural_compressor.strategy": [[263, 0, 0, "-", "auto"], [264, 0, 0, "-", "auto_mixed_precision"], [265, 0, 0, "-", "basic"], [266, 0, 0, "-", "bayesian"], [267, 0, 0, "-", "conservative"], [268, 0, 0, "-", "exhaustive"], [269, 0, 0, "-", "hawq_v2"], [271, 0, 0, "-", "mse"], [272, 0, 0, "-", "mse_v2"], [273, 0, 0, "-", "random"], [274, 0, 0, "-", "strategy"], [276, 0, 0, "-", "utils"]], "neural_compressor.strategy.auto": [[263, 1, 1, "", "AutoTuneStrategy"]], "neural_compressor.strategy.auto_mixed_precision": [[264, 1, 1, "", "AutoMixedPrecisionTuneStrategy"]], "neural_compressor.strategy.basic": [[265, 1, 1, "", "BasicTuneStrategy"]], "neural_compressor.strategy.bayesian": [[266, 1, 1, "", "BayesianOptimization"], [266, 1, 1, "", "BayesianTuneStrategy"], [266, 1, 1, "", "TargetSpace"], [266, 2, 1, "", "acq_max"]], "neural_compressor.strategy.conservative": [[267, 1, 1, "", "ConservativeTuneStrategy"]], "neural_compressor.strategy.exhaustive": [[268, 1, 1, "", "ExhaustiveTuneStrategy"]], "neural_compressor.strategy.hawq_v2": [[269, 1, 1, "", "HAWQ_V2TuneStrategy"]], "neural_compressor.strategy.mse": [[271, 1, 1, "", "MSETuneStrategy"]], "neural_compressor.strategy.mse_v2": [[272, 1, 1, "", "MSE_V2TuneStrategy"]], "neural_compressor.strategy.random": [[273, 1, 1, "", "RandomTuneStrategy"]], "neural_compressor.strategy.strategy": [[274, 1, 1, "", "TuneStrategy"], [274, 1, 1, "", "TuneStrategyMeta"], [274, 2, 1, "", "strategy_registry"]], "neural_compressor.strategy.utils": [[275, 0, 0, "-", "constant"], [277, 0, 0, "-", "tuning_sampler"], [278, 0, 0, "-", "tuning_space"], [279, 0, 0, "-", "tuning_structs"], [280, 0, 0, "-", "utility"]], "neural_compressor.strategy.utils.tuning_sampler": [[277, 1, 1, "", "BlockFallbackTuningSampler"], [277, 1, 1, "", "FallbackTuningSampler"], [277, 1, 1, "", "LowerBitsSampler"], [277, 1, 1, "", "ModelWiseTuningSampler"], [277, 1, 1, "", "OpTypeWiseTuningSampler"], [277, 1, 1, "", "OpWiseTuningSampler"], [277, 1, 1, "", "SmoothQuantSampler"], [277, 1, 1, "", "TuningOrder"], [277, 1, 1, "", "TuningSampler"], [277, 1, 1, "", "WeightOnlyQuantSampler"]], "neural_compressor.strategy.utils.tuning_space": [[278, 1, 1, "", "TuningItem"], [278, 1, 1, "", "TuningSpace"], [278, 2, 1, "", "initial_tuning_cfg_with_quant_mode"], [278, 2, 1, "", "pattern_to_internal"], [278, 2, 1, "", "pattern_to_path"], [278, 2, 1, "", "quant_mode_from_pattern"]], "neural_compressor.strategy.utils.tuning_structs": [[279, 1, 1, "", "OpTuningConfig"]], "neural_compressor.strategy.utils.utility": [[280, 1, 1, "", "ClassRegister"], [280, 1, 1, "", "OrderedDefaultDict"], [280, 1, 1, "", "QuantOptions"], [280, 1, 1, "", "QuantType"], [280, 2, 1, "", "build_slave_faker_model"], [280, 2, 1, "", "extract_data_type"], [280, 2, 1, "", "get_adaptor_name"], [280, 2, 1, "", "preprocess_user_cfg"], [280, 2, 1, "", "reverted_data_type"]], "neural_compressor.template": [[281, 0, 0, "-", "api_doc_example"]], "neural_compressor.template.api_doc_example": [[281, 1, 1, "", "ExampleClass"], [281, 4, 1, "", "attribute1"], [281, 2, 1, "", "function1"], [281, 2, 1, "", "function2"], [281, 2, 1, "", "function3"], [281, 2, 1, "", "generator1"], [281, 5, 1, "", "module_debug_level1"]], "neural_compressor.template.api_doc_example.ExampleClass": [[281, 4, 1, "", "attr1"], [281, 4, 1, "", "attr2"], [281, 4, 1, "", "attr5"]], "neural_compressor.tensorflow": [[282, 0, 0, "-", "algorithms"], [291, 0, 0, "-", "keras"], [304, 0, 0, "-", "quantization"], [388, 0, 0, "-", "utils"]], "neural_compressor.tensorflow.algorithms": [[285, 0, 0, "-", "smoother"], [287, 0, 0, "-", "static_quant"]], "neural_compressor.tensorflow.algorithms.smoother": [[283, 0, 0, "-", "calibration"], [284, 0, 0, "-", "core"], [286, 0, 0, "-", "scaler"]], "neural_compressor.tensorflow.algorithms.smoother.calibration": [[283, 1, 1, "", "SmoothQuantCalibration"], [283, 1, 1, "", "SmoothQuantCalibrationLLM"]], "neural_compressor.tensorflow.algorithms.smoother.core": [[284, 1, 1, "", "SmoothQuant"]], "neural_compressor.tensorflow.algorithms.smoother.scaler": [[286, 1, 1, "", "SmoothQuantScaler"], [286, 1, 1, "", "SmoothQuantScalerLLM"]], "neural_compressor.tensorflow.algorithms.static_quant": [[288, 0, 0, "-", "keras"], [289, 0, 0, "-", "tensorflow"]], "neural_compressor.tensorflow.algorithms.static_quant.keras": [[288, 1, 1, "", "KerasAdaptor"], [288, 1, 1, "", "KerasConfigConverter"], [288, 1, 1, "", "KerasQuery"], [288, 1, 1, "", "KerasSurgery"]], "neural_compressor.tensorflow.algorithms.static_quant.tensorflow": [[289, 1, 1, "", "TensorFlowAdaptor"], [289, 1, 1, "", "TensorFlowConfig"], [289, 1, 1, "", "TensorflowConfigConverter"], [289, 1, 1, "", "TensorflowQuery"], [289, 1, 1, "", "Tensorflow_ITEXAdaptor"]], "neural_compressor.tensorflow.keras": [[295, 0, 0, "-", "layers"], [300, 0, 0, "-", "quantization"]], "neural_compressor.tensorflow.keras.layers": [[292, 0, 0, "-", "conv2d"], [293, 0, 0, "-", "dense"], [294, 0, 0, "-", "depthwise_conv2d"], [296, 0, 0, "-", "layer_initializer"], [297, 0, 0, "-", "pool2d"], [298, 0, 0, "-", "separable_conv2d"]], "neural_compressor.tensorflow.keras.layers.conv2d": [[292, 1, 1, "", "QConv2D"], [292, 2, 1, "", "initialize_int8_conv2d"]], "neural_compressor.tensorflow.keras.layers.dense": [[293, 1, 1, "", "QDense"], [293, 2, 1, "", "initialize_int8_dense"]], "neural_compressor.tensorflow.keras.layers.depthwise_conv2d": [[294, 1, 1, "", "QDepthwiseConv2D"], [294, 2, 1, "", "initialize_int8_depthwise_conv2d"]], "neural_compressor.tensorflow.keras.layers.pool2d": [[297, 1, 1, "", "QAvgPool2D"], [297, 1, 1, "", "QMaxPool2D"], [297, 2, 1, "", "initialize_int8_avgpool"], [297, 2, 1, "", "initialize_int8_maxpool"]], "neural_compressor.tensorflow.keras.layers.separable_conv2d": [[298, 1, 1, "", "QSeparableConv2D"], [298, 2, 1, "", "initialize_int8_separable_conv2d"]], "neural_compressor.tensorflow.keras.quantization": [[299, 0, 0, "-", "config"]], "neural_compressor.tensorflow.keras.quantization.config": [[299, 1, 1, "", "OperatorConfig"], [299, 1, 1, "", "StaticQuantConfig"], [299, 2, 1, "", "get_all_registered_configs"], [299, 2, 1, "", "get_default_static_quant_config"]], "neural_compressor.tensorflow.quantization": [[301, 0, 0, "-", "algorithm_entry"], [302, 0, 0, "-", "autotune"], [303, 0, 0, "-", "config"], [305, 0, 0, "-", "quantize"], [361, 0, 0, "-", "utils"]], "neural_compressor.tensorflow.quantization.algorithm_entry": [[301, 2, 1, "", "smooth_quant_entry"], [301, 2, 1, "", "static_quant_entry"]], "neural_compressor.tensorflow.quantization.autotune": [[302, 2, 1, "", "autotune"], [302, 2, 1, "", "get_all_config_set"]], "neural_compressor.tensorflow.quantization.config": [[303, 1, 1, "", "SmoothQuantConfig"], [303, 1, 1, "", "StaticQuantConfig"], [303, 2, 1, "", "get_default_sq_config"], [303, 2, 1, "", "get_default_static_quant_config"]], "neural_compressor.tensorflow.quantization.quantize": [[305, 2, 1, "", "need_apply"], [305, 2, 1, "", "quantize_model"], [305, 2, 1, "", "quantize_model_with_single_config"]], "neural_compressor.tensorflow.quantization.utils": [[306, 0, 0, "-", "graph_converter"], [344, 0, 0, "-", "graph_rewriter"], [360, 0, 0, "-", "graph_util"], [362, 0, 0, "-", "quantize_graph"], [379, 0, 0, "-", "quantize_graph_common"], [382, 0, 0, "-", "transform_graph"], [385, 0, 0, "-", "utility"]], "neural_compressor.tensorflow.quantization.utils.graph_converter": [[306, 1, 1, "", "GraphConverter"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter": [[309, 0, 0, "-", "bf16"], [333, 0, 0, "-", "generic"], [343, 0, 0, "-", "graph_base"], [351, 0, 0, "-", "int8"], [356, 0, 0, "-", "qdq"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16": [[307, 0, 0, "-", "bf16_convert"], [308, 0, 0, "-", "dequantize_cast_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert": [[307, 1, 1, "", "BF16Convert"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer": [[308, 1, 1, "", "DequantizeCastOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic": [[310, 0, 0, "-", "convert_add_to_biasadd"], [311, 0, 0, "-", "convert_layout"], [312, 0, 0, "-", "convert_leakyrelu"], [313, 0, 0, "-", "convert_nan_to_random"], [314, 0, 0, "-", "convert_placeholder_to_const"], [315, 0, 0, "-", "dilated_contraction"], [316, 0, 0, "-", "dummy_biasadd"], [317, 0, 0, "-", "expanddims_optimizer"], [318, 0, 0, "-", "fetch_weight_from_reshape"], [319, 0, 0, "-", "fold_batch_norm"], [320, 0, 0, "-", "fold_constant"], [321, 0, 0, "-", "fuse_biasadd_add"], [322, 0, 0, "-", "fuse_column_wise_mul"], [323, 0, 0, "-", "fuse_conv_with_math"], [324, 0, 0, "-", "fuse_decomposed_bn"], [325, 0, 0, "-", "fuse_decomposed_in"], [326, 0, 0, "-", "fuse_gelu"], [327, 0, 0, "-", "fuse_layer_norm"], [328, 0, 0, "-", "fuse_pad_with_conv"], [329, 0, 0, "-", "fuse_pad_with_fp32_conv"], [330, 0, 0, "-", "fuse_reshape_transpose"], [331, 0, 0, "-", "graph_cse_optimizer"], [332, 0, 0, "-", "grappler_pass"], [334, 0, 0, "-", "insert_print_node"], [335, 0, 0, "-", "move_squeeze_after_relu"], [336, 0, 0, "-", "pre_optimize"], [337, 0, 0, "-", "remove_training_nodes"], [338, 0, 0, "-", "rename_batch_norm"], [339, 0, 0, "-", "split_shared_input"], [340, 0, 0, "-", "strip_equivalent_nodes"], [341, 0, 0, "-", "strip_unused_nodes"], [342, 0, 0, "-", "switch_optimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd": [[310, 1, 1, "", "ConvertAddToBiasAddOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout": [[311, 1, 1, "", "ConvertLayoutOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu": [[312, 1, 1, "", "ConvertLeakyReluOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random": [[313, 1, 1, "", "ConvertNanToRandom"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const": [[314, 1, 1, "", "ConvertPlaceholderToConst"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction": [[315, 1, 1, "", "DilatedContraction"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd": [[316, 1, 1, "", "InjectDummyBiasAddOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer": [[317, 1, 1, "", "ExpandDimsOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape": [[318, 1, 1, "", "FetchWeightFromReshapeOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm": [[319, 1, 1, "", "FoldBatchNormNodesOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant": [[320, 1, 1, "", "GraphFoldConstantOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add": [[321, 1, 1, "", "FuseBiasAddAndAddOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul": [[322, 1, 1, "", "FuseColumnWiseMulOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math": [[323, 1, 1, "", "FuseConvWithMathOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn": [[324, 1, 1, "", "FuseDecomposedBNOptimizer"], [324, 2, 1, "", "bypass_reshape"], [324, 2, 1, "", "get_const_dim_count"], [324, 2, 1, "", "node_from_map"], [324, 2, 1, "", "node_name_from_input"], [324, 2, 1, "", "valid_reshape_inputs"], [324, 2, 1, "", "values_from_const"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in": [[325, 1, 1, "", "FuseDecomposedINOptimizer"], [325, 2, 1, "", "bypass_reshape"], [325, 2, 1, "", "get_const_dim_count"], [325, 2, 1, "", "node_from_map"], [325, 2, 1, "", "node_name_from_input"], [325, 2, 1, "", "valid_reshape_inputs"], [325, 2, 1, "", "values_from_const"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu": [[326, 1, 1, "", "FuseGeluOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm": [[327, 1, 1, "", "FuseLayerNormOptimizer"], [327, 2, 1, "", "node_from_map"], [327, 2, 1, "", "node_name_from_input"], [327, 2, 1, "", "values_from_const"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv": [[328, 1, 1, "", "FusePadWithConv2DOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv": [[329, 1, 1, "", "FusePadWithFP32Conv2DOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose": [[330, 1, 1, "", "FuseTransposeReshapeOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer": [[331, 1, 1, "", "GraphCseOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass": [[332, 1, 1, "", "GrapplerOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node": [[334, 1, 1, "", "InsertPrintMinMaxNode"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu": [[335, 1, 1, "", "MoveSqueezeAfterReluOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize": [[336, 1, 1, "", "PreOptimization"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes": [[337, 1, 1, "", "RemoveTrainingNodesOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm": [[338, 1, 1, "", "RenameBatchNormOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input": [[339, 1, 1, "", "SplitSharedInputOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes": [[340, 1, 1, "", "StripEquivalentNodesOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes": [[341, 1, 1, "", "StripUnusedNodesOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer": [[342, 1, 1, "", "SwitchOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base": [[343, 1, 1, "", "GraphRewriterBase"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8": [[345, 0, 0, "-", "freeze_fake_quant"], [346, 0, 0, "-", "freeze_value"], [347, 0, 0, "-", "fuse_conv_redundant_dequantize"], [348, 0, 0, "-", "fuse_conv_requantize"], [349, 0, 0, "-", "fuse_matmul_redundant_dequantize"], [350, 0, 0, "-", "fuse_matmul_requantize"], [352, 0, 0, "-", "meta_op_optimizer"], [353, 0, 0, "-", "post_hostconst_converter"], [354, 0, 0, "-", "post_quantized_op_cse"], [355, 0, 0, "-", "scale_propagation"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant": [[345, 1, 1, "", "FreezeFakeQuantOpOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value": [[346, 1, 1, "", "FreezeValueTransformer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize": [[347, 1, 1, "", "FuseConvRedundantDequantizeTransformer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize": [[348, 1, 1, "", "FuseConvRequantizeTransformer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize": [[349, 1, 1, "", "FuseMatMulRedundantDequantizeTransformer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize": [[350, 1, 1, "", "FuseMatMulRequantizeDequantizeNewAPITransformer"], [350, 1, 1, "", "FuseMatMulRequantizeDequantizeTransformer"], [350, 1, 1, "", "FuseMatMulRequantizeNewAPITransformer"], [350, 1, 1, "", "FuseMatMulRequantizeTransformer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer": [[352, 1, 1, "", "MetaInfoChangingMemOpOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter": [[353, 1, 1, "", "PostHostConstConverter"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse": [[354, 1, 1, "", "PostCseOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation": [[355, 1, 1, "", "ScaleProPagationTransformer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq": [[357, 0, 0, "-", "insert_qdq_pattern"], [358, 0, 0, "-", "merge_duplicated_qdq"], [359, 0, 0, "-", "share_qdq_y_pattern"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern": [[357, 1, 1, "", "GenerateGraphWithQDQPattern"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq": [[358, 1, 1, "", "MergeDuplicatedQDQOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern": [[359, 1, 1, "", "ShareQDQForItexYPatternOptimizer"]], "neural_compressor.tensorflow.quantization.utils.graph_util": [[360, 1, 1, "", "GraphAnalyzer"], [360, 1, 1, "", "GraphRewriterHelper"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph": [[370, 0, 0, "-", "qdq"], [372, 0, 0, "-", "quantize_graph_base"], [373, 0, 0, "-", "quantize_graph_bn"], [374, 0, 0, "-", "quantize_graph_concatv2"], [375, 0, 0, "-", "quantize_graph_conv"], [376, 0, 0, "-", "quantize_graph_for_intel_cpu"], [377, 0, 0, "-", "quantize_graph_matmul"], [378, 0, 0, "-", "quantize_graph_pooling"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq": [[363, 0, 0, "-", "fuse_qdq_bn"], [364, 0, 0, "-", "fuse_qdq_concatv2"], [365, 0, 0, "-", "fuse_qdq_conv"], [366, 0, 0, "-", "fuse_qdq_deconv"], [367, 0, 0, "-", "fuse_qdq_in"], [368, 0, 0, "-", "fuse_qdq_matmul"], [369, 0, 0, "-", "fuse_qdq_pooling"], [371, 0, 0, "-", "optimize_qdq"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn": [[363, 1, 1, "", "FuseNodeStartWithFusedBatchNormV3"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2": [[364, 1, 1, "", "FuseNodeStartWithConcatV2"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv": [[365, 1, 1, "", "FuseNodeStartWithConv2d"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv": [[366, 1, 1, "", "FuseNodeStartWithDeconv2d"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in": [[367, 1, 1, "", "FuseNodeStartWithFusedInstanceNorm"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul": [[368, 1, 1, "", "FuseNodeStartWithMatmul"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling": [[369, 1, 1, "", "FuseNodeStartWithPooling"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq": [[371, 1, 1, "", "OptimizeQDQGraph"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base": [[372, 1, 1, "", "QuantizeGraphBase"], [372, 1, 1, "", "QuantizeNodeBase"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn": [[373, 1, 1, "", "FuseNodeStartWithFusedBatchNormV3"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2": [[374, 1, 1, "", "FuseNodeStartWithConcatV2"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv": [[375, 1, 1, "", "FuseNodeStartWithConv2d"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu": [[376, 1, 1, "", "QuantizeGraphForIntel"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul": [[377, 1, 1, "", "FuseNodeStartWithMatmul"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling": [[378, 1, 1, "", "FuseNodeStartWithPooling"]], "neural_compressor.tensorflow.quantization.utils.quantize_graph_common": [[379, 1, 1, "", "QuantizeGraphHelper"]], "neural_compressor.tensorflow.quantization.utils.transform_graph": [[380, 0, 0, "-", "bias_correction"], [381, 0, 0, "-", "graph_transform_base"], [383, 0, 0, "-", "insert_logging"], [384, 0, 0, "-", "rerange_quantized_concat"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction": [[380, 1, 1, "", "BiasCorrection"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base": [[381, 1, 1, "", "GraphTransformBase"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging": [[383, 1, 1, "", "InsertLogging"]], "neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat": [[384, 1, 1, "", "RerangeQuantizedConcat"]], "neural_compressor.tensorflow.quantization.utils.utility": [[385, 2, 1, "", "apply_inlining"], [385, 2, 1, "", "collate_tf_preds"], [385, 2, 1, "", "construct_function_from_graph_def"], [385, 2, 1, "", "fix_ref_type_of_graph_def"], [385, 2, 1, "", "generate_feed_dict"], [385, 2, 1, "", "get_graph_def"], [385, 2, 1, "", "get_input_output_node_names"], [385, 2, 1, "", "get_model_input_shape"], [385, 2, 1, "", "get_tensor_by_name"], [385, 2, 1, "", "is_ckpt_format"], [385, 2, 1, "", "is_saved_model_format"], [385, 2, 1, "", "iterator_sess_run"], [385, 2, 1, "", "parse_saved_model"], [385, 2, 1, "", "read_graph"], [385, 2, 1, "", "reconstruct_saved_model"], [385, 2, 1, "", "strip_equivalent_nodes"], [385, 2, 1, "", "strip_unused_nodes"], [385, 2, 1, "", "write_graph"]], "neural_compressor.tensorflow.utils": [[386, 0, 0, "-", "constants"], [387, 0, 0, "-", "data"], [389, 0, 0, "-", "model"], [390, 0, 0, "-", "model_wrappers"], [391, 0, 0, "-", "utility"]], "neural_compressor.tensorflow.utils.data": [[387, 1, 1, "", "BaseDataLoader"], [387, 1, 1, "", "BatchSampler"], [387, 1, 1, "", "DummyDataset"], [387, 1, 1, "", "DummyDatasetV2"], [387, 1, 1, "", "IndexFetcher"], [387, 1, 1, "", "IterableFetcher"], [387, 1, 1, "", "IterableSampler"], [387, 1, 1, "", "SequentialSampler"], [387, 2, 1, "", "default_collate"]], "neural_compressor.tensorflow.utils.model": [[389, 1, 1, "", "Model"], [389, 1, 1, "", "TensorflowGlobalConfig"]], "neural_compressor.tensorflow.utils.model_wrappers": [[390, 1, 1, "", "BaseModel"], [390, 1, 1, "", "KerasModel"], [390, 1, 1, "", "TensorflowBaseModel"], [390, 1, 1, "", "TensorflowCheckpointModel"], [390, 1, 1, "", "TensorflowLLMModel"], [390, 1, 1, "", "TensorflowModel"], [390, 1, 1, "", "TensorflowSavedModelModel"], [390, 2, 1, "", "checkpoint_session"], [390, 2, 1, "", "estimator_session"], [390, 2, 1, "", "frozen_pb_session"], [390, 2, 1, "", "get_model_type"], [390, 2, 1, "", "get_tf_model_type"], [390, 2, 1, "", "graph_def_session"], [390, 2, 1, "", "graph_session"], [390, 2, 1, "", "keras_session"], [390, 2, 1, "", "load_saved_model"], [390, 2, 1, "", "saved_model_session"], [390, 2, 1, "", "slim_session"], [390, 2, 1, "", "try_loading_keras"], [390, 2, 1, "", "validate_and_inference_input_output"], [390, 2, 1, "", "validate_graph_node"]], "neural_compressor.tensorflow.utils.utility": [[391, 1, 1, "", "CaptureOutputToFile"], [391, 1, 1, "", "CpuInfo"], [391, 1, 1, "", "TFSlimNetsFactory"], [391, 2, 1, "", "combine_histogram"], [391, 2, 1, "", "deep_get"], [391, 2, 1, "", "disable_random"], [391, 2, 1, "", "dump_elapsed_time"], [391, 2, 1, "", "get_all_fp32_data"], [391, 2, 1, "", "get_tensor_histogram"], [391, 2, 1, "", "itex_installed"], [391, 2, 1, "", "register_algo"], [391, 2, 1, "", "singleton"], [391, 2, 1, "", "valid_keras_format"], [391, 2, 1, "", "version1_eq_version2"], [391, 2, 1, "", "version1_gt_version2"], [391, 2, 1, "", "version1_gte_version2"], [391, 2, 1, "", "version1_lt_version2"], [391, 2, 1, "", "version1_lte_version2"]], "neural_compressor.torch": [[394, 0, 0, "-", "algorithms"], [434, 0, 0, "-", "export"], [440, 0, 0, "-", "quantization"], [446, 0, 0, "-", "utils"]], "neural_compressor.torch.algorithms": [[392, 0, 0, "-", "base_algorithm"], [395, 0, 0, "-", "layer_wise"], [400, 0, 0, "-", "mixed_precision"], [402, 0, 0, "-", "mx_quant"], [407, 0, 0, "-", "pt2e_quant"], [410, 0, 0, "-", "smooth_quant"], [414, 0, 0, "-", "static_quant"], [428, 0, 0, "-", "weight_only"]], "neural_compressor.torch.algorithms.base_algorithm": [[392, 1, 1, "", "Quantizer"]], "neural_compressor.torch.algorithms.fp8_quant.utils": [[393, 0, 0, "-", "logger"]], "neural_compressor.torch.algorithms.layer_wise": [[396, 0, 0, "-", "load"], [397, 0, 0, "-", "modified_pickle"], [398, 0, 0, "-", "utils"]], "neural_compressor.torch.algorithms.layer_wise.load": [[396, 2, 1, "", "load"]], "neural_compressor.torch.algorithms.layer_wise.modified_pickle": [[397, 3, 1, "", "PickleError"], [397, 3, 1, "", "PicklingError"], [397, 3, 1, "", "UnpicklingError"]], "neural_compressor.torch.algorithms.layer_wise.utils": [[398, 1, 1, "", "QDQLayer"], [398, 2, 1, "", "clean_module_weight"], [398, 2, 1, "", "dowload_hf_model"], [398, 2, 1, "", "get_children"], [398, 2, 1, "", "get_module"], [398, 2, 1, "", "get_named_children"], [398, 2, 1, "", "get_super_module_by_name"], [398, 2, 1, "", "load_empty_model"], [398, 2, 1, "", "load_layer_wise_quantized_model"], [398, 2, 1, "", "load_module"], [398, 2, 1, "", "load_tensor"], [398, 2, 1, "", "load_tensor_from_shard"], [398, 2, 1, "", "load_value"], [398, 2, 1, "", "register_weight_hooks"], [398, 2, 1, "", "update_module"]], "neural_compressor.torch.algorithms.mixed_precision": [[399, 0, 0, "-", "half_precision_convert"], [401, 0, 0, "-", "module_wrappers"]], "neural_compressor.torch.algorithms.mixed_precision.half_precision_convert": [[399, 1, 1, "", "HalfPrecisionConverter"]], "neural_compressor.torch.algorithms.mixed_precision.module_wrappers": [[401, 1, 1, "", "HalfPrecisionModuleWrapper"]], "neural_compressor.torch.algorithms.mx_quant": [[403, 0, 0, "-", "mx"], [404, 0, 0, "-", "utils"]], "neural_compressor.torch.algorithms.mx_quant.mx": [[403, 1, 1, "", "MXLinear"], [403, 1, 1, "", "MXQuantizer"]], "neural_compressor.torch.algorithms.mx_quant.utils": [[404, 1, 1, "", "ElemFormat"], [404, 1, 1, "", "RoundingMode"], [404, 2, 1, "", "quantize_elemwise_op"], [404, 2, 1, "", "quantize_mx_op"]], "neural_compressor.torch.algorithms.pt2e_quant": [[405, 0, 0, "-", "core"], [406, 0, 0, "-", "half_precision_rewriter"], [408, 0, 0, "-", "save_load"], [409, 0, 0, "-", "utility"]], "neural_compressor.torch.algorithms.pt2e_quant.core": [[405, 1, 1, "", "W8A8PT2EQuantizer"]], "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter": [[406, 1, 1, "", "PatternPair"], [406, 2, 1, "", "apply_single_pattern_pair"], [406, 2, 1, "", "get_filter_fn"], [406, 2, 1, "", "get_half_precision_node_set"], [406, 2, 1, "", "get_unquantized_node_set"], [406, 2, 1, "", "pattern_factory"], [406, 2, 1, "", "transformation"]], "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter.PatternPair": [[406, 4, 1, "", "fn"], [406, 4, 1, "", "replace_pattern"], [406, 4, 1, "", "search_pattern"]], "neural_compressor.torch.algorithms.pt2e_quant.save_load": [[408, 2, 1, "", "load"], [408, 2, 1, "", "save"]], "neural_compressor.torch.algorithms.pt2e_quant.utility": [[409, 2, 1, "", "create_quant_spec_from_config"], [409, 2, 1, "", "create_xiq_quantizer_from_pt2e_config"]], "neural_compressor.torch.algorithms.smooth_quant": [[411, 0, 0, "-", "save_load"], [412, 0, 0, "-", "smooth_quant"], [413, 0, 0, "-", "utility"]], "neural_compressor.torch.algorithms.smooth_quant.save_load": [[411, 2, 1, "", "recover_model_from_json"]], "neural_compressor.torch.algorithms.smooth_quant.smooth_quant": [[412, 1, 1, "", "SmoothQuantQuantizer"], [412, 2, 1, "", "qdq_quantize"]], "neural_compressor.torch.algorithms.smooth_quant.utility": [[413, 1, 1, "", "AutoAlpha"], [413, 1, 1, "", "Calibration"], [413, 1, 1, "", "GraphTrace"], [413, 1, 1, "", "SQLinearWrapper"], [413, 1, 1, "", "TorchSmoothQuant"], [413, 1, 1, "", "WrapperLayer"], [413, 2, 1, "", "build_captured_dataloader"], [413, 2, 1, "", "cal_scale"], [413, 2, 1, "", "cfg_to_qconfig"], [413, 2, 1, "", "check_cfg_and_qconfig"], [413, 2, 1, "", "dump_model_op_stats"], [413, 2, 1, "", "enough_memo_store_scale"], [413, 2, 1, "", "forward_wrapper"], [413, 2, 1, "", "get_module"], [413, 2, 1, "", "get_parent"], [413, 2, 1, "", "get_quantizable_ops_recursively"], [413, 2, 1, "", "model_forward"], [413, 2, 1, "", "model_forward_per_sample"], [413, 2, 1, "", "move_input_to_device"], [413, 2, 1, "", "quant_dequant_w_v1"], [413, 2, 1, "", "quant_dequant_x_v1"], [413, 2, 1, "", "register_autotune"], [413, 2, 1, "", "reshape_in_channel_to_last"], [413, 2, 1, "", "reshape_scale_as_input"], [413, 2, 1, "", "reshape_scale_as_weight"], [413, 2, 1, "", "set_module"], [413, 2, 1, "", "update_sq_scale"]], "neural_compressor.torch.algorithms.static_quant": [[415, 0, 0, "-", "save_load"], [416, 0, 0, "-", "static_quant"], [417, 0, 0, "-", "utility"]], "neural_compressor.torch.algorithms.static_quant.save_load": [[415, 2, 1, "", "load"], [415, 2, 1, "", "save"]], "neural_compressor.torch.algorithms.static_quant.static_quant": [[416, 1, 1, "", "StaticQuantQuantizer"]], "neural_compressor.torch.algorithms.static_quant.utility": [[417, 1, 1, "", "TransformerBasedModelBlockPatternDetector"], [417, 2, 1, "", "cfg_to_qconfig"], [417, 2, 1, "", "check_cfg_and_qconfig"], [417, 2, 1, "", "dump_model_op_stats"], [417, 2, 1, "", "generate_activation_observer"], [417, 2, 1, "", "generate_xpu_qconfig"], [417, 2, 1, "", "get_depth"], [417, 2, 1, "", "get_dict_at_depth"], [417, 2, 1, "", "get_element_under_depth"], [417, 2, 1, "", "get_quantizable_ops_from_cfgs"], [417, 2, 1, "", "get_quantizable_ops_recursively"], [417, 2, 1, "", "parse_cfgs"], [417, 2, 1, "", "simple_inference"]], "neural_compressor.torch.algorithms.weight_only": [[418, 0, 0, "-", "autoround"], [419, 0, 0, "-", "awq"], [420, 0, 0, "-", "gptq"], [424, 0, 0, "-", "hqq"], [429, 0, 0, "-", "modules"], [430, 0, 0, "-", "rtn"], [431, 0, 0, "-", "save_load"], [432, 0, 0, "-", "teq"], [433, 0, 0, "-", "utility"]], "neural_compressor.torch.algorithms.weight_only.autoround": [[418, 1, 1, "", "AutoRoundQuantizer"], [418, 2, 1, "", "get_dataloader"]], "neural_compressor.torch.algorithms.weight_only.awq": [[419, 1, 1, "", "AWQQuantizer"]], "neural_compressor.torch.algorithms.weight_only.gptq": [[420, 1, 1, "", "GPTQ"], [420, 1, 1, "", "GPTQuantizer"], [420, 1, 1, "", "Quantizer"], [420, 1, 1, "", "RAWGPTQuantizer"], [420, 2, 1, "", "find_layers"], [420, 2, 1, "", "find_layers_name"], [420, 2, 1, "", "is_leaf"], [420, 2, 1, "", "log_quantizable_layers_per_transformer"], [420, 2, 1, "", "trace_gptq_target_blocks"]], "neural_compressor.torch.algorithms.weight_only.hqq": [[421, 0, 0, "-", "bitpack"], [422, 0, 0, "-", "config"], [423, 0, 0, "-", "core"], [425, 0, 0, "-", "optimizer"], [426, 0, 0, "-", "qtensor"], [427, 0, 0, "-", "quantizer"]], "neural_compressor.torch.algorithms.weight_only.hqq.bitpack": [[421, 1, 1, "", "Packer"]], "neural_compressor.torch.algorithms.weight_only.hqq.config": [[422, 1, 1, "", "HQQModuleConfig"], [422, 1, 1, "", "QTensorConfig"]], "neural_compressor.torch.algorithms.weight_only.hqq.core": [[423, 1, 1, "", "HQQLinear"], [423, 1, 1, "", "HQQTensorHandle"]], "neural_compressor.torch.algorithms.weight_only.hqq.optimizer": [[425, 2, 1, "", "optimize_weights_proximal_legacy"]], "neural_compressor.torch.algorithms.weight_only.hqq.qtensor": [[426, 1, 1, "", "QTensor"], [426, 1, 1, "", "QTensorMetaInfo"]], "neural_compressor.torch.algorithms.weight_only.hqq.qtensor.QTensorMetaInfo": [[426, 4, 1, "", "axis"], [426, 4, 1, "", "group_size"], [426, 4, 1, "", "nbits"], [426, 4, 1, "", "packing"], [426, 4, 1, "", "shape"]], "neural_compressor.torch.algorithms.weight_only.hqq.quantizer": [[427, 1, 1, "", "HQQuantizer"], [427, 2, 1, "", "filter_fn"], [427, 2, 1, "", "patch_hqq_moduile"], [427, 2, 1, "", "replacement_fn"]], "neural_compressor.torch.algorithms.weight_only.modules": [[429, 1, 1, "", "FakeAffineTensorQuantFunction"], [429, 1, 1, "", "HPUWeightOnlyLinear"], [429, 1, 1, "", "INCWeightOnlyLinear"], [429, 1, 1, "", "MulLinear"], [429, 1, 1, "", "QDQLayer"], [429, 1, 1, "", "TEQLinearFakeQuant"], [429, 1, 1, "", "UnpackedWeightOnlyLinearParams"], [429, 1, 1, "", "WeightOnlyLinear"]], "neural_compressor.torch.algorithms.weight_only.rtn": [[430, 1, 1, "", "RTNQuantizer"]], "neural_compressor.torch.algorithms.weight_only.save_load": [[431, 1, 1, "", "WOQModelLoader"], [431, 2, 1, "", "load"], [431, 2, 1, "", "save"]], "neural_compressor.torch.algorithms.weight_only.teq": [[432, 1, 1, "", "TEQuantizer"], [432, 1, 1, "", "TrainableEquivalentTransformation"]], "neural_compressor.torch.algorithms.weight_only.utility": [[433, 1, 1, "", "GraphTrace"], [433, 2, 1, "", "fetch_module"], [433, 2, 1, "", "forward_wrapper"], [433, 2, 1, "", "get_absorb_layers"], [433, 2, 1, "", "get_block_prefix"], [433, 2, 1, "", "get_module"], [433, 2, 1, "", "get_module_input_output"], [433, 2, 1, "", "get_parent"], [433, 2, 1, "", "model_forward"], [433, 2, 1, "", "move_input_to_device"], [433, 2, 1, "", "qdq_weight_actor"], [433, 2, 1, "", "qdq_weight_asym"], [433, 2, 1, "", "qdq_weight_sym"], [433, 2, 1, "", "quant_tensor"], [433, 2, 1, "", "quant_weight_w_scale"], [433, 2, 1, "", "quantize_4bit"], [433, 2, 1, "", "recover_forward"], [433, 2, 1, "", "replace_forward"], [433, 2, 1, "", "search_clip"], [433, 2, 1, "", "set_module"]], "neural_compressor.torch.export": [[435, 0, 0, "-", "pt2e_export"]], "neural_compressor.torch.export.pt2e_export": [[435, 2, 1, "", "export"], [435, 2, 1, "", "export_model_for_pt2e_quant"]], "neural_compressor.torch.quantization": [[437, 0, 0, "-", "algorithm_entry"], [438, 0, 0, "-", "autotune"], [439, 0, 0, "-", "config"], [441, 0, 0, "-", "load_entry"], [442, 0, 0, "-", "quantize"]], "neural_compressor.torch.quantization.algorithm_entry": [[437, 2, 1, "", "autoround_quantize_entry"], [437, 2, 1, "", "awq_quantize_entry"], [437, 2, 1, "", "fp8_entry"], [437, 2, 1, "", "gptq_entry"], [437, 2, 1, "", "hqq_entry"], [437, 2, 1, "", "mixed_precision_entry"], [437, 2, 1, "", "mx_quant_entry"], [437, 2, 1, "", "pt2e_dynamic_quant_entry"], [437, 2, 1, "", "pt2e_static_quant_entry"], [437, 2, 1, "", "rtn_entry"], [437, 2, 1, "", "smooth_quant_entry"], [437, 2, 1, "", "static_quant_entry"], [437, 2, 1, "", "teq_quantize_entry"]], "neural_compressor.torch.quantization.autotune": [[438, 2, 1, "", "autotune"], [438, 2, 1, "", "get_all_config_set"], [438, 2, 1, "", "get_rtn_double_quant_config_set"]], "neural_compressor.torch.quantization.config": [[439, 1, 1, "", "AWQConfig"], [439, 1, 1, "", "AutoRoundConfig"], [439, 1, 1, "", "DynamicQuantConfig"], [439, 1, 1, "", "FP8Config"], [439, 1, 1, "", "GPTQConfig"], [439, 1, 1, "", "HQQConfig"], [439, 1, 1, "", "MXQuantConfig"], [439, 1, 1, "", "MixedPrecisionConfig"], [439, 1, 1, "", "OperatorConfig"], [439, 1, 1, "", "RTNConfig"], [439, 1, 1, "", "SmoothQuantConfig"], [439, 1, 1, "", "StaticQuantConfig"], [439, 1, 1, "", "TEQConfig"], [439, 1, 1, "", "TorchBaseConfig"], [439, 2, 1, "", "get_all_registered_configs"], [439, 2, 1, "", "get_default_AutoRound_config"], [439, 2, 1, "", "get_default_awq_config"], [439, 2, 1, "", "get_default_double_quant_config"], [439, 2, 1, "", "get_default_dynamic_config"], [439, 2, 1, "", "get_default_fp8_config"], [439, 2, 1, "", "get_default_fp8_config_set"], [439, 2, 1, "", "get_default_gptq_config"], [439, 2, 1, "", "get_default_hqq_config"], [439, 2, 1, "", "get_default_mixed_precision_config"], [439, 2, 1, "", "get_default_mixed_precision_config_set"], [439, 2, 1, "", "get_default_mx_config"], [439, 2, 1, "", "get_default_rtn_config"], [439, 2, 1, "", "get_default_sq_config"], [439, 2, 1, "", "get_default_static_config"], [439, 2, 1, "", "get_default_teq_config"], [439, 2, 1, "", "get_woq_tuning_config"]], "neural_compressor.torch.quantization.load_entry": [[441, 2, 1, "", "load"]], "neural_compressor.torch.quantization.quantize": [[442, 2, 1, "", "convert"], [442, 2, 1, "", "finalize_calibration"], [442, 2, 1, "", "need_apply"], [442, 2, 1, "", "prepare"], [442, 2, 1, "", "quantize"]], "neural_compressor.torch.utils": [[443, 0, 0, "-", "auto_accelerator"], [444, 0, 0, "-", "constants"], [445, 0, 0, "-", "environ"], [447, 0, 0, "-", "utility"]], "neural_compressor.torch.utils.auto_accelerator": [[443, 1, 1, "", "AcceleratorRegistry"], [443, 1, 1, "", "Auto_Accelerator"], [443, 1, 1, "", "CPU_Accelerator"], [443, 1, 1, "", "CUDA_Accelerator"], [443, 1, 1, "", "HPU_Accelerator"], [443, 1, 1, "", "XPU_Accelerator"], [443, 2, 1, "", "auto_detect_accelerator"], [443, 2, 1, "", "register_accelerator"]], "neural_compressor.torch.utils.constants": [[444, 1, 1, "", "LoadFormat"]], "neural_compressor.torch.utils.environ": [[445, 2, 1, "", "device_synchronize"], [445, 2, 1, "", "get_accelerator"], [445, 2, 1, "", "get_ipex_version"], [445, 2, 1, "", "get_torch_version"], [445, 2, 1, "", "is_hpex_available"], [445, 2, 1, "", "is_ipex_available"], [445, 2, 1, "", "is_ipex_imported"], [445, 2, 1, "", "is_package_available"], [445, 2, 1, "", "is_transformers_imported"]], "neural_compressor.torch.utils.utility": [[447, 2, 1, "", "dowload_hf_model"], [447, 2, 1, "", "dump_model_op_stats"], [447, 2, 1, "", "fetch_module"], [447, 2, 1, "", "get_double_quant_config_dict"], [447, 2, 1, "", "get_model_device"], [447, 2, 1, "", "get_model_info"], [447, 2, 1, "", "get_processor_type_from_user_config"], [447, 2, 1, "", "get_quantizer"], [447, 2, 1, "", "load_empty_model"], [447, 2, 1, "", "postprocess_model"], [447, 2, 1, "", "register_algo"], [447, 2, 1, "", "set_module"]], "neural_compressor.training": [[448, 1, 1, "", "CallBacks"], [448, 1, 1, "", "CompressionManager"], [448, 2, 1, "", "fit"], [448, 2, 1, "", "prepare_compression"]], "neural_compressor.transformers": [[450, 0, 0, "-", "utils"]], "neural_compressor.transformers.quantization": [[449, 0, 0, "-", "utils"]], "neural_compressor.transformers.utils": [[451, 0, 0, "-", "quantization_config"]], "neural_compressor.transformers.utils.quantization_config": [[451, 1, 1, "", "AutoRoundConfig"], [451, 1, 1, "", "AwqConfig"], [451, 1, 1, "", "GPTQConfig"], [451, 1, 1, "", "INCQuantizationConfigMixin"], [451, 1, 1, "", "QuantizationMethod"], [451, 1, 1, "", "RtnConfig"], [451, 1, 1, "", "TeqConfig"]], "neural_compressor.utils": [[452, 0, 0, "-", "collect_layer_histogram"], [453, 0, 0, "-", "constant"], [454, 0, 0, "-", "create_obj_from_config"], [455, 0, 0, "-", "export"], [460, 0, 0, "-", "kl_divergence"], [461, 0, 0, "-", "load_huggingface"], [462, 0, 0, "-", "logger"], [463, 0, 0, "-", "options"], [464, 0, 0, "-", "pytorch"], [465, 0, 0, "-", "utility"], [466, 0, 0, "-", "weights_details"]], "neural_compressor.utils.collect_layer_histogram": [[452, 1, 1, "", "LayerHistogramCollector"]], "neural_compressor.utils.create_obj_from_config": [[454, 2, 1, "", "create_dataloader"], [454, 2, 1, "", "create_dataset"], [454, 2, 1, "", "create_eval_func"], [454, 2, 1, "", "create_train_func"], [454, 2, 1, "", "get_algorithm"], [454, 2, 1, "", "get_func_from_config"], [454, 2, 1, "", "get_metrics"], [454, 2, 1, "", "get_postprocess"], [454, 2, 1, "", "get_preprocess"]], "neural_compressor.utils.export": [[456, 0, 0, "-", "qlinear2qdq"], [457, 0, 0, "-", "tf2onnx"], [458, 0, 0, "-", "torch2onnx"]], "neural_compressor.utils.export.qlinear2qdq": [[456, 2, 1, "", "check_model"], [456, 2, 1, "", "onnx_qlinear_to_qdq"]], "neural_compressor.utils.export.tf2onnx": [[457, 2, 1, "", "tf_to_fp32_onnx"], [457, 2, 1, "", "tf_to_int8_onnx"]], "neural_compressor.utils.export.torch2onnx": [[458, 2, 1, "", "dynamic_quant_export"], [458, 2, 1, "", "get_node_mapping"], [458, 2, 1, "", "get_quantizable_onnx_ops"], [458, 2, 1, "", "static_quant_export"], [458, 2, 1, "", "torch_to_fp32_onnx"], [458, 2, 1, "", "torch_to_int8_onnx"]], "neural_compressor.utils.kl_divergence": [[460, 1, 1, "", "KL_Divergence"]], "neural_compressor.utils.load_huggingface": [[461, 1, 1, "", "OptimizedModel"], [461, 2, 1, "", "export_compressed_model"], [461, 2, 1, "", "save_for_huggingface_upstream"]], "neural_compressor.utils.logger": [[462, 1, 1, "", "Logger"], [462, 2, 1, "", "debug"], [462, 2, 1, "", "error"], [462, 2, 1, "", "fatal"], [462, 2, 1, "", "info"], [462, 2, 1, "", "log"], [462, 2, 1, "", "warn"], [462, 2, 1, "", "warning"]], "neural_compressor.utils.options": [[463, 1, 1, "", "onnxrt"]], "neural_compressor.utils.pytorch": [[464, 2, 1, "", "is_int8_model"], [464, 2, 1, "", "load"], [464, 2, 1, "", "load_weight_only"], [464, 2, 1, "", "recover_model_from_json"]], "neural_compressor.utils.utility": [[465, 1, 1, "", "CaptureOutputToFile"], [465, 1, 1, "", "CpuInfo"], [465, 2, 1, "", "Dequantize"], [465, 1, 1, "", "DotDict"], [465, 1, 1, "", "GLOBAL_STATE"], [465, 1, 1, "", "LazyImport"], [465, 1, 1, "", "MODE"], [465, 1, 1, "", "OpEntry"], [465, 1, 1, "", "Statistics"], [465, 2, 1, "", "alias_param"], [465, 2, 1, "", "calculate_mse"], [465, 2, 1, "", "check_key_exist"], [465, 2, 1, "", "combine_histogram"], [465, 2, 1, "", "compare_objects"], [465, 2, 1, "", "compute_sparsity"], [465, 2, 1, "", "deep_get"], [465, 2, 1, "", "deep_set"], [465, 2, 1, "", "dequantize_weight"], [465, 2, 1, "", "dump_class_attrs"], [465, 2, 1, "", "dump_data_to_local"], [465, 2, 1, "", "dump_elapsed_time"], [465, 2, 1, "", "dump_table"], [465, 2, 1, "", "dump_table_to_csv"], [465, 2, 1, "", "equal_dicts"], [465, 2, 1, "", "fault_tolerant_file"], [465, 2, 1, "", "get_all_fp32_data"], [465, 2, 1, "", "get_number_of_sockets"], [465, 2, 1, "", "get_op_list"], [465, 2, 1, "", "get_size"], [465, 2, 1, "", "get_tensor_histogram"], [465, 2, 1, "", "get_tensors_info"], [465, 2, 1, "", "get_tuning_history"], [465, 2, 1, "", "get_weights_details"], [465, 2, 1, "", "load_data_from_pkl"], [465, 2, 1, "", "mse_metric_gap"], [465, 2, 1, "", "print_op_list"], [465, 2, 1, "", "print_table"], [465, 2, 1, "", "recover"], [465, 2, 1, "", "set_random_seed"], [465, 2, 1, "", "set_resume_from"], [465, 2, 1, "", "set_tensorboard"], [465, 2, 1, "", "set_workspace"], [465, 2, 1, "", "show_memory_info"], [465, 2, 1, "", "singleton"], [465, 2, 1, "", "str2array"], [465, 2, 1, "", "time_limit"], [465, 2, 1, "", "version1_eq_version2"], [465, 2, 1, "", "version1_gt_version2"], [465, 2, 1, "", "version1_gte_version2"], [465, 2, 1, "", "version1_lt_version2"], [465, 2, 1, "", "version1_lte_version2"]], "neural_compressor.utils.weights_details": [[466, 1, 1, "", "WeightsDetails"], [466, 1, 1, "", "WeightsStatistics"]]}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "function", "Python function"], "3": ["py", "exception", "Python exception"], "4": ["py", "attribute", "Python attribute"], "5": ["py", "data", "Python data"]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:function", "3": "py:exception", "4": "py:attribute", "5": "py:data"}, "terms": {"": [30, 31, 90, 128, 133, 140, 150, 152, 173, 174, 175, 179, 180, 181, 182, 185, 187, 192, 194, 195, 208, 211, 224, 225, 232, 234, 235, 239, 262, 380, 385, 391, 396, 413, 431, 433, 441, 465, 469, 470, 471, 473, 474, 475, 476, 478, 480, 482, 487, 488, 489, 494, 495, 520, 524, 526, 527, 528, 529, 531, 536, 537, 541, 542, 543, 544, 547, 548, 549, 550, 552, 553], "0": [3, 30, 31, 39, 75, 90, 133, 139, 140, 145, 147, 149, 152, 153, 154, 163, 169, 171, 192, 195, 200, 202, 205, 206, 208, 209, 212, 213, 216, 221, 225, 234, 245, 262, 267, 281, 303, 311, 385, 387, 396, 413, 417, 425, 433, 439, 443, 451, 458, 461, 472, 473, 474, 476, 479, 481, 482, 485, 487, 490, 492, 502, 520, 521, 524, 526, 527, 528, 529, 532, 533, 534, 535, 536, 537, 539, 542, 544, 545, 547, 548, 549, 550, 551, 552], "00": [534, 553], "000": [211, 492], "0000": 538, "00000": 211, "00001": 211, "00003": 211, "00004": 211, "0001": [3, 195, 536], "0003": [534, 553], "0004": 536, "0005": 534, "0006": [534, 553], "0007": 553, "0008": [534, 553], "001": [211, 487, 524, 550], "0016": 534, "002": 524, "0021": 534, "0025": 534, "0029": [487, 550, 553], "00296431384049356": [487, 550], "0030": 553, "0036": [487, 550], "0040": 534, "0043": 534, "0046": [534, 553], "0048": 553, "005": 547, "0051": 534, "0058": 553, "0059755356051027775": [487, 550], "0061": 534, "006533813662827015": [487, 550], "00774": 542, "0086": [487, 550], "0097": 534, "00978": [439, 476, 487, 547], "01": [31, 153, 195, 425, 439, 476, 534, 536, 547, 552, 553], "0106": 553, "0115": 553, "0119": 553, "0130": 553, "0141": 553, "0142": 534, "017": 551, "01x": 553, "02": [195, 553], "0201": 534, "0213": 553, "02340": 169, "027": 553, "02x": 553, "03": [534, 553], "0352": 534, "03x": 553, "04": [492, 532, 553], "04191": 519, "0438": 553, "04x": 553, "05": [150, 195, 234, 413, 534, 535, 550, 553], "0500": [487, 550], "05516": [439, 476, 487], "0559": 534, "05754": 542, "05x": 553, "06": 553, "0626": 553, "0698": [487, 550], "06x": 553, "07": [487, 492, 550, 553], "0734": 553, "0737": [487, 550], "07x": 553, "08": [225, 534, 551, 553], "0806": [487, 550], "083": 553, "0837": 549, "08x": 553, "09": [534, 553], "0927": 553, "09656": 187, "099": 211, "0999": 553, "0f": 524, "0x": [140, 396], "0x2b0001b0": 553, "1": [3, 29, 30, 31, 40, 59, 74, 90, 94, 98, 131, 133, 140, 142, 145, 147, 149, 150, 151, 153, 154, 163, 169, 181, 182, 184, 195, 200, 202, 205, 206, 208, 209, 210, 212, 213, 216, 217, 221, 225, 230, 231, 232, 234, 245, 262, 280, 281, 284, 292, 294, 298, 312, 331, 346, 359, 383, 385, 387, 391, 396, 413, 417, 418, 420, 425, 429, 433, 439, 441, 451, 454, 461, 465, 469, 471, 472, 473, 474, 475, 476, 478, 479, 480, 481, 482, 487, 488, 490, 492, 493, 495, 519, 521, 526, 528, 532, 534, 535, 537, 539, 540, 541, 542, 544, 545, 547, 548, 549, 550, 551, 552], "10": [195, 211, 266, 425, 481, 482, 492, 518, 526, 532, 536, 542, 551, 552, 553], "100": [3, 151, 152, 153, 195, 211, 281, 301, 302, 305, 443, 480, 487, 518, 524, 530, 532, 536, 544, 551, 552, 553], "1000": 536, "10000": [266, 542], "10004": [473, 476, 477, 482, 490, 493, 521, 523, 524, 528, 531, 537, 539, 541, 545, 547], "10005": [539, 545], "10006": 523, "10016": [487, 550], "100x": [476, 487, 547], "101": [209, 234, 487, 535, 550, 553], "10163": 553, "1024": [131, 211, 383], "10271": [472, 539], "10281": [472, 539], "103": [551, 553], "10339": 553, "104": 553, "10438": [476, 487, 547, 550], "1052": 553, "10537": [472, 539], "1058": 553, "1077": 553, "10833": 225, "1095": 553, "10k": [418, 451, 525], "11": [473, 487, 532, 535, 537, 550, 552, 553], "1120": 553, "1129": 553, "1137": 553, "1139": 553, "1142": 553, "116": 551, "1161": 553, "1165": 553, "117": 553, "118": 553, "1186": 553, "119": [487, 550], "12": [534, 553], "120": [487, 550], "1209": 553, "123": [211, 551], "1244": 553, "124m": [474, 550], "1253": 553, "125m": [474, 529, 550], "126": 553, "1262": 553, "1268": 553, "127": [212, 213, 387, 487, 544, 550], "1276": 553, "128": [3, 31, 145, 209, 212, 213, 225, 387, 418, 420, 439, 451, 476, 481, 487, 536, 544, 547, 551, 553], "1280": 553, "1284": 553, "12b": 534, "12x": 553, "13": [487, 527, 532, 550, 553], "1324": 553, "13325": [476, 487, 547, 550], "135": 553, "136": 553, "1365": [225, 551], "1367": 553, "137": 553, "1374": 553, "1381": [487, 550], "1383": 553, "139": [487, 550, 553], "13b": [474, 534, 550, 553], "13x": 553, "14": [195, 457, 458, 526, 532, 553], "1406": 553, "142": 553, "14314": [476, 487, 547], "1451": 553, "1495": 553, "1498": 553, "14x": 553, "15": [133, 385, 528, 532, 534], "1510": [487, 550], "1512": 553, "1514": 553, "1515": 553, "1517": 553, "152": 553, "155": 553, "1556": 553, "1583": [487, 550], "1587": 553, "15x": 553, "16": [473, 532, 547, 553], "1601": [487, 550], "161": 553, "162": [487, 550, 553], "1658": 553, "16599": [487, 550], "1661": 553, "1666": 553, "16x": 553, "16x16gb": 553, "17": [485, 492, 532, 534], "170": 553, "1713": 553, "172": [487, 550, 553], "1720": 553, "173": 553, "17323": [420, 439, 476, 487, 547], "174": 553, "1742": [487, 550], "1747": 553, "1749": [487, 550], "175": 553, "17509": [487, 550], "1751": [487, 550], "176": 553, "177": [232, 553], "178": 553, "179": 553, "17x": 553, "18": [532, 534, 543, 553], "1809": 519, "1810": 169, "1838": 553, "184": 553, "18518": 135, "18529": 135, "186": 553, "1862": 553, "1889": 553, "1890": [487, 550], "18x": 553, "19": 553, "192": [487, 550], "1920": 553, "192795": 520, "195": 553, "1951": 553, "1956": 553, "1971": 553, "1978": 195, "1981": 553, "1983354538679123": [487, 550], "1989": 553, "19x": 553, "1_11_capabl": 495, "1b7": [474, 534, 550], "1e": [150, 413, 487, 550], "1e1": 425, "1s4c14ins1bsthroughput": 553, "1x": 553, "1x1": [536, 542], "1x2": [487, 550], "1xchannel": [195, 542], "2": [29, 30, 31, 39, 59, 90, 94, 140, 147, 149, 151, 153, 154, 175, 181, 182, 195, 210, 230, 232, 234, 245, 266, 281, 297, 311, 331, 359, 396, 413, 433, 441, 465, 470, 471, 472, 474, 475, 476, 478, 479, 480, 481, 482, 483, 487, 490, 492, 493, 502, 519, 521, 528, 529, 531, 532, 533, 534, 535, 537, 539, 540, 542, 543, 544, 545, 547, 548, 549, 550, 551, 552], "20": [225, 425, 542, 551, 553], "200": [224, 418, 439, 451, 476, 490, 552], "2000": 536, "2001": 209, "201": 553, "2011": 519, "2012": 211, "2017": 519, "2018": 519, "2019": 542, "2020": [135, 472, 539], "2021": 542, "20210514": 553, "2022": [195, 476, 487, 533, 542, 547, 550], "2023": [472, 476, 487, 492, 539, 542, 547, 550], "2024": [492, 553], "2043": 209, "2048": [3, 391, 418, 420, 439, 451, 465, 476, 547], "206": 553, "207": [487, 550, 553], "2080": 553, "2083": 553, "20b": [534, 553], "21": [234, 487, 534, 543, 550, 553], "21020": [487, 550], "2111": 542, "212": 553, "213": 553, "2132": 549, "214": 553, "215": 553, "2169": 553, "217": 553, "2198": 553, "21x": 553, "22": [532, 534, 553], "2204": 187, "2209": [476, 487, 547, 550, 553], "2210": [420, 439, 476, 487, 547], "2211": [476, 487, 547, 550], "2213": 553, "222": 553, "2220": [487, 550], "223": 553, "2232": 553, "224": [195, 221, 524, 526, 536, 551], "22444": [487, 550], "225": [221, 536, 553], "2287": 553, "229": [221, 536], "23": [154, 534, 553], "230": 553, "2301": 542, "2305": [476, 487, 547], "2306": [439, 476, 487, 547], "2309": [439, 476, 487], "2310": [472, 539], "234": 553, "235": 553, "2365": 553, "2384": 553, "23f1": 553, "23x": 553, "24": [154, 482, 542, 552, 553], "24101": 542, "24116": 542, "2420": [487, 550], "244": 553, "249": 553, "25": [542, 553], "250": 542, "2504": 553, "2538": 553, "255": [487, 544, 550], "256": [216, 221, 439, 524, 536, 551], "256gb": 553, "2570": [487, 550], "2584": 553, "25x": 553, "26": [534, 553], "2630": 553, "26f1": 553, "26x": 553, "27": [527, 534, 553], "2788": 553, "2793": 553, "2799": 553, "27x": 553, "28": [209, 210, 214, 553], "2805": 553, "281": 553, "282": 553, "2862": 553, "2897": 553, "28x": 553, "29": [534, 553], "2970": [487, 550], "298": 553, "2991": [487, 550], "29x": 553, "2d": [55, 327, 487, 550], "2e5m2": 471, "2gb": [243, 390], "2x": [525, 531], "2x1": [542, 553], "2x2": [487, 550], "2xlarg": 553, "3": [29, 31, 133, 140, 153, 154, 182, 195, 211, 225, 230, 281, 385, 396, 413, 441, 465, 472, 473, 475, 476, 478, 480, 481, 482, 487, 490, 492, 502, 519, 520, 521, 524, 526, 528, 529, 532, 535, 536, 537, 539, 540, 542, 543, 544, 547, 548, 549, 550, 551, 552, 553], "30": [225, 525, 531, 551, 553], "300": 542, "302": 553, "303": 553, "3067": 553, "30b": [474, 534, 550, 553], "30x": 553, "31": [30, 534, 553], "312": 553, "3121": 553, "31x": 553, "32": [31, 171, 280, 413, 418, 429, 433, 439, 451, 472, 473, 480, 481, 524, 530, 539, 547, 553], "320": 553, "3242": 553, "3253": [487, 550], "329": 553, "32accuraci": 553, "32x": 553, "33": [135, 472, 534, 539, 553], "3377": 553, "3388": 553, "339": 553, "33x": 553, "34": [492, 534, 553], "3429": 553, "344": 553, "3445": 553, "3463": 553, "349": 553, "34f1": 553, "34x": 553, "35": [534, 542, 553], "350m": [474, 550], "354": [474, 550], "3542": [474, 550], "358": 553, "35x": 553, "36": 553, "365": 553, "3686": 553, "36x": 553, "37": [534, 553], "373": 553, "374": 553, "3740": [487, 550], "375": 553, "3757": [474, 550], "377": 553, "379": [474, 550], "38": 553, "3804": [474, 550], "381": 542, "3815": [487, 550], "382": 553, "384": [225, 551], "3845": [487, 550], "3850": [487, 550], "385297635664756e": [487, 550], "3852e": [487, 550], "3887": [474, 550], "39": 553, "390": 553, "391": 553, "3911": [487, 550], "3924": [487, 550], "393": 553, "3930": [474, 550], "3947": [474, 550], "395": 553, "3950": 553, "396": 553, "399": 553, "3a14": 553, "3b": [474, 534, 550], "3d": [55, 327, 487, 543, 550], "3dgan": 543, "3f": 482, "3rd": [473, 487, 537, 543, 544, 546], "3x": 527, "4": [31, 39, 142, 145, 151, 154, 175, 184, 195, 218, 221, 225, 227, 228, 230, 280, 281, 311, 418, 429, 433, 439, 451, 470, 472, 474, 475, 476, 477, 482, 487, 488, 492, 493, 495, 518, 524, 525, 528, 531, 532, 535, 536, 539, 542, 544, 547, 550, 551, 552, 553], "40": [534, 553], "4019": 553, "404": [542, 553], "405": 553, "4055": [487, 550], "406": [536, 553], "4096": 553, "40b": 534, "41": 553, "4124": 553, "4149": [474, 550], "4172": [474, 550], "4193": 553, "42": [195, 418, 439, 476, 553], "420": 531, "4202": 553, "4208": 553, "4227": 553, "4237": 553, "4259": 553, "4271": 553, "42x": 553, "43": [534, 553], "4312": 553, "4319": 553, "434": 553, "4351": 553, "43x": 553, "44": 553, "440": 553, "4413": 553, "4430": 553, "4469": 549, "448": 553, "449": 553, "45": [490, 534, 553], "4516": [474, 550], "4533": [474, 550], "4542": 553, "456": 536, "46": [534, 553], "4607": 553, "4628": 553, "4634": [474, 550], "4697": 553, "46x": 553, "47": [154, 482, 534, 553], "471": 553, "4728": 553, "4731": 553, "4734": [487, 550], "4741": [487, 550], "4743": [487, 550], "4789": 553, "47x": 553, "48": [154, 487, 550, 553], "4800": 553, "4828": [474, 550], "484": [281, 553], "485": 536, "4895": 553, "4899": 553, "48x": 553, "49": [534, 553], "4906": [474, 550], "4907": 553, "4916": 553, "4923": 553, "4936": [474, 550], "494": 553, "4954": 553, "497": 553, "4973": 553, "4980": [474, 550], "4984": 553, "4f": 520, "4th": [473, 487, 534, 543, 544], "4x": [184, 487, 544], "4x1": [175, 195, 536, 542, 553], "5": [139, 149, 153, 163, 195, 213, 221, 234, 262, 303, 413, 417, 439, 474, 476, 479, 487, 493, 526, 528, 532, 535, 536, 542, 544, 547, 550, 551, 552, 553], "50": [232, 487, 494, 542, 550, 553], "5018": [474, 550], "504": 553, "5040": [487, 550], "5045": 553, "5048": [474, 550], "5049": 553, "5053": 553, "5057": [474, 550], "5058": 553, "5084": 553, "5098": 553, "50x": 553, "51": [534, 553], "511": 553, "512": [473, 476], "5142": 553, "517": 553, "5177": 553, "518": [474, 550], "5185": [474, 550], "52": 553, "5228": 553, "525": 553, "5282": 553, "52f1": 553, "53": [534, 553], "530": 553, "5328": 553, "533": 553, "534": 553, "535": 553, "5359": 553, "5369": 553, "5398": 553, "54": 553, "5419": 553, "5436": [474, 550], "5443": [474, 550, 553], "5444": [487, 550], "5477": 553, "548": 553, "549": 553, "5494": 553, "54accuraci": 553, "55": [534, 553], "5514": 553, "5523": 553, "5525": 553, "5540": 553, "5552": [474, 550], "5555": [487, 550], "5593": [474, 550, 553], "55x": 553, "56": 553, "5603": 553, "5604": 553, "560m": [474, 550], "5617": 553, "5637": 553, "5642": 553, "5655": 553, "566": 553, "567": 553, "5682": 553, "56be4db0acb8001400a502ec": 232, "57": [487, 534, 550, 553], "570": 553, "5711": 553, "5714": 553, "5716": 553, "5718": 553, "5732": 553, "5738": 553, "5742": [474, 550], "5752": 553, "5764": [474, 550, 553], "5765": 553, "577": 553, "5771": 553, "5777": 553, "5789": [474, 550], "5799": 553, "57x": 553, "58": [534, 553], "5814": 553, "5819": 553, "582": 553, "5823": 553, "5826": [487, 550], "5834": 553, "584": 553, "5841": 553, "5843": 553, "5871": 553, "588": 553, "5881": 553, "5898": 553, "5899": 553, "58x": 553, "59": [487, 534, 550, 553], "5911": 553, "5933": 553, "5934": 553, "5951": 553, "5972": [487, 550, 553], "5977": [474, 550], "598": 553, "5991": 553, "5997": 553, "59f1": 553, "59x": 553, "5b": [474, 550], "5gb": 431, "5x": 543, "6": [195, 472, 474, 476, 479, 487, 528, 539, 544, 550, 552, 553], "60": 553, "600": [536, 553], "6002": 553, "6004": 553, "6018": 553, "6029": 553, "6038": [487, 550], "6053": 553, "6057": 553, "6059": 553, "6094": 553, "60x": 553, "61": [534, 553], "611": 553, "6123": 553, "613": 553, "6134": 553, "6136": 553, "614": 553, "615": 553, "6154": 553, "6181": 553, "6187": 553, "619": 553, "6195": 553, "61accuraci": 553, "61x": 553, "62": [534, 553], "6224": 553, "623": 553, "6239": 553, "624": 553, "6247": [474, 550], "6261": 553, "6266": 553, "6297": [474, 550], "62x": 553, "63": [534, 542, 553], "6301": 553, "6312": 553, "635": 553, "636": 553, "6360": 553, "6361": 553, "6365": [474, 550], "637690492221736e": [487, 550], "6376e": [487, 550], "6377": 553, "6379": 553, "6390": 553, "6392": [474, 550], "6393": 553, "6396": 553, "6399": 553, "63x": 553, "64": [225, 439, 473, 481, 487, 534, 547, 550, 551, 553], "6401": 553, "6404": [474, 550], "6409": 553, "6410": 553, "6433": 553, "6434": 553, "6437": [474, 550, 553], "6438": 553, "6439": 553, "6448": 553, "6455": 553, "6456": 553, "6472": 553, "6473": 553, "6474": 553, "648": 553, "6481": [487, 550], "6483": 553, "6484": 553, "6488": 553, "6491": 553, "6496": 553, "6497": 553, "6499": [474, 550], "64x": 553, "65": 553, "6504": 553, "6505": 553, "6506": [487, 550], "6509": 553, "6519": 553, "652": 553, "6527": 553, "6532": 553, "6535": 553, "6542": [474, 550], "65421": 520, "6543": 553, "655": [474, 550, 553], "6559": 553, "6569": [474, 550], "6571": 553, "6575": 553, "6579": 553, "6582": 553, "659": 553, "6594": 553, "6598": 553, "65b": [474, 550], "65x": 553, "66": 553, "6604": 553, "6612": 553, "6614": 553, "6621": [474, 550], "6622": 553, "663": 553, "6654": 553, "6661": 553, "6669": 553, "6678": 553, "6685": 553, "6687": 553, "6693": 553, "66b": [474, 550], "66x": 553, "67": [534, 553], "6709": 553, "6713": 553, "6718": [474, 550], "6719": 553, "6724": 553, "6726": 553, "6735": [474, 550], "6739": 553, "6740": [474, 550, 553], "6742": 553, "6746": 553, "6748": 553, "6756": 553, "6769": [474, 550, 553], "678": 553, "679": 553, "67x": 553, "68": [534, 551, 553], "6803": 553, "6804": [474, 550, 553], "6814": [474, 550], "6820": 553, "6821": [474, 487, 550], "6824": 553, "6827": 553, "6829": 553, "6831": [474, 550, 553], "6832": 553, "6835": [487, 550], "6836": [487, 550], "6837": [487, 550], "6839": [487, 550], "684": 553, "6845": 553, "6848": [487, 550], "685": 553, "6854": 553, "6857": 553, "6859": 553, "6861": 553, "6862": 553, "6864": 553, "6866": [474, 550, 553], "6872": [474, 550], "6876": 553, "6878": 553, "6883": [487, 550], "6885": 553, "6887": 553, "689": 553, "6890": 553, "6895": [474, 550], "69": 553, "6902": 553, "6911": 553, "6918": 553, "693": 553, "6953": [474, 550, 553], "6961": 553, "6977": 553, "6982": 553, "6994": 550, "6ap0": 553, "6b": [474, 534, 550, 553], "6f": 524, "7": [29, 151, 154, 195, 245, 413, 425, 433, 474, 476, 479, 487, 495, 518, 527, 528, 536, 542, 544, 548, 550, 552, 553], "70": [534, 553], "7002": 553, "7006": 553, "7009": 553, "7018": 553, "7022": 553, "7024": 553, "7025": 553, "7030": 553, "7031": 553, "7032": 553, "7034": 553, "7056": 553, "7058": [550, 553], "707": 553, "7075": 553, "7077": 553, "7080": 553, "7088": 553, "70b": [534, 553], "70x": 553, "71": [154, 534, 553], "7103": 553, "7105": 553, "7106": 553, "7107": 553, "7111": 553, "712": 553, "7122": 553, "7128": [474, 550], "714": 553, "7143": [474, 550], "7149": [474, 550], "715": 553, "7153": 553, "7174": [487, 550], "718": 553, "7186": 553, "7190": 553, "7198": 553, "71x": 553, "72": [154, 487, 534, 550, 553], "7203": 553, "722": 553, "7221": [474, 550], "7233": 553, "7240": 553, "7243": 553, "7244": 553, "7246": 553, "7247": 553, "7268": 553, "7269": 553, "727": 553, "7273": 553, "7277": 553, "728": 553, "7283": 553, "7285": 553, "72x": 553, "73": [534, 553], "7312": 553, "732": 553, "7322": 553, "7323": 553, "7326": [474, 550], "733": 553, "7332": 550, "7334": 553, "7335": 550, "7337": 553, "734": 553, "7350": 553, "7353": 553, "7357": [474, 550], "7361": [474, 550, 553], "7392": [550, 553], "7398": [474, 550], "7399": 553, "73x": 553, "74": [534, 553], "7415": 553, "7432": 553, "7440": [487, 550], "7442": 553, "7443": 553, "7448": 553, "7451": [487, 550], "7476": 553, "7486": 553, "7495": 549, "7497": 553, "74x": 553, "75": [534, 542, 553], "7518": 553, "7519": 553, "753": 553, "754": 473, "7541": 553, "7543": 553, "756": 553, "7566": 553, "7568": 553, "7572": 553, "7589": [487, 550], "7590": [474, 550], "7596": 553, "75x": 553, "76": [534, 553], "7608": [487, 550], "7615": [550, 553], "7616": 553, "7617": 553, "7622": 553, "7627": [474, 550, 553], "7628": 553, "7632": 550, "7633": 553, "7634": 553, "767": 553, "7675": 553, "7677": [550, 553], "7682": 553, "7699": 553, "76x": 553, "77": [534, 553], "770": 553, "7704": 553, "7706": 553, "7715": 553, "7742": 553, "774m": [474, 550], "7753": 553, "7758": 553, "7759": [474, 550, 553], "7764": 553, "7772": [487, 550], "778": 553, "7797": 553, "77x": 553, "78": [551, 553], "780": 553, "7807": 553, "7813": 553, "7824": 553, "7828": 553, "7829": 553, "783": 553, "7835": 553, "7836": 553, "784": 553, "7840": [474, 550], "7845": 553, "7851": 553, "7856": 553, "7873": 553, "7878": 553, "7894": 553, "7895": 542, "79": [534, 553], "790": 553, "7905": 553, "7908": [474, 550], "7911": 553, "7927": 553, "7941": 553, "7957": [474, 550], "7964": 553, "7965": 553, "79x": 553, "7b": [474, 483, 492, 534, 550, 553], "7b1": [474, 550, 553], "8": [98, 140, 154, 195, 224, 396, 404, 413, 418, 433, 439, 451, 470, 471, 472, 474, 476, 477, 487, 490, 494, 519, 520, 528, 532, 539, 542, 543, 547, 550, 552, 553], "80": [527, 534, 545, 553], "800": [225, 551], "8001": [1, 452], "801": 542, "8018": 553, "8025": 553, "8044": 553, "8047": 553, "805": 547, "8058": 553, "8074": 553, "8084": 553, "8096": 553, "81": 553, "8146": 553, "8178": 553, "82": [534, 553], "8207": [487, 550], "8213": 553, "822": 553, "8235": 553, "8246": [487, 550], "8256": 553, "8259": 553, "8266": 549, "8291": 549, "8294": 549, "8298": [487, 550], "8299": 549, "82x": 553, "83": [487, 549, 550, 553], "8314": 553, "8363": 553, "8371": 553, "8372": 549, "8382": 553, "83x": 553, "84": [487, 550, 553], "841": 553, "8411": 553, "8480": 553, "84x": 553, "85": [487, 549, 550, 553], "8539": 553, "85x": 553, "86": [534, 553], "8626": 553, "863": 553, "8684": 553, "86x": 553, "87": [221, 534, 553], "875": [221, 551], "8763": [487, 550], "8768": [487, 550], "8780": 553, "8782": 553, "87f1": 553, "88": [527, 549, 553], "8809": 553, "8814": 553, "8816": 553, "8863": 553, "88x": 553, "89": [487, 534, 550, 553], "893": 553, "8984": 553, "89x": 553, "8ghz": 553, "8x1": 195, "9": [169, 195, 474, 482, 490, 532, 536, 542, 550, 552, 553], "90": [195, 534, 545, 553], "9048": 553, "9091": 553, "90f1": 553, "91": [487, 547, 550, 553], "9125": 553, "9163": 553, "91x": 553, "92": [534, 553], "921": 553, "925": 553, "927": 553, "93": [487, 550, 553], "9301": [487, 550], "9308": [487, 550], "9317": 553, "9324": 553, "9359": 553, "93x": 553, "94": [551, 553], "9403": 553, "9411": 553, "94x": 553, "95": [75, 154, 234, 535, 553], "951": 553, "9522": 553, "9527": [266, 536], "953": 553, "95top1": 553, "95x": 553, "96": [534, 553], "9635": 553, "97": [534, 536, 553], "9702": 553, "98": [195, 536, 542, 553], "9860": [487, 550], "9867": 534, "9892": 553, "99": [3, 153, 303, 553], "9902": 553, "9906": 553, "9907": 534, "9909": 553, "9911": 534, "9915": 534, "9916": 553, "9917": 553, "9919": 553, "9921": 553, "9922": 553, "9928": 534, "9930": 534, "9931": 553, "9932": 553, "9933": [534, 553], "9934": 553, "9935": 553, "9937": 553, "9941": 553, "9942": 553, "9944": 553, "9945": [534, 553], "9947": 553, "9950": 553, "9951": 553, "9952": 553, "9953": 553, "9955": 534, "9957": [534, 553], "9958": 553, "9961": 553, "9962": 553, "9963": 553, "9967": 553, "9971": 553, "9972": 534, "9975": 534, "9976": 534, "9978": 553, "9979": 553, "9983": 553, "9984": [534, 553], "9986": 534, "9987": 534, "9988": 534, "9989": 534, "999": [3, 303], "9990": 534, "9991": 534, "9992": 534, "9994": [534, 553], "9995": 534, "9997": 534, "9998": 553, "99ccff": 552, "99x": 553, "A": [3, 40, 59, 60, 88, 101, 125, 126, 133, 138, 145, 152, 153, 159, 161, 162, 169, 170, 173, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 195, 211, 225, 227, 230, 231, 232, 234, 235, 239, 243, 266, 283, 286, 312, 331, 332, 385, 389, 390, 391, 397, 404, 406, 409, 412, 413, 415, 425, 427, 433, 443, 448, 465, 474, 476, 477, 487, 489, 494, 520, 521, 525, 528, 534, 535, 536, 538, 542, 543, 544, 547, 550, 551, 552], "And": [55, 327, 480, 487, 489, 490, 518, 520, 536, 550], "As": [471, 476, 487, 490, 494, 521, 535, 536, 542, 547, 552], "At": [472, 489, 494, 539, 552], "Being": 488, "By": [140, 173, 195, 227, 396, 476, 483, 494, 495, 535, 538, 542, 543, 547, 552], "For": [29, 31, 145, 149, 153, 156, 160, 173, 174, 177, 178, 188, 195, 211, 225, 231, 232, 234, 235, 262, 413, 431, 433, 439, 465, 471, 474, 476, 477, 478, 479, 483, 487, 488, 490, 491, 493, 495, 523, 524, 526, 528, 529, 531, 542, 546, 547, 550, 552, 553], "IT": [211, 218, 543], "If": [52, 53, 55, 59, 140, 151, 153, 156, 195, 198, 199, 211, 225, 235, 262, 281, 324, 325, 327, 331, 396, 413, 431, 433, 435, 441, 447, 448, 451, 471, 477, 480, 487, 489, 490, 494, 518, 520, 521, 524, 527, 532, 533, 535, 536, 540, 542, 544, 547, 549, 550, 551, 552], "In": [162, 177, 178, 179, 184, 185, 186, 189, 195, 208, 230, 245, 447, 469, 476, 477, 480, 487, 488, 490, 492, 493, 494, 521, 523, 524, 535, 536, 540, 541, 542, 544, 546, 547, 549, 550, 551, 552], "It": [39, 140, 159, 162, 166, 175, 198, 199, 232, 234, 235, 262, 267, 271, 311, 396, 433, 442, 448, 472, 475, 476, 477, 478, 480, 481, 487, 493, 494, 495, 519, 527, 529, 536, 539, 542, 544, 547, 549, 552], "Its": [494, 519, 542], "NOT": [209, 528], "No": [413, 489, 520, 527, 536, 543], "Not": [277, 278, 391, 465, 471, 520], "ON": 546, "Of": 521, "On": [487, 544, 553], "One": [477, 495, 520, 524, 531, 542, 543, 552], "TO": 524, "The": [3, 21, 39, 59, 98, 104, 106, 125, 133, 140, 145, 146, 151, 152, 153, 155, 156, 158, 160, 161, 162, 163, 165, 169, 173, 175, 177, 178, 180, 181, 182, 187, 188, 189, 190, 191, 192, 195, 198, 199, 200, 209, 210, 211, 212, 213, 217, 218, 225, 227, 228, 229, 231, 232, 234, 235, 243, 245, 262, 263, 264, 265, 266, 267, 268, 269, 271, 272, 273, 274, 278, 280, 281, 283, 284, 288, 292, 293, 294, 297, 298, 299, 301, 302, 305, 311, 331, 344, 361, 385, 386, 387, 388, 389, 390, 391, 392, 396, 405, 406, 407, 408, 409, 410, 412, 413, 414, 416, 417, 418, 422, 423, 425, 426, 427, 431, 433, 435, 437, 438, 439, 441, 442, 443, 447, 448, 452, 454, 460, 461, 464, 465, 466, 469, 470, 471, 472, 473, 475, 476, 477, 479, 480, 481, 487, 488, 490, 493, 494, 495, 496, 498, 504, 507, 510, 518, 519, 520, 521, 524, 526, 528, 529, 530, 531, 532, 534, 535, 536, 537, 538, 539, 540, 541, 542, 544, 545, 546, 547, 548, 549, 550, 551, 552, 553], "Their": 454, "Then": [230, 487, 494, 550, 552], "There": [100, 263, 265, 470, 475, 479, 487, 492, 520, 528, 531, 536, 547, 550, 552], "These": [494, 531], "To": [30, 230, 245, 392, 472, 473, 474, 475, 476, 479, 481, 482, 487, 489, 492, 494, 495, 520, 524, 537, 539, 542, 546, 547, 548, 550, 552], "Will": [128, 380, 441, 531], "With": [81, 245, 352, 480, 487, 490, 493, 495, 521, 532, 536, 540, 542, 543, 544, 549, 550, 552, 553], "_": [198, 199, 262, 473, 474, 476, 477, 480, 482, 487, 490, 492, 493, 494, 519, 524, 526, 528, 532, 536, 537, 538, 540, 542, 544, 547, 548, 549, 550, 552], "__all__": 520, "__call__": 218, "__class__": 245, "__getitem__": [207, 211, 225, 521, 536], "__init__": [431, 441, 493, 520, 521, 535, 552], "__iter__": [207, 211, 521, 536], "__len__": [207, 211], "__name__": 245, "__str__": 451, "__version__": [1, 138, 397, 520], "_configset": 153, "_description_": [438, 477], "_epoch_ran": 162, "_generate_dataload": [200, 387], "_inductor": [470, 475], "_lossandgradi": 520, "_propagate_qconfig_help": 145, "_quantiz": 458, "_quantizedconv": [76, 347], "_quantizeddeconv": [76, 347], "_quantizedfusedbatchnorm": [108, 363], "_quantizedmatmul": [78, 79, 349, 350], "_saved_model": [133, 385], "_type_": [145, 461], "_use_new_zipfile_seri": 170, "a100cuda": 553, "aarch64": 518, "ab": [30, 169, 187, 420, 433, 439, 480, 487, 542, 544, 550], "abbrevi": 195, "abc": [98, 232, 493, 552], "abcadaptor": 493, "abctunestrategi": 552, "abil": [472, 493, 494, 528, 539, 550], "abl": [198, 199, 235, 262, 448, 480, 487, 544], "abound": 543, "about": [169, 191, 465, 469, 471, 488, 520, 521, 536, 542, 546, 552, 553], "abov": [39, 311, 474, 475, 476, 478, 487, 493, 494, 495, 542, 544, 550, 552], "absolut": [169, 195, 234, 413, 472, 487, 535, 536, 539, 542, 544, 552], "absorb": [145, 149, 413, 433, 476, 547], "absorb_layer_dict": [419, 439, 451], "absorb_pair": 31, "absorb_to_lay": [145, 413, 432, 433, 439], "absorbed_1": [145, 433], "absorpt": [145, 433], "abstract": [71, 162, 225, 343, 493, 495, 530], "abus": 488, "ac": 266, "acc": [473, 478, 534, 542, 553], "acceler": [171, 439, 443, 445, 471, 473, 474, 476, 477, 479, 487, 492, 532, 536, 542, 543, 546, 547, 550, 552], "accelerator_execution_tim": 251, "acceleratorregistri": 443, "accept": [195, 281, 481, 488, 518, 520, 521, 547], "access": [52, 53, 55, 195, 324, 325, 327, 461, 465], "accommod": [494, 495], "accompani": [533, 552], "accord": [1, 107, 145, 151, 195, 209, 210, 211, 225, 269, 271, 392, 442, 447, 454, 471, 480, 481, 487, 493, 524, 542, 546, 550, 551, 552], "accordingli": 550, "account": [488, 549, 552], "accumul": [277, 472, 476, 539, 552], "accur": [29, 149, 413, 420, 439, 475, 476, 487, 542, 547, 550], "accuraci": [31, 151, 153, 192, 195, 198, 199, 234, 235, 245, 262, 267, 281, 448, 472, 474, 475, 476, 480, 481, 483, 490, 492, 494, 495, 519, 521, 523, 524, 525, 526, 529, 535, 536, 539, 540, 541, 542, 543, 547, 548, 549, 550, 553], "accuracy_criterion": [195, 245, 536, 540, 552], "accuracy_level": 31, "accuracycriterion": [195, 536, 552], "accuracyspars": 553, "achiev": [474, 475, 476, 477, 478, 481, 483, 487, 526, 534, 536, 541, 542, 543, 544, 550, 552], "acq": 266, "acq_max": 266, "acquisit": 266, "across": [235, 392, 472, 481, 522, 529, 536, 539, 542, 545, 550, 552], "act": [192, 207, 387, 488], "act_algo": [413, 439, 475], "act_algorithm": 303, "act_bit": [418, 439], "act_dtyp": [299, 303, 439, 472, 474, 475, 478, 539], "act_dynam": [418, 439], "act_fn": 174, "act_granular": [299, 303, 439, 478], "act_group_s": [418, 439], "act_max_valu": [292, 293, 294, 297, 298], "act_maxabs_hw_weights_pcs_maxabs_pow2": 471, "act_maxabs_pow2_weights_pcs_opt_pow2": 471, "act_min_valu": [292, 293, 294, 297, 298], "act_ord": [439, 476], "act_sym": [299, 303, 418, 439, 475, 478, 480, 481], "action": 488, "activ": [16, 31, 126, 145, 166, 195, 278, 280, 286, 292, 293, 294, 298, 413, 417, 439, 470, 471, 474, 475, 476, 479, 480, 487, 493, 494, 495, 519, 523, 528, 536, 544, 547, 550], "activation_max": 465, "activation_min": 465, "activation_min_max": 465, "activationoper": 5, "activity_regular": [292, 293, 294, 298], "actord": [31, 476, 547], "actual": [234, 475, 524, 527], "ad": [186, 209, 227, 266, 470, 473, 476, 494, 495, 537, 542, 547], "adadelta": 524, "adam": 165, "adamw": 165, "adapt": [472, 488, 494, 539, 543], "adaptor": [162, 195, 280, 288, 289, 454, 469, 495, 531, 545, 546, 548, 550], "adaptor_registri": 493, "add": [30, 38, 49, 94, 104, 133, 165, 192, 195, 209, 211, 278, 310, 321, 359, 385, 465, 469, 474, 489, 490, 492, 495, 521, 524, 526, 528, 535, 536, 549, 550, 552], "add_origin_loss": [163, 195], "add_port_to_nam": 90, "add_qdq_pair_to_weight": [28, 195, 544], "add_relu": 526, "addit": [145, 195, 431, 448, 476, 494, 495, 547, 548, 552], "addition": [476, 495, 524, 542, 552], "addn": 528, "address": [211, 473, 476, 481, 488, 520, 537, 543], "addv2": [38, 54, 310, 326, 528], "adher": 489, "adjust": [487, 544, 550], "adopt": [487, 489, 542, 543, 550], "advanc": [135, 195, 472, 473, 476, 478, 480, 487, 488, 494, 499, 534, 539, 542, 544, 547], "advantag": [473, 542, 552], "afc": 232, "affect": [487, 550], "affin": [142, 429, 544], "aforement": 536, "after": [1, 63, 133, 145, 171, 175, 180, 182, 187, 195, 209, 221, 225, 267, 281, 335, 385, 406, 413, 445, 461, 465, 470, 471, 475, 476, 479, 487, 492, 494, 523, 526, 531, 535, 536, 540, 541, 542, 544, 546, 547, 549, 550, 551, 552], "ag": 488, "again": [211, 546], "against": [228, 406], "aggress": 552, "agnost": [157, 477], "agnostic_mod": 230, "agre": 489, "ai": [469, 472, 473, 477, 492, 539, 543, 546], "aid": 522, "aim": [469, 481, 492, 529, 534, 542, 550, 552], "ajanthan": 542, "al": [135, 472, 476, 487, 492, 519, 532, 539, 547, 550], "albert": 553, "alemb": 527, "alexnet": 553, "algo": [156, 288, 289, 409, 442, 454], "algo_nam": [152, 305, 442, 520], "algorithm": [1, 31, 145, 152, 156, 195, 226, 227, 234, 290, 299, 301, 305, 391, 436, 437, 439, 441, 442, 447, 454, 460, 476, 477, 480, 481, 483, 487, 492, 493, 494, 495, 520, 523, 528, 529, 531, 534, 542, 544], "algorithm_entri": [304, 440, 520], "algorithm_registri": 146, "algorithm_typ": 146, "algorithmschedul": 146, "algos_map": [391, 447], "alia": [462, 465], "alias": [465, 520], "alias_param": 465, "alibaba": [492, 543], "align": [225, 471, 488, 547, 551], "alignimagechannel": 551, "alignimagechanneltransform": 225, "alistarh": 542, "all": [1, 3, 21, 31, 48, 82, 140, 141, 145, 146, 148, 151, 152, 154, 157, 162, 165, 170, 175, 183, 192, 195, 200, 201, 207, 211, 218, 225, 227, 230, 232, 234, 236, 245, 274, 280, 282, 299, 302, 320, 353, 387, 389, 390, 391, 392, 396, 398, 413, 417, 420, 429, 438, 439, 441, 454, 458, 465, 471, 474, 477, 480, 481, 483, 487, 488, 489, 492, 493, 494, 495, 520, 521, 524, 528, 532, 536, 541, 542, 543, 544, 546, 547, 550, 551, 552], "all_par": [413, 433], "allbalanc": 553, "allenai": [231, 232], "allevi": 550, "alloc": 482, "allow": [145, 152, 266, 433, 473, 475, 476, 481, 524, 535, 536, 537, 542, 547, 550, 552], "allowlist": [439, 471], "along": [425, 426, 431, 476, 532, 542, 547], "alpha": [126, 139, 142, 149, 169, 189, 286, 303, 413, 417, 429, 439, 487, 520, 544, 552], "alpha_list": 277, "alpha_max": [413, 439, 550], "alpha_min": [413, 439, 550], "alpha_step": [413, 439, 550], "alreadi": [140, 151, 211, 224, 396, 473, 477, 493, 527, 531, 552], "also": [138, 174, 208, 211, 225, 227, 234, 245, 262, 397, 471, 473, 476, 477, 478, 479, 487, 489, 493, 494, 495, 521, 525, 529, 531, 535, 536, 540, 542, 543, 544, 546, 547, 550, 552], "altern": [140, 195, 262, 396], "although": [208, 549], "alwai": [153, 230, 234, 262, 471, 481, 535, 536, 547], "amax": [433, 472, 539], "amazon": 492, "amd": [492, 532, 553], "among": [234, 472, 487, 539, 550], "amount": [3, 413, 479, 550], "amp": [1, 418, 547], "amp_cfg": 1, "amp_convert": 1, "amx": [473, 543], "an": [1, 52, 53, 55, 90, 126, 128, 133, 135, 138, 140, 145, 150, 166, 180, 195, 203, 207, 211, 225, 226, 227, 231, 232, 235, 257, 261, 262, 281, 286, 324, 325, 327, 380, 385, 396, 397, 409, 417, 433, 447, 448, 465, 467, 471, 472, 473, 474, 475, 476, 477, 479, 480, 481, 487, 488, 490, 492, 493, 495, 519, 521, 522, 526, 534, 535, 536, 537, 539, 540, 542, 543, 544, 547, 549, 550, 551, 552], "anaconda": 532, "analysi": [472, 539, 542, 549], "analyt": [469, 532, 543], "analyz": [95, 173, 243, 360, 390, 549, 550], "andrew": 519, "ani": [135, 140, 156, 230, 232, 257, 261, 277, 281, 302, 392, 396, 422, 435, 442, 443, 451, 465, 477, 480, 488, 492, 495, 520, 524, 542, 549, 552], "anneal": 168, "anno_dir": 210, "anno_path": [234, 535], "annot": [210, 230, 281, 494, 495, 535, 542, 552], "anoth": [225, 227, 465, 551, 552], "answer": [225, 231, 232, 488, 542, 551, 553], "answer_start": 232, "answeringsquad": 553, "ao": 409, "ap": 535, "ap0": 553, "apach": [3, 533], "api": [55, 60, 95, 154, 230, 234, 262, 277, 278, 281, 290, 302, 303, 304, 305, 327, 332, 360, 389, 391, 392, 420, 436, 438, 439, 440, 442, 444, 465, 471, 474, 476, 481, 487, 490, 492, 496, 498, 504, 507, 510, 526, 527, 529, 531, 532, 536, 548, 549, 552, 554], "appear": [140, 396, 488], "append": [145, 266, 490, 523, 536, 541], "append_attr": 145, "appl": 552, "appli": [31, 98, 111, 112, 113, 116, 118, 122, 133, 142, 162, 184, 186, 228, 301, 305, 366, 367, 368, 371, 373, 377, 385, 392, 406, 413, 429, 437, 442, 447, 469, 472, 475, 479, 480, 481, 487, 488, 494, 495, 536, 539, 541, 542, 544, 546, 549, 550, 552], "applianc": 543, "applic": [221, 431, 476, 478, 487, 495, 526, 543, 547, 550, 551], "apply_awq_clip": 31, "apply_awq_scal": 31, "apply_inlin": [133, 385], "apply_single_pattern_pair": 406, "appoint": 488, "approach": [195, 475, 476, 487, 490, 519, 531, 536, 542, 543, 545, 547, 552], "appropri": [443, 475, 481, 483, 487, 488, 519, 550], "approv": 489, "approx": [476, 487, 547], "approxim": [227, 228, 476, 494, 535, 547], "appu": 476, "apr": [492, 543], "apt": [527, 532], "ar": [52, 53, 90, 140, 145, 154, 175, 180, 181, 182, 187, 195, 209, 225, 230, 234, 263, 265, 266, 280, 281, 324, 325, 392, 396, 406, 409, 413, 417, 454, 464, 465, 470, 471, 472, 473, 475, 476, 477, 479, 480, 483, 487, 488, 489, 490, 493, 494, 520, 521, 523, 524, 525, 526, 528, 530, 531, 533, 534, 535, 536, 537, 539, 540, 541, 542, 543, 544, 546, 547, 548, 549, 550, 551, 552], "arang": 550, "arbitrari": [140, 396, 477, 536, 541], "arcfac": 553, "architectur": [151, 469, 473, 476, 483, 487, 492, 518, 529, 536, 542, 543, 547], "arctic": 532, "are_shapes_equ": 90, "area": [225, 230, 472, 535, 539, 551], "arg": [1, 39, 90, 145, 154, 209, 210, 211, 266, 281, 311, 399, 420, 433, 437, 447, 461, 462, 472, 477, 524, 536, 539, 542, 544, 547, 550, 551], "argmax": 16, "argmaxoper": 6, "argpars": 154, "argu": 520, "argument": [140, 154, 195, 281, 396, 406, 413, 431, 438, 441, 442, 477, 480, 481, 547], "ariel": 542, "arithmet": 528, "arm": [492, 531, 532, 553], "around": 90, "arr": [30, 391, 465], "arrai": [3, 30, 31, 133, 140, 225, 230, 396, 465, 551], "arrang": [181, 182, 187, 210, 211, 214, 542], "art": 542, "articl": [231, 232], "arxiv": [169, 187, 420, 439, 472, 476, 487, 492, 519, 539, 542, 543, 547, 550], "as_text": 90, "ascii": [140, 396], "asd932_": 211, "ask": [492, 532], "aspect": [221, 225, 551], "asplo": 543, "assert_error": 90, "assertionerror": [170, 176, 183, 192, 235, 435, 447], "assign": [230, 465, 524, 552], "assist": [159, 548], "associ": [133, 140, 230, 396, 406], "assum": [224, 230, 493, 528], "asterisk": [474, 550], "asym": [29, 30, 31, 142, 145, 413, 429, 433, 495, 528, 547], "asymmetr": [413, 480, 495, 544, 547, 552], "atenc": 482, "atom": 533, "att": [231, 232], "attach": [487, 536, 550], "attack": 488, "attempt": 552, "attent": [16, 143, 171, 173, 184, 195, 209, 417, 488, 542], "attention_ffn_nam": 184, "attention_mask": [209, 536], "attentionoper": 7, "attr": [90, 133, 173, 385], "attr1": 281, "attr2": 281, "attr5": 281, "attribut": [30, 68, 89, 90, 133, 145, 173, 184, 195, 340, 447, 465, 471, 493, 521, 528, 530, 536], "attribute1": 281, "attribute_to_kwarg": 30, "attributeerror": [138, 281, 397], "aug": [492, 543], "augment": 2, "author": 533, "auto": [145, 152, 153, 171, 173, 195, 264, 270, 302, 413, 438, 439, 443, 445, 465, 471, 474, 477, 484, 490, 492, 519, 529, 542, 544, 547], "auto_acceler": 446, "auto_alpha_arg": [303, 439, 550], "auto_clip": 451, "auto_config": 542, "auto_copi": 145, "auto_detect_acceler": 443, "auto_input_output": [133, 385], "auto_merg": 30, "auto_mixed_precis": 270, "auto_scal": 451, "auto_slim": 172, "autoalpha": 413, "autom": [543, 550], "automat": [171, 173, 174, 195, 211, 214, 221, 443, 447, 471, 477, 480, 482, 483, 490, 492, 518, 531, 536, 537, 541, 542, 544, 550, 551, 552], "automixedprecisiontunestrategi": 264, "automodelforcausallm": [141, 398, 529], "automodelforsequenceclassif": 536, "autonumb": [494, 495], "autoround": [428, 437, 439, 477, 487, 492, 534], "autoround_arg": 476, "autoround_quantize_entri": 437, "autoroundconfig": [437, 439, 451, 476], "autoroundquant": 418, "autotoken": 536, "autotrack": [125, 133, 283, 385], "autotun": [478, 479, 480, 487, 500, 520], "autotunestrategi": 263, "aux": 1, "auxiliari": 459, "avail": [154, 188, 195, 239, 413, 445, 473, 476, 477, 483, 492, 496, 498, 504, 507, 510, 520, 525, 527, 529, 531, 542, 552, 553], "averag": [31, 231, 232, 234, 476, 535, 536, 547, 552, 553], "averagepool": 23, "averagepooling2d": 297, "avg": 544, "avgpool": [114, 123, 297, 369, 378, 528], "avoid": [90, 140, 145, 209, 396, 413, 433, 447, 482, 490, 520], "avx": 473, "avx512": [473, 487, 537, 544], "avx512_bf16": [473, 537], "avx512_core_amx_fp16": 473, "avx512_fp16": 473, "aw": [543, 553], "awai": 521, "awar": [31, 135, 162, 195, 269, 439, 448, 476, 477, 481, 493, 494, 495, 519, 523, 524, 526, 531, 541, 543, 547, 552], "awq": [31, 428, 433, 437, 439, 477, 487, 545, 547], "awq_arg": [476, 547], "awq_g32asym": 547, "awq_quant": 31, "awq_quantize_entri": 437, "awqconfig": [437, 439, 451, 476], "awqquant": 419, "ax": [195, 404, 458], "axi": [30, 195, 425, 426], "azur": [489, 492, 543], "b": [30, 59, 154, 209, 331, 418, 465, 476, 487, 489, 519, 535, 542, 547, 550, 552], "b1": [59, 331], "b16": [36, 308], "b_dataload": [151, 195, 518, 536], "b_filter": 1, "b_func": [151, 518], "back": [140, 145, 154, 225, 396], "backbon": 549, "backend": [2, 28, 29, 149, 165, 195, 196, 197, 201, 202, 205, 209, 210, 212, 213, 214, 215, 216, 220, 222, 225, 235, 236, 237, 239, 272, 439, 473, 476, 477, 490, 495, 524, 530, 531, 536, 537, 547, 551, 552], "backward": [448, 487, 523, 524, 536, 541, 542, 544, 548], "badri": 476, "baichuan": 534, "baichuan2": 534, "balanc": [217, 413, 472, 474, 476, 480, 487, 539, 547, 550], "ban": 488, "bandit": 489, "bandwidth": [473, 476, 487, 536, 537, 547], "bar": [30, 211, 543], "bare": [492, 527, 532], "bart": 553, "base": [1, 3, 21, 32, 71, 90, 101, 105, 107, 117, 129, 135, 138, 143, 145, 146, 152, 153, 154, 161, 162, 169, 176, 183, 189, 191, 195, 200, 203, 207, 209, 211, 218, 225, 234, 236, 243, 244, 245, 271, 274, 278, 289, 305, 343, 372, 381, 387, 390, 392, 397, 409, 413, 417, 429, 439, 442, 443, 445, 447, 470, 471, 473, 474, 476, 477, 481, 483, 487, 493, 494, 495, 500, 520, 523, 524, 528, 536, 537, 542, 543, 544, 547, 549, 550, 552, 553], "base_algorithm": 394, "base_config": [153, 155, 299, 301, 302, 303, 305, 438, 439, 442], "base_dir": 30, "base_model": 237, "base_tun": [155, 302, 438, 478, 480], "basecallback": 162, "baseconfig": [152, 153, 156, 299, 301, 302, 305, 438, 439, 442, 477, 480, 520], "basedataload": [200, 204, 206, 387], "basedatalod": [200, 387], "baselin": [454, 481, 549, 550], "baseline_model": [480, 481], "basemetr": [234, 262], "basemodel": [236, 301, 302, 305, 390, 480], "basepattern": [175, 177, 179], "baseprun": [180, 185, 187, 188], "basereg": 189, "basetransform": 225, "basi": 542, "basic": [173, 175, 183, 195, 224, 270, 274, 277, 448, 472, 531, 536, 539, 549], "basicprun": [186, 188], "basictoken": 224, "basictunestrategi": 265, "batch": [1, 145, 200, 202, 203, 207, 208, 387, 418, 448, 476, 521, 523, 536, 541, 542, 544, 550, 551, 552, 553], "batch_idx": 524, "batch_sampl": [200, 202, 205, 206, 208, 387, 521], "batch_siz": [195, 200, 202, 205, 206, 207, 208, 209, 210, 387, 418, 439, 451, 458, 476, 521, 524, 526, 530, 536, 544], "batchmatmul": [113, 368], "batchmatmulv2": [113, 368], "batchnorm": [20, 47, 52, 106, 319, 324, 490, 550], "batchnormalizationoper": 20, "batchsampl": [207, 387], "batchtospacend": [43, 315], "bayesian": [195, 270, 542], "bayesianoptim": 266, "bayesiantunestrategi": 266, "bbox": [230, 490, 535], "bboxes_labels_scor": 490, "beam": [227, 535], "becaus": [140, 179, 184, 225, 396, 479, 487, 490, 544, 550, 551, 552], "becom": [476, 487, 493, 526, 542, 547], "been": [3, 140, 170, 176, 183, 227, 391, 396, 404, 412, 413, 417, 473, 476, 480, 487, 495, 520, 536, 537, 547, 550], "befor": [92, 94, 149, 175, 180, 182, 187, 188, 190, 195, 209, 288, 357, 359, 420, 431, 441, 445, 471, 476, 487, 489, 495, 521, 523, 524, 527, 528, 536, 544, 547, 549, 552], "begin": [101, 181, 182, 187, 475, 520, 521, 523, 536, 542, 552], "behavior": [140, 396, 488, 493, 494, 495, 528, 538, 547, 552], "being": [135, 230, 495], "beit": 553, "belong": [211, 239, 544], "below": [40, 51, 59, 154, 195, 234, 262, 312, 323, 331, 469, 471, 472, 474, 476, 477, 480, 481, 487, 489, 490, 492, 493, 494, 495, 521, 524, 529, 530, 535, 539, 540, 541, 542, 544, 547, 549, 550, 552], "benchmark": [155, 195, 226, 245, 465, 469, 492, 499, 500, 529, 538, 552, 553], "benchmark_with_raw_cmd": 151, "benchmarkconf": 536, "benchmarkconfig": [151, 195, 518, 536], "benefici": 519, "benefit": [529, 541], "bert": [173, 195, 205, 208, 209, 225, 492, 535, 537, 542, 551, 553], "bert_dataset": 215, "bertattent": 173, "besid": [476, 487, 493, 547], "best": [162, 225, 271, 433, 476, 477, 478, 479, 481, 488, 520, 532, 540, 544, 547, 550, 551, 552], "best_clip_ratio": 433, "best_configur": 464, "best_model": [162, 464, 473, 478, 479, 480, 481, 547], "best_model_weight": 464, "best_scor": 162, "beta": [169, 425], "better": [81, 195, 198, 199, 235, 262, 352, 448, 473, 476, 487, 520, 523, 535, 537, 542, 543, 544, 547, 549, 550, 552], "between": [3, 29, 128, 150, 186, 195, 225, 231, 234, 257, 261, 380, 406, 413, 465, 471, 472, 476, 477, 480, 487, 490, 492, 493, 494, 495, 519, 531, 535, 536, 539, 544, 547, 548, 549, 550, 551, 552], "bf16": [31, 72, 134, 195, 278, 344, 399, 401, 406, 439, 471, 480, 493, 494, 528, 536, 546, 552, 553], "bf16_convert": [37, 136, 309], "bf16_op": [33, 35, 92, 306, 307, 357, 494, 546], "bf16convert": [35, 307, 546], "bf16modul": 134, "bf16modulewrapp": 134, "bf16wrapper": 546, "bfloat16": [30, 429, 439, 473, 492, 537, 546], "bfloat16fp16": 471, "bi": [231, 232], "bia": [128, 195, 380, 403, 423, 429, 547], "bias_constraint": [292, 293, 294, 298], "bias_correct": [130, 382], "bias_initi": [292, 293, 294, 298], "bias_regular": [292, 293, 294, 298], "biasadd": [38, 44, 49, 51, 94, 310, 316, 321, 323, 359, 528], "biascorrect": [128, 380], "bibtex": 533, "bicub": [225, 551], "big": [135, 476, 547], "bigscienc": [474, 534, 550, 553], "bilibili": 543, "bilinear": [221, 225, 551], "bilinearimagenet": 551, "bilinearimagenettransform": 221, "bilingu": 227, "billion": 542, "bilstm": 553, "bin": [3, 140, 141, 391, 396, 398, 465, 527], "binari": [8, 133, 234, 385, 527, 535, 548], "binary_op": 16, "binarydirect8bitoper": 8, "binaryoper": 8, "bind": [151, 483], "bio": 553, "bit": [29, 31, 145, 195, 280, 413, 421, 426, 429, 433, 439, 451, 470, 471, 472, 473, 476, 477, 487, 495, 519, 523, 537, 539, 543, 544, 547, 550], "bita": [472, 539], "bitnami": 543, "bitpack": 424, "bitwidth": 470, "bk3": 3, "black": 552, "black_nod": 2, "blendcnn": 553, "bleu": [228, 233, 535, 542], "bleu_hook": 228, "bleu_scor": 228, "bleu_token": 227, "bleu_util": 233, "blob": [3, 135, 177, 178, 227, 228, 231, 232, 234, 262, 536], "blob_siz": 31, "block": [31, 143, 145, 169, 179, 182, 187, 192, 245, 281, 417, 433, 472, 476, 531, 539, 540, 542, 547, 552], "block_list": [145, 433], "block_mask": [169, 183], "block_num": [145, 433], "block_pattern": [143, 417], "block_prefix": [145, 433], "block_siz": [179, 404, 439, 476, 547], "blockfallbacktuningsampl": 277, "blocklist": [439, 471], "blockmaskcriterion": 169, "blocksiz": [31, 439, 451, 472, 539], "blockwis": 550, "blockwise_over_matmul_gemm_conv": 192, "blog": [439, 492, 543], "bloom": [474, 487, 492, 534, 542, 550, 553], "bloomz": [474, 550, 553], "blue": [476, 545], "bmm": [471, 476, 487, 547], "bn": 553, "bnb": [476, 547], "bnb_nf4": [439, 447], "bo": 195, "bodi": 488, "bool": [1, 29, 30, 31, 126, 133, 140, 144, 145, 153, 161, 175, 195, 209, 211, 221, 225, 228, 234, 277, 281, 286, 299, 303, 385, 396, 398, 406, 409, 412, 413, 418, 420, 423, 425, 426, 427, 431, 433, 439, 442, 445, 451, 458, 461, 464, 465, 476, 477, 521, 535, 551], "bool_val": 90, "boolean": [1, 409], "boost": [473, 492, 537, 542, 543], "booster": 523, "border": 551, "both": [133, 195, 385, 443, 475, 476, 478, 483, 487, 488, 493, 523, 536, 542, 544, 547, 550, 552], "bottleneck": [476, 487, 547], "boudoukh": 542, "bound": [59, 151, 225, 230, 266, 331, 413, 535, 551], "boundari": [225, 551], "bowl": 232, "box": [225, 230, 234, 490, 535, 551, 552], "branch": [133, 385, 489], "brand": 533, "break": [94, 359, 524, 536], "breakthrough": [472, 539], "breviti": [227, 228, 535], "bridg": [493, 494, 531], "briefli": [487, 536, 550], "bright": 551, "bring": [487, 550], "broad": [469, 492, 531], "broadcast": [225, 524, 551], "broadcast_optimizer_st": 524, "broadcast_paramet": 524, "bronco": 232, "brought": [487, 538, 544], "buffer": [140, 396, 451], "bug": [489, 492], "build": [1, 29, 31, 100, 146, 147, 149, 150, 154, 238, 240, 242, 243, 244, 390, 413, 480, 493, 494, 495, 532, 538, 543, 552], "build_captured_dataload": 413, "build_slave_faker_model": 280, "build_torch_model": 473, "built": [60, 165, 184, 196, 197, 201, 205, 209, 210, 215, 217, 219, 220, 221, 222, 225, 234, 237, 245, 262, 301, 305, 332, 448, 480, 481, 493, 524, 536, 540, 544, 549, 551, 552], "builtin": [140, 396, 524], "busi": 543, "button": [489, 531], "bypass_reshap": [52, 53, 324, 325], "byte": [140, 396, 413], "byte_arrai": [140, 396], "bytes_or_buff": 451, "bytesio": [140, 396], "c": [3, 59, 154, 211, 331, 465, 476, 482, 487, 527, 547, 552], "c1": [59, 331], "c1c2": [59, 331], "c2": [59, 331], "c6a": 553, "c6g": 553, "c6i": 553, "c_": [476, 547], "c_out": 476, "cach": [209, 476, 487, 492, 527, 544, 547], "cache_dir": [141, 398, 447], "cache_kl": 1, "cache_minmax": 1, "caffenet": 553, "cal_scal": 413, "calcul": [30, 45, 145, 153, 169, 177, 192, 195, 212, 213, 231, 232, 271, 317, 387, 413, 425, 452, 465, 471, 474, 476, 480, 487, 519, 535, 536, 540, 542, 544, 547, 549, 550, 552], "calculate_md5": 211, "calculate_ms": 465, "calculate_quant_min_max": 145, "calculate_scale_zp": 30, "calib": [145, 292, 293, 294, 297, 298, 494], "calib_cfg": 1, "calib_data": [1, 139], "calib_dataload": [262, 284, 301, 302, 305, 478, 479, 480, 481, 490, 521, 530, 535, 536, 544, 545, 546, 547], "calib_func": [33, 145, 262, 284, 301, 302, 305, 306, 433, 471, 480, 492, 546], "calib_iter": [284, 288, 301, 302, 305, 480, 494], "calib_method": 3, "calib_model": 1, "calib_num": 413, "calib_registri": 3, "calib_tensor": 1, "calibcollector": 1, "calibdata": 1, "calibr": [1, 4, 31, 34, 74, 75, 125, 145, 151, 195, 198, 199, 262, 285, 301, 305, 346, 412, 413, 418, 438, 442, 460, 469, 471, 475, 476, 477, 480, 487, 492, 493, 495, 530, 531, 542, 544, 547, 552], "calibration_data": [84, 92, 357], "calibration_sampling_s": [195, 536], "calibratorbas": 3, "call": [1, 29, 140, 146, 161, 173, 181, 182, 187, 230, 396, 413, 445, 480, 483, 487, 490, 493, 521, 530, 542, 544, 550, 551], "call_count": 161, "call_on": 151, "callabl": [140, 153, 195, 232, 284, 301, 302, 305, 396, 412, 437, 438, 439, 442, 443, 447, 448, 477, 480, 520, 521], "callback": [448, 454, 490, 536, 541, 542, 544], "callbacks_list": 448, "camembert": 553, "can": [29, 30, 31, 128, 135, 140, 150, 173, 174, 175, 180, 188, 190, 195, 198, 199, 208, 211, 225, 230, 232, 234, 235, 245, 262, 380, 396, 413, 442, 448, 465, 471, 472, 473, 474, 475, 476, 477, 478, 479, 480, 481, 483, 487, 490, 492, 493, 494, 495, 518, 520, 521, 523, 524, 526, 528, 531, 532, 534, 535, 536, 537, 538, 539, 540, 541, 542, 544, 545, 546, 547, 549, 550, 551, 552, 553], "candid": 406, "cannot": [230, 476, 490, 520, 527, 547], "cap": 492, "cap_s8_1_11": 495, "cap_s8_1_11_conv1d": 495, "capabl": [1, 32, 278, 289, 471, 473, 476, 487, 494, 495, 518, 528, 536, 537, 542, 544, 552], "capac": [476, 487, 547, 549], "captur": [391, 413, 465, 475, 476], "captureddataload": 413, "captureoutputtofil": [391, 465], "card": [476, 542], "carri": [412, 413, 542], "cascad": 532, "case": [30, 55, 59, 140, 151, 154, 195, 208, 224, 225, 245, 327, 331, 396, 441, 443, 469, 476, 477, 480, 487, 495, 520, 521, 523, 524, 528, 530, 535, 540, 542, 543, 544, 547, 548, 550, 551, 553], "cast": [30, 36, 308, 546, 551], "cast_tensor": 30, "castonnxtransform": 225, "castpytorchtransform": 225, "casttftransform": 225, "cat": [490, 526], "categor": 535, "categori": [211, 229, 518], "category_id_set": 230, "caus": [192, 476, 487, 494, 521, 542, 547], "causal": [431, 441, 542], "cce5ff": 552, "cd": [524, 532], "cdot": [487, 550], "ce": [163, 195, 536], "center": [225, 491, 492, 532, 551, 552], "centercrop": 551, "centercroptftransform": 225, "centercroptransform": 225, "cento": [532, 553], "central_fract": [221, 551], "cern": 543, "certain": [140, 194, 396, 481, 549], "certif": 489, "cfg": [56, 57, 145, 278, 328, 329, 412, 413, 417, 454, 494, 495], "cfg_filter": 454, "cfg_from_fil": 465, "cfg_preprocess": 454, "cfg_to_qconfig": [413, 417], "challeng": [472, 476, 539, 545], "chang": [29, 81, 128, 150, 181, 182, 184, 185, 187, 190, 195, 269, 352, 380, 413, 442, 465, 477, 489, 494, 521, 524, 527, 533, 536, 542, 551, 552], "channel": [29, 30, 31, 128, 149, 150, 171, 174, 179, 195, 221, 225, 380, 413, 433, 461, 471, 472, 474, 476, 492, 493, 495, 531, 532, 539, 542, 547, 551, 553], "channel_axi": [98, 147, 150], "channels_last": 221, "channelx1": [195, 542], "chapter": 494, "characterist": 488, "chart": [487, 544, 549], "chat": [474, 483, 534, 550, 553], "chatbot": [472, 539, 543], "chatglm2": 534, "chatglm3": 534, "check": [1, 31, 52, 53, 90, 133, 145, 192, 201, 211, 324, 325, 385, 391, 406, 413, 417, 427, 442, 445, 456, 464, 465, 480, 482, 492, 524, 532, 548], "check_cfg_and_qconfig": [145, 413, 417], "check_config": 192, "check_dataload": 201, "check_integr": 211, "check_key_exist": 465, "check_key_valid": 192, "check_model": 456, "check_mx_vers": 1, "checknumer": [65, 337], "checkout": 489, "checkpoint": [140, 243, 390, 396, 431, 441, 464, 538], "checkpoint_dir": [431, 441, 464], "checkpoint_sess": [243, 390], "checksum": 211, "chees": 520, "cheeseshopaddress": 520, "chen": 533, "cheng": [476, 487], "child": [59, 141, 331, 398, 420], "children": [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 19, 21, 22, 23, 25, 26, 141, 398], "chines": 543, "choic": [209, 476, 480, 487, 493, 535, 550], "choos": [211, 433, 461, 477, 487, 531, 543, 548, 550, 552], "chosen": [471, 494, 519], "chunk": [225, 551], "chunk_siz": 211, "ci": 489, "cifar": [211, 553], "cifar10": 211, "cifar100": 211, "circumst": 488, "ckpt": [133, 235, 243, 262, 385, 390, 553], "cl": [141, 146, 161, 163, 165, 175, 180, 188, 189, 190, 211, 218, 225, 234, 245, 274, 391, 398, 447, 465, 520], "claim": 533, "clamp_": [487, 550], "clarifi": 488, "class": [101, 138, 145, 170, 176, 183, 215, 235, 262, 285, 287, 291, 305, 397, 400, 447, 476, 477, 478, 480, 481, 490, 494, 520, 521, 535, 536, 540, 541, 544, 548, 552], "class_1": 211, "class_n": 211, "classdef": 552, "classic": [477, 552], "classif": [188, 209, 225, 234, 526, 535, 542, 543], "classifi": [173, 192, 209, 234], "classificationmnli": 553, "classificationmrpc": 553, "classificationqnli": 553, "classificationqqp": 553, "classificationsst": 553, "classifierheadsearch": 173, "classifierheadsearchertf": 173, "classregist": 280, "clean": [224, 398, 536], "clean_module_weight": 398, "clean_weight": 398, "clear": [207, 493, 528, 535, 536], "click": [492, 531, 532, 543], "client": [161, 492], "clip": [31, 413, 433, 476, 487, 547, 550], "clip_grad_norm_": 536, "clm": 542, "clone": [489, 532], "close": [128, 150, 380, 519], "cloud": [472, 489, 492, 539, 543], "cluster": 552, "cmd": [151, 532], "cnn": 553, "cnt": 536, "co": 542, "coarsest": [487, 550], "coco": [210, 217, 230, 234, 535, 542], "coco_dataset": 215, "coco_filt": 219, "coco_label_map": 233, "coco_tool": 233, "cocoev": 230, "cocoevalwrapp": 230, "cocomap": 535, "cocomapv2": [234, 535], "coconpi": 210, "cocoraw": 210, "cocorecorddataset": 210, "cocowrapp": 230, "code": [140, 173, 198, 199, 262, 396, 439, 448, 469, 473, 476, 478, 490, 492, 493, 494, 495, 523, 524, 530, 531, 533, 535, 540, 541, 542, 543, 544, 549, 550, 551], "codec": [140, 396], "codenam": [473, 534, 537], "coder": [531, 543], "coeff": 189, "coeffici": [40, 189, 312, 542], "cola": [209, 535, 553], "collabor": [489, 492], "collat": [133, 145, 385], "collate_fn": [200, 202, 203, 205, 206, 208, 387, 521], "collate_pr": 30, "collate_result": 145, "collate_tf_pr": [133, 385], "collate_torch_pr": 145, "collctor": 3, "collect": [1, 3, 30, 145, 153, 154, 223, 225, 232, 234, 391, 403, 412, 413, 416, 419, 421, 430, 452, 465, 480, 487, 494, 544, 552], "collect_layer_histogram": 459, "collect_layer_input": 192, "collect_weight_info": 145, "collector": [1, 135, 452], "collectorbas": 1, "collecttransform": 225, "color": [476, 542, 545], "colorjitt": 551, "column": [465, 476, 487, 547, 550], "column_map": 465, "columnwis": [50, 322], "com": [3, 135, 177, 178, 188, 209, 227, 228, 231, 232, 234, 262, 439, 488, 520, 532, 533, 536, 548, 549, 553], "comb": 523, "combin": [1, 145, 195, 198, 199, 221, 235, 262, 391, 417, 448, 465, 476, 479, 490, 492, 493, 531, 536, 541, 543, 544, 546, 547, 551, 552], "combine_cap": 1, "combine_histogram": [391, 465], "come": [140, 396, 472, 534, 539, 552], "comma": 418, "command": [151, 154, 448, 482, 483, 524], "command_prefix": 154, "comment": [138, 397, 476, 482, 488, 494, 535, 536, 547, 551], "commentsbalancedor": 553, "commit": [477, 480, 488, 489], "common": [124, 138, 140, 195, 223, 226, 299, 301, 302, 303, 305, 379, 396, 397, 437, 438, 439, 442, 447, 454, 474, 478, 479, 480, 488, 520, 523, 524, 526, 529, 530, 532, 536, 544, 550], "commonli": 542, "commun": 488, "comoress": 461, "compact": [536, 542], "compar": [135, 234, 465, 472, 475, 476, 481, 487, 523, 535, 539, 542, 544, 547, 549, 552], "compare_kei": 465, "compare_label": [234, 262, 535], "compare_object": 465, "compare_weight": 135, "comparison": [465, 547, 548], "compat": [133, 243, 385, 390, 489, 524, 538, 542, 548], "compatible_format": [138, 397], "compil": [227, 470, 475, 536], "complaint": 488, "complement": [473, 542], "complet": [278, 471, 493, 494, 542, 544, 552, 553], "complex": [156, 473, 520, 536, 537, 542], "complex_attr": 156, "complextfmap": 520, "compli": 552, "compon": [162, 284, 481, 490, 520, 524, 532, 533, 541, 542], "compos": [152, 225, 454, 551], "composableconfig": [152, 520], "composetransform": 225, "comprehens": [469, 477, 480, 536], "compress": [226, 245, 420, 439, 448, 461, 467, 469, 471, 474, 476, 477, 479, 481, 487, 492, 499, 529, 531, 536, 540, 541, 542, 543, 544, 550, 553], "compressed_model": 547, "compression_dim": [429, 461, 547], "compression_dtyp": [429, 461, 547], "compression_manag": [195, 448, 490, 523, 536, 541, 542, 544], "compressionmanag": 448, "compressor": [1, 151, 154, 162, 165, 177, 178, 188, 195, 221, 222, 225, 226, 233, 234, 235, 239, 246, 262, 270, 276, 290, 302, 303, 304, 305, 389, 392, 394, 436, 437, 438, 439, 440, 441, 442, 444, 445, 446, 447, 449, 451, 455, 467, 469, 471, 472, 473, 474, 475, 476, 477, 478, 480, 481, 482, 484, 487, 489, 493, 494, 495, 518, 519, 520, 522, 523, 524, 525, 526, 527, 528, 529, 530, 533, 534, 537, 538, 539, 540, 541, 542, 543, 544, 547, 548, 550, 551, 552, 553], "comput": [30, 31, 90, 135, 145, 227, 228, 231, 232, 234, 413, 417, 425, 448, 465, 471, 472, 473, 475, 476, 487, 519, 521, 523, 526, 535, 536, 537, 539, 542, 543, 544, 547, 550, 552], "compute_bleu": 228, "compute_const_folding_using_tf": 90, "compute_dtyp": 451, "compute_error": 135, "compute_spars": 465, "computemetr": 230, "concat": [16, 132, 384], "concat_gener": 225, "concaten": 413, "concatoper": 9, "concatv2": [109, 119, 132, 364, 374, 384, 528], "concept": [469, 530, 549], "concret": [133, 385, 390, 552], "conda": [527, 548], "condit": [70, 153, 209, 210, 211, 225, 263, 265, 342, 481, 533, 551, 552], "conduct": [469, 490, 536, 552], "conf": [146, 151, 162, 195, 198, 199, 235, 245, 262, 263, 264, 266, 267, 271, 273, 274, 278, 281, 448, 490, 495, 518, 530, 536, 537, 538, 541, 544, 545, 546, 547, 549, 550, 552], "confer": [135, 487, 542, 550], "confid": 145, "confidence_batch": [145, 552], "confidenti": 488, "config": [1, 31, 100, 101, 103, 107, 145, 151, 152, 153, 156, 160, 161, 169, 170, 171, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 198, 199, 209, 226, 235, 257, 261, 278, 279, 280, 281, 284, 288, 289, 300, 301, 302, 304, 305, 389, 406, 409, 412, 413, 417, 424, 427, 431, 438, 440, 442, 447, 448, 451, 454, 464, 465, 470, 471, 473, 475, 476, 477, 478, 494, 495, 499, 500, 518, 520, 521, 523, 524, 526, 531, 535, 536, 537, 538, 541, 542, 544, 546, 547, 549, 552], "config1": 153, "config2": 153, "config_file_path": 188, "config_inst": 151, "config_list": [152, 153], "config_map": [160, 427], "config_name_map": 160, "config_quantizable_lay": 103, "config_set": [153, 473, 478, 479, 480, 481], "config_sourc": 153, "configload": 153, "configmappingtyp": 427, "configproto": 261, "configregistri": [152, 160], "configs_map": [305, 399, 437, 442], "configset": 153, "configur": [1, 103, 134, 145, 151, 152, 153, 154, 161, 192, 195, 198, 199, 201, 211, 214, 234, 235, 245, 262, 271, 280, 301, 305, 406, 408, 409, 411, 413, 417, 422, 427, 437, 439, 442, 447, 448, 453, 454, 458, 463, 464, 477, 481, 483, 490, 493, 494, 536, 540, 542, 544, 547, 548, 550, 551, 552, 553], "confirm": 494, "conflict": [90, 520, 527], "connect": [169, 542, 549], "consecut": [171, 173, 174, 542], "conserv": [195, 270], "conservativetunestrategi": 267, "consid": [31, 133, 234, 385, 488, 519, 520, 552], "consider": [479, 550], "consist": [41, 48, 313, 320, 476, 489, 490, 520, 550, 552], "consolid": 532, "const": [41, 42, 48, 49, 52, 53, 55, 67, 83, 313, 314, 320, 321, 324, 325, 327, 339, 354], "const_node_valu": 90, "constant": [90, 158, 266, 276, 388, 446, 458, 459, 520, 521, 528, 551], "constant_valu": 225, "constfold": 528, "constrain": 545, "constraint": [195, 536, 542, 549, 552], "construct": [140, 209, 212, 213, 216, 223, 234, 239, 243, 280, 387, 389, 390, 396, 454, 481, 488, 494, 495, 524, 542, 552], "construct_function_from_graph_def": [133, 385], "consum": [481, 521], "consumpt": [472, 476, 487, 539, 550], "contact": [488, 548, 549], "contain": [1, 52, 53, 55, 59, 124, 133, 135, 140, 145, 151, 162, 170, 173, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 190, 192, 195, 198, 199, 209, 210, 211, 230, 231, 232, 235, 262, 324, 325, 327, 331, 379, 385, 396, 406, 409, 412, 413, 417, 425, 429, 448, 454, 458, 464, 469, 476, 480, 492, 519, 527, 531, 535, 542, 547, 552], "content_fold": 216, "context": [1, 465, 476, 487, 547], "contextu": 542, "contigu": 145, "continu": [178, 230, 476, 534, 536, 542], "contract": [43, 315], "contrast": [175, 551], "contrib": [3, 226], "contribut": [488, 492, 542], "control": [146, 195, 490, 536, 542, 552], "conv": [16, 43, 47, 51, 56, 57, 58, 77, 94, 149, 195, 315, 319, 323, 328, 329, 330, 348, 359, 490, 494, 495, 536, 542, 544, 552], "conv1": [195, 478, 544], "conv1d": [194, 477, 495], "conv1d_relu": 526, "conv2d": [38, 44, 45, 46, 50, 51, 56, 110, 120, 128, 294, 295, 298, 303, 310, 316, 317, 318, 322, 323, 328, 365, 375, 380, 413, 471, 494, 495, 526, 528, 550, 552], "conv2d_config": 478, "conv2d_relu": 526, "conv2dbackpropinput": [111, 366], "conv3d": [56, 110, 328, 365], "conv3dbackpropinputv2": [111, 366], "conveni": [477, 536], "convent": [211, 230, 472, 489, 539], "convers": [39, 40, 195, 311, 312, 406, 473, 474, 487, 489, 493, 494, 536, 537, 544, 546, 550], "convert": [1, 30, 33, 34, 35, 38, 39, 40, 41, 42, 51, 59, 71, 84, 85, 87, 88, 89, 90, 116, 121, 125, 127, 134, 145, 173, 195, 209, 221, 224, 225, 230, 278, 281, 283, 288, 289, 306, 307, 310, 311, 312, 313, 314, 323, 331, 343, 355, 371, 376, 392, 399, 406, 437, 442, 447, 449, 457, 470, 471, 472, 473, 474, 475, 476, 477, 479, 480, 483, 487, 490, 492, 494, 529, 536, 537, 544, 546, 547, 550, 551, 552], "convert_add_to_biasadd": [61, 333], "convert_bf16": 494, "convert_by_vocab": 224, "convert_examples_to_featur": [209, 225], "convert_layout": [61, 333], "convert_leakyrelu": [61, 333], "convert_nan_to_random": [61, 333], "convert_placeholder_to_const": [61, 333], "convert_tensorflow_tensor_to_onnx": 90, "convert_to_unicod": 224, "convertaddtobiasaddoptim": [38, 310], "converted_model": [195, 235, 536, 537], "convertlayoutoptim": [39, 311], "convertleakyreluoptim": [40, 312], "convertnantorandom": [41, 313], "convertplaceholdertoconst": [42, 314], "convolut": 543, "convoper": 10, "cooper": [473, 532, 537, 543], "coordin": [225, 266, 551, 552], "copi": [195, 465, 521], "copyreg": [138, 397], "copyright": [489, 533], "core": [151, 154, 195, 285, 407, 424, 476, 482, 483, 489, 492, 518, 532, 533, 553], "core_id": 151, "core_list": [151, 154], "core_list_per_inst": 154, "cores_per_inst": [151, 195, 518, 536], "corner": [225, 489, 493, 495, 551], "corpor": 533, "correct": [128, 150, 192, 195, 230, 231, 232, 234, 380, 488], "correspond": [3, 135, 173, 184, 195, 209, 227, 230, 234, 412, 413, 417, 427, 454, 465, 471, 477, 487, 493, 528, 536, 542, 544, 549, 552], "cost": [471, 472, 476, 487, 539, 544, 547], "could": [140, 149, 175, 198, 199, 211, 235, 262, 396, 413, 448, 469, 473, 475, 476, 478, 480, 487, 488, 490, 523, 527, 536, 541, 542, 544, 547, 550], "count": [1, 476, 487, 547], "counter": 90, "coupl": 208, "cover": [489, 526, 530, 543], "coverag": 489, "cowork": [431, 441], "cpu": [76, 77, 78, 79, 139, 140, 145, 154, 161, 195, 347, 348, 349, 350, 391, 396, 398, 401, 413, 420, 429, 431, 433, 441, 443, 461, 465, 473, 475, 477, 480, 482, 494, 518, 519, 531, 536, 537, 543, 544, 545, 546, 547], "cpu_acceler": 443, "cpu_execution_tim": 251, "cpu_index": 154, "cpu_rang": 154, "cpuexecutionprovid": [2, 28, 29, 31, 537, 544], "cpufreq": 520, "cpuinfo": [161, 391, 465], "craft": [472, 539], "crbug": 520, "creat": [1, 3, 90, 138, 156, 195, 200, 209, 211, 230, 257, 261, 278, 280, 281, 387, 397, 406, 409, 451, 454, 469, 471, 487, 488, 493, 538, 542, 544, 549, 552], "create_data_exampl": 1, "create_dataload": 454, "create_dataset": 454, "create_eval_func": 454, "create_obj_from_config": 459, "create_onnx_config": 257, "create_quant_spec_from_config": 409, "create_tf_config": 261, "create_train_func": 454, "create_xiq_quantizer_from_pt2e_config": 409, "criteria": [170, 195, 481, 490, 550], "criterion": [135, 162, 164, 165, 169, 175, 180, 181, 182, 184, 187, 191, 195, 523, 536, 542, 544, 550, 552], "criterion_class": [169, 191], "criterion_conf": 195, "criterion_registri": 163, "criterion_typ": 163, "critet": 163, "critic": [184, 420, 480, 488], "crop": [221, 225, 551], "crop_pad": 225, "crop_ratio": 216, "cropres": 551, "cropresizetftransform": 225, "cropresizetransform": 225, "croptoboundingbox": [225, 551], "cross": [165, 234, 482, 530, 552], "cross_memori": 482, "crossentropyloss": [163, 195, 536], "crowd": 230, "crucial": [475, 542], "cs412": 3, "cse": [59, 83, 331, 354], "csv": 465, "ctx": 1, "cube": [195, 542], "cuda": [140, 192, 396, 413, 425, 443, 477, 537, 542, 544], "cuda_acceler": 443, "cudaexecutionprovid": [537, 544], "current": [1, 55, 89, 154, 169, 170, 173, 176, 180, 183, 195, 266, 272, 327, 413, 433, 441, 447, 465, 475, 476, 477, 481, 490, 492, 493, 495, 519, 520, 524, 528, 529, 536, 540, 542, 544, 547, 550, 552], "current_pattern": 173, "current_sparsity_ratio": 180, "curv": 535, "custom": [100, 138, 145, 151, 234, 245, 292, 293, 294, 295, 297, 298, 397, 433, 464, 471, 477, 481, 487, 492, 518, 523, 542, 543, 547, 549], "custom_metr": 530, "custom_tune_config": [473, 478, 479, 480, 481], "customis": [521, 535], "customized_msg": [161, 391, 465], "cv": [195, 471, 475, 477, 480, 542], "cv2": 221, "cvf": [487, 550], "d": [59, 145, 331, 417, 530, 542], "d1": [59, 331, 465], "d2": 465, "d_": 195, "d_conf": [195, 523, 536, 541], "dai": 552, "damp_perc": 451, "dampen": 31, "darvish": [472, 539], "data": [1, 29, 30, 31, 41, 90, 125, 133, 135, 140, 145, 149, 161, 173, 195, 198, 199, 226, 235, 256, 260, 262, 266, 278, 280, 283, 301, 305, 313, 385, 388, 391, 396, 403, 404, 409, 413, 418, 433, 448, 451, 454, 458, 465, 469, 470, 471, 472, 473, 475, 476, 477, 480, 487, 492, 493, 519, 521, 524, 528, 532, 535, 536, 537, 539, 544, 546, 547, 548, 549, 550, 551, 552], "data_dir": 209, "data_format": [211, 221, 292, 294, 297, 298], "data_it": [1, 173], "data_load": [33, 34, 306, 493], "data_path": 214, "data_sourc": [207, 454], "data_typ": [280, 418], "data_x": 1, "databas": 211, "databrick": [474, 534, 550, 553], "datafunc": 211, "dataiterload": 1, "dataload": [1, 2, 29, 31, 125, 126, 135, 145, 151, 170, 171, 173, 188, 192, 198, 199, 209, 220, 256, 260, 262, 283, 286, 387, 413, 418, 420, 433, 448, 454, 469, 480, 490, 493, 494, 523, 524, 530, 536, 537, 541, 542, 544, 545, 546, 547, 550, 551], "dataloader_cfg": 454, "dataloaderwrap": 1, "datalod": 413, "dataset": [125, 126, 145, 188, 198, 199, 200, 202, 203, 205, 206, 207, 208, 220, 230, 231, 232, 234, 235, 262, 283, 286, 387, 418, 448, 451, 454, 474, 476, 478, 479, 480, 487, 493, 494, 521, 524, 535, 536, 542, 544, 547, 548, 550, 552, 553], "dataset_format": 211, "dataset_nam": 418, "dataset_registri": 211, "dataset_typ": 211, "datatyp": [90, 145, 546, 552, 553], "date": [476, 547], "datetim": 195, "dbox": 490, "dco": 489, "ddr5": 553, "deal": 448, "debug": [281, 462, 552], "debug_stripp": 528, "dec": 543, "decapoda": 553, "decid": [101, 195, 228, 480, 482, 493, 494, 536, 544, 548, 552], "decim": 465, "decis": [520, 535], "declar": 520, "decod": [140, 221, 227, 396, 451, 535, 551], "decode_singl": 490, "decodeimag": 551, "decompos": [52, 53, 324, 325], "decor": [3, 21, 52, 53, 55, 133, 146, 152, 161, 165, 175, 180, 188, 190, 225, 234, 245, 274, 324, 325, 327, 391, 413, 445, 447, 465, 490, 493, 552], "decorator_metr": 234, "decreas": [83, 354, 542], "dedic": 195, "dedicated_qdq_pair": [28, 195, 544], "deem": 488, "deep": [391, 465, 469, 472, 473, 477, 480, 487, 492, 493, 494, 521, 531, 532, 536, 537, 539, 543, 544, 552], "deep_get": [245, 391, 465], "deep_set": [245, 465], "deepcopi": 195, "deepen": 543, "deepst": 195, "def": [52, 53, 55, 153, 198, 199, 262, 281, 324, 325, 327, 391, 447, 448, 473, 474, 477, 478, 480, 481, 487, 490, 493, 520, 521, 523, 524, 535, 536, 544, 550, 552], "default": [3, 31, 82, 133, 140, 145, 152, 156, 161, 192, 195, 198, 199, 202, 209, 210, 211, 221, 225, 227, 234, 243, 280, 299, 303, 353, 385, 390, 391, 396, 398, 408, 409, 412, 413, 418, 425, 431, 433, 435, 437, 438, 439, 441, 442, 447, 451, 454, 457, 458, 461, 465, 471, 472, 473, 474, 476, 477, 480, 481, 482, 483, 490, 493, 520, 521, 528, 531, 535, 536, 537, 539, 540, 542, 544, 546, 547, 549, 550, 551, 552], "default_alpha": 550, "default_col": [202, 387], "default_config": 192, "default_dtyp": 278, "default_opset_vers": 127, "default_sampl": [153, 481], "default_sq_alpha_arg": 303, "default_v": 156, "default_white_list": [152, 299, 303, 439], "default_workspac": 195, "defaultdataload": [202, 208], "defin": [71, 135, 156, 173, 175, 180, 181, 182, 187, 188, 189, 190, 195, 198, 199, 235, 262, 343, 448, 451, 464, 471, 478, 480, 481, 487, 488, 492, 493, 494, 521, 523, 528, 531, 535, 536, 541, 542, 544, 547, 549, 550, 552], "definit": [133, 142, 203, 207, 385, 429], "defult": [431, 441], "degrad": [523, 542, 552], "delet": 542, "delete_assign": 261, "deliv": [473, 476, 536, 543, 548], "demand": [476, 487, 547], "demo": [154, 477, 536], "democrat": 543, "demonstr": [472, 476, 481, 483, 492, 525, 539], "denot": [487, 550], "dens": [173, 190, 195, 295, 542, 553], "dense_shap": 213, "densenet": 553, "densiti": 552, "denver": 232, "depend": [1, 198, 199, 235, 262, 448, 489, 492, 527, 528, 532, 544, 552], "deploi": [476, 481, 487, 489, 536, 547, 552], "deploy": [477, 522, 543, 545, 550], "deprec": [153, 520, 548, 551], "depth": [145, 417, 546], "depth_multipli": [294, 298], "depthwis": [294, 413], "depthwise_constraint": [294, 298], "depthwise_conv2d": 295, "depthwise_initi": [294, 298], "depthwise_regular": [294, 298], "depthwiseconv2d": 294, "depthwiseconv2dn": [50, 56, 110, 120, 322, 328, 365, 375, 528], "dequant": [29, 30, 31, 36, 73, 76, 77, 78, 79, 81, 135, 145, 308, 345, 347, 348, 349, 350, 352, 398, 413, 423, 429, 433, 465, 487, 490, 494, 550], "dequantize_cast_optim": [37, 309], "dequantize_data": 30, "dequantize_data_with_scale_zero": 30, "dequantize_per_channel": [487, 550], "dequantize_tensor": 465, "dequantize_weight": 465, "dequantizecastoptim": [36, 308], "dequantizelinear": 30, "deriv": [162, 169, 177, 178, 179, 185, 186, 187, 188, 189, 190, 191], "derogatori": 488, "desc": 536, "desc_act": 451, "descent": [173, 439, 476, 487, 492, 543], "describ": [493, 495, 520, 528], "descript": [1, 117, 281, 372, 471, 474, 490, 494, 495, 521, 550], "deseri": [140, 396], "design": [162, 208, 234, 267, 469, 475, 477, 480, 492, 536, 542, 544], "desir": [195, 221, 225, 409, 474, 494, 495, 542, 550, 551], "despit": 481, "dest": 90, "destin": [133, 385, 456], "detach": [487, 550], "detail": [29, 149, 152, 173, 225, 413, 439, 465, 466, 469, 473, 474, 476, 477, 478, 479, 480, 487, 488, 492, 494, 495, 519, 520, 528, 530, 534, 535, 536, 537, 542, 547, 548, 549, 550, 552], "detect": [143, 145, 161, 173, 195, 230, 234, 239, 417, 443, 447, 477, 489, 490, 542, 552], "detect_processor_type_based_on_hw": 161, "detection_box": [230, 536], "detection_boxes_list": 230, "detection_class": [230, 536], "detection_classes_list": 230, "detection_mask": 230, "detection_scor": [230, 536], "detection_scores_list": 230, "detection_typ": 230, "detectionboxes_precis": 234, "detectioncoco": 553, "detections_list": 230, "detector": 143, "determin": [169, 175, 180, 191, 195, 427, 460, 470, 475, 481, 483, 488, 490, 519, 542, 544], "determinist": 536, "dettmer": [476, 487, 547], "dev": 527, "develop": [135, 156, 245, 472, 473, 489, 490, 520, 532, 536, 537, 539, 542, 543, 546, 549], "deviat": [225, 551], "devic": [1, 64, 74, 75, 76, 77, 78, 79, 82, 92, 116, 121, 132, 139, 140, 145, 170, 173, 174, 188, 192, 195, 336, 346, 347, 348, 349, 350, 353, 357, 371, 376, 384, 396, 398, 401, 413, 417, 418, 420, 423, 425, 429, 431, 433, 441, 445, 447, 461, 473, 476, 477, 483, 487, 492, 494, 521, 536, 537, 542, 545, 547], "device_id": [140, 396], "device_nam": [443, 445], "device_synchron": 445, "devop": 489, "df": 90, "diag": 31, "diagnosi": 543, "diagon": [31, 476, 547], "diagram": [476, 494, 495, 552], "dict": [1, 31, 101, 133, 134, 135, 140, 145, 146, 151, 154, 160, 165, 169, 170, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 194, 195, 198, 199, 208, 229, 230, 231, 232, 234, 235, 243, 262, 277, 280, 281, 289, 299, 303, 305, 385, 390, 391, 396, 399, 404, 406, 411, 412, 413, 417, 418, 419, 420, 425, 427, 433, 435, 437, 438, 439, 442, 447, 448, 451, 452, 454, 456, 458, 464, 465, 476, 477, 478, 483, 490, 494, 520, 526, 535, 542, 544, 550, 552], "dictionari": [52, 53, 55, 133, 134, 135, 140, 145, 194, 195, 224, 230, 324, 325, 327, 391, 396, 404, 413, 417, 431, 441, 447, 465], "differ": [128, 146, 150, 152, 154, 156, 157, 163, 184, 195, 203, 211, 225, 234, 243, 245, 380, 390, 444, 460, 471, 476, 477, 480, 483, 487, 488, 490, 494, 521, 524, 525, 529, 530, 531, 535, 536, 538, 540, 542, 544, 547, 550, 551, 552], "difficult": [474, 479, 481, 487, 493, 550], "difficulti": [474, 479, 487, 550], "diffus": [492, 543], "digit": [227, 465, 543], "dilat": [43, 315], "dilated_contract": [61, 333], "dilatedcontract": [43, 315], "dilation_r": [292, 294, 298], "dim": [225, 487, 550, 551], "dimens": [52, 53, 90, 202, 225, 324, 325, 387, 413, 476, 547, 551], "dir": [145, 209, 461, 464, 527, 530], "direct": [85, 179, 355, 477, 542], "direct8bit": 11, "direct8bitoper": 11, "direct_q8": 16, "directli": [171, 195, 208, 230, 234, 478, 535, 536, 542, 544], "directori": [195, 210, 211, 243, 390, 408, 431, 441, 461, 464, 465, 492, 524, 527], "disabl": [133, 195, 391, 488, 546, 547, 550], "disable_al": 195, "disable_quanted_input": 451, "disable_random": [133, 391], "discard": 521, "discord": 492, "discourag": 542, "discov": 519, "discret": [3, 552], "discrimin": 553, "discuss": [477, 492], "dispatch": [494, 531], "displai": [195, 277, 278, 391, 465], "distanc": 465, "distil": [162, 195, 469, 492, 525, 529, 531, 541], "distil_loss": [195, 536], "distilbert": [209, 537, 543, 553], "distillation_conf": 162, "distillation_criterion": [523, 536, 541], "distillationcallback": 162, "distillationconfig": [195, 448, 523, 536, 541], "distilroberta": 553, "distinct": [472, 539], "distort": 494, "distribut": [1, 3, 128, 150, 195, 200, 202, 203, 205, 206, 207, 208, 380, 387, 460, 469, 471, 476, 480, 487, 494, 521, 532, 543, 544, 547, 548, 550, 553], "distribute_calib_tensor": 1, "distributedoptim": 524, "distributedsampl": 524, "distutil": 527, "div_": [487, 550], "dive": [469, 528], "diverg": [3, 452, 460, 495, 519, 552], "divid": [487, 521, 550, 552], "divis": [31, 413], "dl": [235, 473, 530, 543, 553], "dlabel": 490, "dlrm": 234, "dmlexecutionprovid": 544, "dnnlexecutionprovid": [537, 544], "do": [162, 188, 195, 208, 209, 227, 230, 411, 458, 464, 471, 477, 488, 494, 520, 524, 528, 531, 535, 536, 542, 546, 548, 550, 552], "do_blockwis": [413, 439, 550], "do_constant_fold": 458, "do_lower_cas": [209, 224, 225, 551], "doc": [177, 178, 195, 234, 262, 277, 278, 281, 391, 443, 465, 492, 532, 535, 536], "doc_span_index": 225, "doc_strid": [225, 551], "doc_token": 225, "docker": 527, "docstr": [195, 281], "docstyl": 489, "document": [225, 281, 469, 473, 478, 479, 487, 494, 495, 499, 524, 534, 537, 542, 548, 551], "doe": [227, 280, 301, 305, 475, 476, 480, 520, 521, 535, 536, 547, 548, 551], "doesn": [140, 225, 396, 473, 480, 493, 524, 536, 537], "dolli": [474, 534, 542, 550, 553], "domain": [89, 90, 195, 542, 552], "don": [128, 150, 175, 195, 380, 474, 475, 490, 542, 552], "done": [487, 490, 523, 542, 544], "dong": 135, "dot": [391, 465, 473, 487, 537, 544], "dotdict": [195, 245, 465], "doubl": [438, 439, 476, 543], "double_qu": 447, "double_quant_bit": [439, 476], "double_quant_dtyp": [439, 476], "double_quant_group_s": [439, 476], "double_quant_typ": 447, "double_quant_use_sym": [439, 476], "dowload_hf_model": [141, 398, 447], "download": [141, 211, 398, 447, 492, 532, 548], "download_url": 211, "downstream": 542, "dq": [92, 94, 116, 357, 359, 371, 470, 475, 477, 487, 550], "draw": [521, 549, 552], "drive": 495, "driven": [245, 492, 529, 536, 540], "drop": [192, 230, 418, 473, 474, 476, 487, 489, 536, 537, 542, 547, 550, 553], "drop_last": [203, 207, 387], "dry_run": 524, "dscore": 490, "dtype": [30, 31, 87, 90, 195, 212, 213, 221, 225, 387, 401, 406, 409, 413, 423, 429, 433, 439, 461, 473, 476, 477, 487, 494, 495, 526, 528, 544, 547, 550, 551], "dtype_map": 30, "dtype_to_nam": 30, "duc": 553, "due": [154, 487, 495, 526, 542, 544, 550], "dummi": [44, 173, 212, 213, 234, 316, 387, 480, 535, 536], "dummy_biasadd": [61, 333], "dummy_dataset": 215, "dummy_dataset_v2": 215, "dummy_v2": [213, 387], "dummydataset": [212, 213, 387, 480], "dummydatasetv2": 387, "dump": [2, 138, 145, 151, 154, 397, 413, 417, 447, 458, 465, 480, 487, 489, 544], "dump_class_attr": 465, "dump_data_to_loc": 465, "dump_elapsed_tim": [161, 391, 465, 493], "dump_fp32": [131, 383], "dump_model_op_stat": [413, 417, 447], "dump_numa_info": 154, "dump_op_typ": 2, "dump_stats_path": [439, 471], "dump_tabl": 465, "dump_table_to_csv": 465, "duplic": [83, 93, 266, 354, 358], "durat": 549, "dure": [1, 138, 140, 175, 179, 190, 195, 245, 396, 397, 413, 442, 447, 465, 474, 475, 477, 480, 487, 492, 494, 529, 536, 538, 540, 541, 542, 544, 550], "dyna": 195, "dynam": [140, 195, 200, 278, 387, 396, 409, 435, 437, 439, 458, 476, 477, 492, 493, 521, 526, 529, 531, 536, 543, 552, 553], "dynamic_ax": [195, 458, 526], "dynamic_length": 209, "dynamic_max_gap": [418, 439, 476], "dynamic_quant_export": 458, "dynamic_shap": 435, "dynamicquantconfig": [439, 470], "dynamo": [475, 477], "e": [140, 154, 175, 195, 396, 476, 483, 487, 488, 489, 492, 525, 542, 547, 550, 552], "e16": 489, "e2m1": [472, 476, 539, 547], "e2m3": [472, 539], "e3m2": [472, 539], "e4m3": [439, 471, 472, 492, 539], "e5m2": [471, 472, 539], "e8m0": [472, 539], "each": [126, 133, 135, 140, 145, 154, 192, 195, 207, 211, 214, 221, 225, 228, 230, 231, 232, 271, 286, 387, 396, 412, 413, 417, 431, 433, 465, 469, 476, 479, 482, 487, 489, 493, 494, 495, 520, 523, 528, 536, 540, 542, 545, 547, 549, 551, 552], "eager": [188, 261, 435, 470, 475, 476, 477, 524, 531, 544, 546], "earli": [195, 487, 536, 544, 552], "eas": [477, 480, 532, 543], "easi": [209, 475, 477, 480, 526, 536, 543, 544, 547, 549], "easier": 543, "easili": [245, 481, 487, 493, 540, 550], "econom": 488, "ecosystem": [492, 543], "edg": 551, "edit": 488, "edouard": [487, 550], "edu": [3, 211], "educ": 488, "effect": [187, 475, 476, 493, 542, 543], "effici": [29, 149, 413, 475, 483, 487, 492, 519, 521, 541, 542, 543, 547, 550, 552], "efficientnet": 553, "efficientnet_b0": 553, "efficientnet_b3": 553, "effort": 536, "eg": [145, 211, 433], "either": [140, 153, 195, 230, 396, 475, 480, 481, 483, 487, 541, 544], "elaps": [161, 391, 465], "electra": 553, "electron": 488, "elem_format": 404, "elem_typ": 90, "element": [31, 153, 177, 178, 192, 207, 230, 387, 404, 433, 465, 472, 476, 487, 531, 535, 539, 542, 547, 550], "elementwise_over_al": 192, "elementwise_over_matmul_gemm_conv": 192, "elemformat": 404, "eleutherai": [474, 529, 534, 550, 553], "elia": [476, 487, 547], "elimin": [51, 323], "ellipsi": [406, 443], "els": [1, 133, 195, 207, 245, 385, 433, 547], "em": 553, "email": 492, "emb": 476, "embed": [145, 420, 519, 542], "embed_layernorm": 16, "embed_out": 542, "embedlayernorm": 12, "embedlayernormalizationoper": 12, "emerg": [472, 539, 550], "emit": 471, "emnlp": [492, 543], "emot": 553, "empathi": 488, "empir": [128, 150, 380], "empow": [472, 539], "empti": [141, 195, 398, 447, 471, 476, 477, 545], "emsp": 542, "emul": [477, 487, 536, 544], "en": [492, 532], "enabl": [31, 94, 135, 180, 195, 359, 409, 473, 475, 476, 480, 494, 495, 524, 537, 542, 543, 550, 552], "enable_act": 135, "enable_al": 195, "enable_auto_scal": [31, 547], "enable_bas": 195, "enable_eager_execut": 524, "enable_extend": 195, "enable_full_rang": [418, 433, 439, 461, 476, 545, 547], "enable_minmax_tun": [418, 439, 476], "enable_mse_search": [31, 547], "enable_quanted_input": [418, 439, 476], "encapsul": [95, 198, 199, 235, 262, 360, 448, 538], "encod": [140, 230, 396, 451, 551], "encodejp": 551, "encount": [521, 527], "end": [133, 180, 181, 182, 187, 195, 209, 224, 225, 263, 265, 385, 493, 494, 495, 523, 528, 532, 536, 540, 542, 547, 551, 552], "end_epoch": 536, "end_posit": 225, "end_step": [180, 195, 536, 542], "endlessli": 552, "energi": [472, 539], "engin": 473, "english": 542, "enhanc": [483, 519, 542, 543, 546], "enough": [156, 413, 480, 487, 544], "enough_memo_store_scal": 413, "ensp": 551, "ensur": [1, 225, 266, 475, 478, 524, 544, 551], "ensure_list": 1, "entir": [262, 448, 474, 476, 479, 490, 494, 495, 519, 542], "entranc": [64, 201, 336], "entri": [52, 53, 55, 135, 165, 301, 302, 305, 324, 325, 327, 437, 438, 441, 442, 465, 477, 520, 533], "entropi": [195, 519, 552], "enum": 1, "enumer": [156, 157, 448, 472, 493, 523, 524, 536, 539, 541, 542], "env": [151, 527], "env_var": 151, "environ": [30, 151, 443, 446, 473, 477, 483, 488, 492, 518, 552], "eoferror": [138, 397], "ep": [3, 150, 537], "epoch": [162, 181, 182, 187, 448, 521, 523, 524, 536, 541, 542], "equal": [90, 128, 133, 150, 281, 380, 391, 465, 472, 539, 542, 547], "equal_dict": 465, "equat": [30, 232, 234, 487, 544, 550], "equival": [68, 340, 432, 472, 474, 476, 479, 487, 492, 539, 543, 547, 550], "erf": [54, 326], "error": [31, 90, 135, 140, 234, 271, 396, 413, 451, 462, 471, 476, 487, 527, 535, 547, 550, 552], "error_msg": 90, "especi": 529, "essenti": [519, 527], "estim": [133, 234, 243, 390, 552], "estimator_sess": [243, 390], "et": [135, 472, 476, 487, 519, 539, 547, 550], "etc": [151, 162, 224, 232, 235, 262, 392, 464, 492, 531, 542, 549, 552], "ethnic": 488, "euclidean": 465, "eural_compressor": 245, "eval": [490, 520, 521, 544], "eval_acc": 153, "eval_acc_fn": [473, 478, 480], "eval_arg": [153, 302, 438, 473, 477, 478, 480], "eval_dataload": [151, 195, 198, 199, 235, 262, 263, 264, 266, 267, 271, 273, 274, 448, 518, 530, 535, 536, 544, 545, 552], "eval_fn": [153, 302, 438, 473, 477, 478, 479, 480, 481], "eval_fn_wrapp": 479, "eval_frequ": 162, "eval_func": [125, 198, 199, 235, 262, 263, 264, 266, 267, 271, 273, 274, 281, 283, 448, 490, 521, 523, 524, 536, 544, 545, 546, 547, 552], "eval_metr": [198, 199, 235, 262, 263, 264, 266, 267, 271, 273, 274, 448, 535, 544], "eval_perf": 153, "eval_result": 520, "eval_result_of_q_model": 153, "evalu": [151, 153, 162, 175, 198, 199, 209, 227, 230, 231, 232, 234, 235, 245, 262, 438, 448, 454, 477, 479, 480, 481, 487, 493, 494, 520, 523, 530, 531, 534, 535, 536, 537, 540, 542, 544, 549, 550, 552], "evaluate_squad": 233, "evaluation_result": 524, "evaluation_time_cost": 524, "evaluationfuncwrapp": 153, "even": [487, 545, 547, 550], "evenli": 521, "event": 488, "everi": [52, 53, 55, 175, 178, 180, 195, 324, 325, 327, 476, 493, 521, 545, 547, 552], "everyon": 488, "everyth": 192, "exact": [231, 418], "exact_match_scor": 231, "exactli": 524, "exampl": [1, 31, 135, 140, 145, 151, 152, 153, 156, 160, 173, 174, 188, 195, 209, 210, 211, 221, 225, 230, 231, 232, 234, 235, 245, 262, 280, 281, 391, 396, 408, 411, 426, 431, 433, 435, 443, 447, 448, 464, 465, 469, 474, 480, 481, 483, 488, 492, 494, 495, 499, 529, 530, 531, 546, 548, 551, 552, 554], "example_algo": [391, 447], "example_gener": 281, "example_index": 225, "example_inp": 145, "example_input": [145, 195, 408, 411, 412, 413, 417, 432, 433, 435, 438, 442, 458, 464, 470, 474, 475, 476, 477, 526], "examplealgorithm": 152, "examplealgorithmconfig": 152, "exampleclass": 281, "exce": [225, 547, 551], "exceed": [243, 390], "excel": [487, 547], "except": [140, 281, 396, 413, 465, 476, 520, 544, 545], "exchang": 526, "exclud": [195, 471, 493, 519, 546], "excluded_op_nam": [56, 57, 195, 328, 329, 536, 542], "excluded_precis": [195, 439, 546], "execut": [29, 30, 39, 140, 151, 157, 180, 181, 182, 195, 261, 262, 263, 265, 311, 392, 396, 412, 420, 448, 454, 464, 465, 475, 476, 487, 523, 536, 537, 541, 542, 544, 547, 549, 552, 553], "executionprovid": 553, "exemplifi": 542, "exhaust": [195, 270, 413], "exhaustivetunestrategi": 268, "exist": [39, 151, 243, 311, 390, 391, 445, 465, 473, 477, 526, 535, 552], "exit": [195, 263, 265, 481, 536], "exit_polici": 536, "exp": [195, 472, 536, 539, 542], "expand_and_reshap": 404, "expanddim": [45, 317], "expanddims_optim": [61, 333], "expanddimsoptim": [45, 317], "expect": [211, 476, 478, 487, 488, 489, 527, 534, 544, 547, 552], "expens": [536, 552], "experi": [480, 488, 549, 550, 552], "experiment": [523, 524, 526, 536, 542, 544, 548, 551], "explain": [156, 487, 495, 550], "explicit": 488, "explicitli": [156, 195, 475, 483, 530, 542], "explor": [472, 493, 539], "explos": [472, 539], "expon": [472, 539], "exporsingleimagedetectionboxestococo": 230, "export": [86, 195, 230, 436, 459, 469, 470, 473, 475, 477, 527], "export_compressed_model": [461, 547], "export_format": [418, 439], "export_model_for_pt2e_qu": 435, "exportconfig": 195, "exportdetectionstococo": 230, "exported_model": [470, 475], "exportgroundtruthtococo": 230, "exportsingleimagedetectionboxestococo": 230, "exportsingleimagedetectionmaskstococo": 230, "exportsingleimagedetectionstococo": 230, "exportsingleimagegroundtruthtococo": 230, "expos": 451, "express": [227, 488], "extend": [477, 494, 495, 529], "extend_engin": [95, 360], "extens": [138, 140, 391, 396, 397, 465, 473, 474, 475, 477, 487, 492, 493, 500, 520, 527, 528, 529, 531, 532, 534, 536, 537, 538, 542, 543, 544, 547, 550, 552], "extra": [140, 232, 396, 476, 536, 547], "extra_opset": 87, "extract": [52, 53, 55, 133, 173, 211, 280, 324, 325, 327], "extract_data_typ": 280, "extran": 520, "extrem": 519, "f": [140, 170, 396, 476, 487, 520, 524, 544, 547, 550], "f1": [231, 233, 234, 524, 535, 536, 549, 553], "f1_score": [231, 232], "face": [141, 398, 447, 488, 492, 499, 543, 548, 553], "facebook": [474, 534, 550, 553], "facil": [140, 396], "facilit": 520, "fact": [487, 544], "factor": [3, 126, 286, 413, 425, 470, 474, 476, 480, 487, 547, 550, 553], "factori": [241, 391], "fail": [140, 396, 490, 521, 526], "failur": [489, 490], "fair": 488, "faith": 488, "fake": [29, 31, 98, 142, 149, 156, 280, 413, 429, 433, 476, 487, 536, 544, 547, 550], "fake_qu": [33, 73, 92, 116, 121, 306, 345, 357, 371, 376], "fake_quant": 99, "fakeaffinetensorquantfunct": [142, 429], "fakealgoconfig": 156, "fakequ": [73, 288, 345], "fakequant": 98, "fakequantizebas": 98, "falcon": [474, 492, 534, 542, 550, 553], "fall": [140, 145, 396, 472, 539], "fallback": [145, 195, 269, 271, 272, 473, 474, 475, 526, 537, 546, 552], "fallback_list": 28, "fallback_ord": 145, "fallbacktuningsampl": 277, "fals": [1, 2, 28, 29, 30, 31, 32, 33, 34, 56, 57, 74, 77, 84, 87, 88, 90, 98, 116, 121, 128, 131, 132, 133, 139, 140, 144, 145, 151, 163, 166, 195, 200, 202, 205, 206, 208, 209, 211, 221, 225, 230, 234, 245, 262, 281, 289, 292, 293, 294, 297, 298, 303, 306, 328, 329, 346, 348, 371, 376, 380, 383, 384, 385, 387, 396, 403, 404, 406, 409, 413, 417, 418, 420, 425, 427, 429, 433, 439, 442, 451, 454, 461, 464, 465, 474, 476, 478, 480, 481, 482, 493, 494, 521, 528, 535, 536, 544, 547, 550, 551, 552], "familiar": 469, "famou": [476, 487, 547], "faq": [488, 492], "far": 477, "fashionmnist": 211, "fast": [187, 195, 476, 480, 542, 543, 547], "fast_bias_correct": [148, 195, 544], "fastbiascorrect": [147, 150], "faster": [521, 522, 526, 543, 552, 553], "fatal": 462, "father": [141, 173, 398], "fault": 489, "fault_tolerant_fil": 465, "fbgemm": [473, 537, 544], "fc": [145, 195, 542], "fc1": [145, 433, 475], "fc2": [31, 145, 433], "feasibl": 195, "featur": [195, 209, 210, 221, 225, 413, 473, 478, 487, 489, 492, 518, 521, 522, 536, 537, 538, 542, 543, 548, 551], "feb": 543, "fed": [413, 552], "feed": [133, 208, 385, 542], "feed_dict": [133, 208, 385], "feedward": 184, "fefin": 199, "feng": 533, "ferplu": 553, "fetch": [46, 145, 148, 154, 203, 318, 387, 494], "fetch_modul": [145, 433, 447], "fetch_weight_from_reshap": [61, 333], "fetchweightfromreshapeoptim": [46, 318], "few": [542, 543, 550, 552], "ffffff": 552, "ffn": [143, 184, 417], "ffn2_sparsiti": [171, 542], "ffn_modul": 184, "ffn_name": 184, "field": [195, 211, 230, 472, 490, 493, 495, 524, 536, 539, 549, 552], "field_nam": [161, 465], "fig": 471, "figur": [476, 545], "file": [90, 133, 138, 140, 141, 145, 148, 160, 166, 188, 192, 195, 198, 199, 209, 210, 211, 214, 224, 225, 230, 235, 245, 249, 250, 253, 262, 385, 391, 396, 397, 398, 411, 413, 417, 464, 465, 471, 476, 482, 489, 493, 494, 495, 524, 527, 530, 533, 535, 536, 538, 540, 544, 547, 551], "file_lik": [140, 396], "file_typ": 465, "filenam": [211, 465], "filepath": [140, 396, 465, 520], "fill": [549, 551, 552], "filter": [1, 209, 210, 211, 212, 213, 214, 216, 220, 292, 298, 387, 406, 427, 465, 495, 531, 542], "filter_fn": 427, "filter_registri": 218, "filter_typ": 218, "final": [140, 173, 180, 192, 396, 475, 487, 494, 536, 540, 542, 544, 548, 552], "finalize_calibr": 442, "find": [30, 52, 53, 55, 90, 133, 194, 234, 266, 324, 325, 327, 385, 465, 481, 493, 534, 542, 547, 549, 550, 552], "find_by_nam": 30, "find_lay": [194, 420], "find_layers_nam": 420, "find_opset": 90, "fine": [186, 209, 477, 520, 542, 543, 544], "finer": [487, 550, 552], "finest": [487, 550], "finetun": [476, 487, 542, 547], "finish": 483, "first": [128, 140, 145, 150, 152, 174, 195, 209, 230, 267, 278, 380, 391, 396, 413, 433, 465, 472, 473, 476, 482, 487, 490, 492, 493, 494, 495, 532, 537, 539, 544, 546, 547, 549, 550, 552], "first_conv_or_matmul_quant": [195, 544], "first_n": [131, 383], "fit": [151, 175, 195, 235, 262, 266, 281, 448, 490, 518, 521, 524, 530, 535, 536, 537, 538, 542, 544, 545, 546, 547], "fit_with_raw_cmd": 151, "fix": [133, 185, 187, 209, 385, 476, 521, 542, 544, 547, 552], "fix_ref_type_of_graph_def": [133, 385], "flag": [195, 228], "flan": 542, "flatten_static_graph": 173, "flex": [492, 532], "flexibl": [473, 476, 480, 492, 542, 547], "flip": [221, 225, 551], "float": [3, 30, 31, 125, 126, 135, 152, 175, 180, 189, 192, 195, 209, 221, 228, 230, 231, 232, 277, 281, 283, 286, 303, 392, 413, 418, 433, 439, 442, 443, 451, 465, 470, 471, 472, 473, 474, 475, 476, 478, 479, 481, 487, 520, 535, 539, 544, 550, 551], "float16": [5, 8, 30, 401, 406, 461, 471, 476, 547], "float16activationoper": 5, "float16binaryoper": 8, "float32": [212, 213, 225, 230, 387, 429, 461, 471, 476, 487, 493, 518, 536, 544, 547, 550, 551], "float_dict": 135, "float_model": [135, 476, 483], "float_to_bfloat16": 30, "float_to_float16": 30, "floatfunct": 490, "floor": [472, 539], "flop": [476, 487, 547], "flow": [231, 232, 487, 490, 536], "flowchart": 552, "fn": 406, "fn_arg": 406, "focu": [519, 552], "focus": [472, 476, 480, 488, 493, 529, 539], "fold": [47, 48, 145, 303, 319, 320, 413, 432, 433, 439, 458, 474, 476, 528, 547, 550], "fold_batch_norm": [61, 333], "fold_const": [61, 333], "foldbatchnormnodesoptim": [47, 319], "folder": [133, 211, 216, 235, 262, 385, 464, 476, 477, 547], "follow": [73, 95, 153, 174, 211, 227, 230, 345, 360, 392, 420, 472, 473, 474, 479, 482, 483, 487, 488, 489, 490, 492, 493, 494, 495, 520, 521, 523, 524, 527, 528, 532, 533, 535, 536, 537, 538, 539, 541, 542, 544, 547, 550, 552], "footprint": [195, 245, 523, 536, 540, 542, 545], "forc": [443, 546], "forg": 527, "fork": 489, "form": 232, "format": [5, 30, 39, 133, 145, 154, 195, 209, 210, 211, 230, 278, 281, 288, 289, 311, 385, 389, 390, 404, 431, 441, 444, 458, 461, 472, 473, 475, 477, 480, 482, 487, 492, 494, 495, 520, 524, 526, 535, 536, 537, 538, 539, 543, 544, 547], "format_list2str": 154, "format_vers": [138, 397], "formul": 536, "formula": [487, 542, 550], "forpytorch": 532, "fortensorflow": 532, "fortieth": 542, "forward": [1, 145, 192, 413, 433, 476, 487, 494, 536, 542, 544, 547, 550], "forward_wrapp": [145, 413, 433], "foster": 488, "found": [162, 406, 413, 473, 492, 520, 534, 537, 550, 552, 553], "foundat": 543, "four": [470, 475, 481, 553], "fp1": [487, 550], "fp16": [31, 195, 278, 399, 401, 406, 418, 439, 487, 544], "fp2": [487, 550], "fp32": [28, 29, 31, 64, 116, 121, 128, 145, 150, 195, 198, 199, 234, 267, 271, 278, 301, 305, 336, 371, 376, 380, 391, 406, 411, 412, 415, 431, 433, 437, 454, 457, 458, 461, 464, 465, 471, 473, 474, 475, 476, 477, 478, 480, 487, 489, 493, 495, 528, 534, 535, 536, 537, 544, 546, 547, 548, 549, 550, 552, 553], "fp32_baselin": [153, 454, 493], "fp32_graph": [128, 380], "fp32_layer": [292, 293, 294, 297, 298], "fp32_model": [135, 145, 431, 441, 458, 465, 474, 475, 479, 480, 545, 547], "fp32_model_path": 545, "fp32_onnx_config": 526, "fp32_onnx_path": 458, "fp32_op": [33, 35, 92, 306, 307, 357], "fp32_tensor": 465, "fp4": [433, 472, 476, 539, 547], "fp6": [472, 539], "fp8": [437, 439, 441, 472, 477, 539, 543], "fp8_config": [439, 471, 492], "fp8_entri": 437, "fp8_white_list": [439, 471], "fp8config": [437, 439, 471, 492], "fpath": 211, "frac": [472, 487, 539, 550], "fraction": [221, 551], "fragment": 493, "framework": [1, 151, 152, 157, 163, 165, 170, 176, 180, 183, 187, 188, 196, 197, 201, 202, 205, 208, 209, 210, 211, 212, 213, 214, 215, 216, 218, 220, 222, 225, 234, 235, 236, 237, 239, 272, 278, 288, 299, 389, 454, 469, 473, 475, 480, 481, 487, 493, 495, 519, 520, 524, 525, 529, 530, 531, 535, 536, 537, 542, 543, 544, 551, 552, 553], "framework_dataset": 211, "framework_nam": [152, 520], "framework_specific_info": [32, 288, 289, 493], "frantar": [476, 487, 542, 547], "free": [29, 149, 187, 198, 199, 262, 413, 474, 479, 487, 488, 540, 549, 550], "freez": [73, 74, 75, 133, 345, 346, 385, 470, 475, 542], "freeze_fake_qu": [80, 351], "freeze_valu": [80, 351], "freeze_value_without_calib": 80, "freezefakequantopoptim": [73, 345], "freezevaluetransform": [74, 346], "freezevaluewithoutcalibtransform": 75, "frequenc": [162, 180, 195, 536, 542], "frequent": 532, "fresh": [492, 532], "friendli": [472, 487, 528, 536, 539, 543, 550], "from": [1, 30, 46, 52, 53, 55, 90, 133, 140, 141, 145, 151, 152, 153, 160, 162, 163, 169, 170, 176, 177, 178, 179, 183, 185, 186, 187, 188, 189, 190, 191, 192, 195, 198, 199, 200, 203, 206, 209, 210, 211, 212, 213, 214, 216, 221, 227, 230, 231, 232, 235, 243, 245, 262, 278, 280, 281, 288, 318, 324, 325, 327, 385, 387, 390, 392, 396, 398, 406, 408, 411, 412, 413, 415, 417, 431, 433, 437, 441, 447, 448, 451, 454, 456, 457, 458, 461, 464, 465, 469, 470, 471, 472, 473, 474, 475, 476, 478, 479, 480, 481, 482, 483, 487, 488, 489, 490, 493, 495, 518, 520, 521, 523, 524, 525, 526, 527, 529, 531, 534, 535, 537, 538, 539, 540, 541, 542, 543, 544, 545, 546, 547, 548, 549, 550, 551, 552], "from_dict": 478, "from_pretrain": [461, 529, 536], "frozen": [235, 243, 262, 390, 538], "frozen_func": [133, 385], "frozen_pb_sess": [243, 390], "fuel": [472, 539], "full": [30, 209, 210, 211, 461, 465, 471, 476, 492, 519, 527, 533, 542, 547, 548], "full_rang": 433, "fulli": [478, 536, 544, 550], "fulltoken": 224, "fun": 281, "func": [133, 145, 161, 385, 465, 544], "func_dict": 454, "function": [124, 125, 138, 159, 181, 182, 187, 195, 198, 199, 210, 283, 296, 379, 393, 397, 421, 459, 469, 473, 475, 476, 477, 480, 487, 489, 490, 493, 494, 495, 518, 521, 523, 526, 530, 531, 534, 535, 536, 537, 542, 544, 547, 549, 550, 552], "function1": 281, "function2": 281, "function3": 281, "fundament": [478, 479, 519, 536], "funnel": 553, "funsd": 553, "further": [55, 195, 327, 473, 487, 488, 492, 537, 538, 544], "fuse": [1, 43, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 76, 77, 78, 79, 81, 116, 121, 144, 145, 149, 315, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 347, 348, 349, 350, 352, 371, 376, 417, 490, 550], "fuse_biasadd_add": [61, 333], "fuse_column_wise_mul": [61, 333], "fuse_conv_redundant_dequant": [80, 351], "fuse_conv_requant": [80, 351], "fuse_conv_with_math": [61, 333], "fuse_decomposed_bn": [61, 333], "fuse_decomposed_in": [61, 333], "fuse_gelu": [61, 333], "fuse_layer_norm": [61, 333], "fuse_matmul_redundant_dequant": [80, 351], "fuse_matmul_requant": [80, 351], "fuse_pad_with_conv": [61, 333], "fuse_pad_with_fp32_conv": [61, 333], "fuse_qdq_bn": [115, 370], "fuse_qdq_concatv2": [115, 370], "fuse_qdq_conv": [115, 370], "fuse_qdq_deconv": [115, 370], "fuse_qdq_in": [115, 370], "fuse_qdq_matmul": [115, 370], "fuse_qdq_pool": [115, 370], "fuse_reshape_transpos": [61, 333], "fusebiasaddandaddoptim": [49, 321], "fusecolumnwisemuloptim": [50, 322], "fuseconvredundantdequantizetransform": [76, 347], "fuseconvrequantizetransform": [77, 348], "fuseconvwithmathoptim": [51, 323], "fusedbatchnorm": [66, 338], "fusedbatchnormv2": [66, 338], "fusedbatchnormv3": [108, 118, 363, 373], "fusedbatcnormv3": [55, 327], "fusedecomposedbnoptim": [52, 324], "fusedecomposedinoptim": [53, 325], "fusedinstancenorm": [112, 367], "fusedmatmul": 18, "fusedmatmuloper": 18, "fusegeluoptim": [54, 326], "fuselayernormoptim": [55, 327], "fusematmulredundantdequantizetransform": [78, 349], "fusematmulrequantizedequantizenewapitransform": [79, 350], "fusematmulrequantizedequantizetransform": [79, 350], "fusematmulrequantizenewapitransform": [79, 350], "fusematmulrequantizetransform": [79, 350], "fusenodestartwithconcatv2": [109, 119, 364, 374], "fusenodestartwithconv2d": [110, 120, 365, 375], "fusenodestartwithdeconv2d": [111, 366], "fusenodestartwithfusedbatchnormv3": [108, 118, 363, 373], "fusenodestartwithfusedinstancenorm": [112, 367], "fusenodestartwithmatmul": [113, 122, 368, 377], "fusenodestartwithpool": [114, 123, 369, 378], "fusepadwithconv2doptim": [56, 328], "fusepadwithfp32conv2doptim": [57, 329], "fusetransposereshapeoptim": [58, 330], "fusion": [44, 46, 55, 63, 94, 111, 112, 113, 116, 117, 118, 122, 316, 318, 327, 335, 359, 366, 367, 368, 371, 372, 373, 377, 479, 490, 493, 528], "futur": [149, 153, 198, 199, 469, 477, 531, 534, 536], "fw": 494, "fwk": 239, "fwk_name": [152, 520], "fx": [145, 272, 406, 435, 441, 470, 473, 475, 531, 537, 543, 544, 546], "fx_model": 145, "fx_white_list": 145, "g": [90, 140, 154, 175, 195, 396, 476, 483, 487, 489, 525, 542, 547, 548, 550, 552], "g_idx": 429, "gain": [541, 543], "gan": 543, "gap": [476, 538], "gather": [1, 16, 195], "gatheroper": 13, "gaudi": [477, 492, 532, 543], "gaudi2": [471, 492, 532], "gaussian": [266, 552], "gavgpool": 16, "gb": 483, "gcc": 553, "gcp": 543, "gelu": [54, 326], "gemm": [16, 195], "gemm_to_matmul": [195, 544], "gemmoper": 15, "gen": [473, 487, 534, 537, 543, 544, 546], "gen_bar_updat": 211, "gender": 488, "gener": [1, 33, 34, 72, 107, 133, 145, 151, 153, 154, 173, 198, 199, 200, 208, 211, 212, 213, 214, 225, 227, 235, 258, 262, 266, 281, 299, 303, 306, 344, 385, 387, 413, 417, 418, 420, 438, 439, 442, 448, 471, 472, 473, 474, 476, 477, 478, 483, 487, 489, 490, 493, 495, 521, 535, 536, 537, 539, 540, 542, 543, 544, 546, 547, 550, 551, 552], "generaltopk": 234, "generate_activation_observ": [145, 417], "generate_feed_dict": [133, 385], "generate_ffn2_pruning_config": 171, "generate_mha_pruning_config": 171, "generate_prefix": [151, 154], "generate_xpu_qconfig": 417, "generategraphwithqdqpattern": [92, 357], "generator1": 281, "geomean": 531, "gestalt": 543, "get": [1, 29, 30, 31, 52, 53, 55, 89, 90, 133, 141, 145, 151, 154, 161, 165, 166, 169, 170, 171, 173, 176, 183, 189, 190, 191, 192, 195, 203, 225, 234, 243, 262, 271, 278, 280, 299, 302, 324, 325, 327, 385, 387, 390, 391, 398, 413, 417, 420, 433, 439, 447, 454, 458, 461, 465, 469, 474, 477, 482, 487, 494, 519, 527, 531, 532, 534, 536, 543, 547, 550, 552, 554], "get_absorb_lay": [145, 433], "get_acceler": 445, "get_activ": 166, "get_adaptor_nam": 280, "get_algorithm": 454, "get_all_config": 160, "get_all_config_set": [302, 438], "get_all_config_set_from_config_registri": [152, 520], "get_all_fp32_data": [391, 465], "get_all_registered_config": [299, 439], "get_architectur": 151, "get_attribut": 173, "get_blob_s": 31, "get_block_prefix": [145, 433], "get_bounded_thread": 151, "get_children": [141, 398], "get_common_modul": 173, "get_const_dim_count": [52, 53, 324, 325], "get_core_id": 151, "get_criterion": 169, "get_dataload": 418, "get_default_autoround_config": 439, "get_default_awq_config": 439, "get_default_double_quant_config": 439, "get_default_dynamic_config": 439, "get_default_fp8_config": 439, "get_default_fp8_config_set": 439, "get_default_gptq_config": 439, "get_default_hqq_config": 439, "get_default_mixed_precision_config": 439, "get_default_mixed_precision_config_set": 439, "get_default_mx_config": 439, "get_default_rtn_config": [439, 483], "get_default_sq_config": [303, 439], "get_default_static_config": 439, "get_default_static_quant_config": [299, 303], "get_default_teq_config": 439, "get_depth": [145, 417], "get_dict_at_depth": [145, 417], "get_double_quant_config_dict": 447, "get_element_under_depth": [145, 417], "get_embedding_contigu": 145, "get_estimator_graph": 133, "get_example_input": 145, "get_fallback_ord": 145, "get_filter_fn": 406, "get_final_text": 225, "get_framework_nam": 1, "get_func_from_config": 454, "get_graph_def": [133, 385], "get_half_precision_node_set": 406, "get_hidden_st": 145, "get_index_from_strided_slice_of_shap": 90, "get_input_output_node_nam": [133, 385], "get_ipex_vers": 445, "get_lay": 192, "get_linux_numa_info": 154, "get_max_supported_opset_vers": 89, "get_metr": 454, "get_model_devic": 447, "get_model_fwk_nam": 239, "get_model_info": 447, "get_model_input_shap": [133, 385], "get_model_typ": [243, 390], "get_modul": [141, 398, 413, 433], "get_module_input_output": [145, 433], "get_mse_order_per_fp32": 145, "get_mse_order_per_int8": 145, "get_named_children": [141, 398], "get_node_map": 458, "get_node_original_nam": 30, "get_numa_nod": 154, "get_number_of_socket": 465, "get_op_list": 465, "get_op_type_by_nam": 145, "get_par": [413, 433], "get_pattern": 176, "get_physical_id": 151, "get_postprocess": 454, "get_preprocess": 454, "get_processor_type_from_user_config": 447, "get_prun": 183, "get_quant": 447, "get_quant_dequant_output": 29, "get_quantizable_onnx_op": 458, "get_quantizable_ops_from_cfg": [145, 417], "get_quantizable_ops_recurs": [413, 417], "get_reg": 189, "get_reg_typ": 189, "get_reversed_numa_info": 154, "get_rtn_double_quant_config_set": 438, "get_schedul": 190, "get_schema": 89, "get_siz": 465, "get_sparsity_ratio": 192, "get_sparsity_ratio_tf": 192, "get_subgraphs_from_onnx": 90, "get_super_module_by_nam": [141, 398], "get_tensor_by_nam": [133, 385], "get_tensor_histogram": [391, 465], "get_tensor_val_from_graph_nod": 133, "get_tensorflow_node_attr": 90, "get_tensorflow_node_shape_attr": 90, "get_tensorflow_tensor_data": 90, "get_tensorflow_tensor_shap": 90, "get_tensors_info": 465, "get_tf_criterion": 191, "get_tf_model_typ": 390, "get_thread": 151, "get_threads_per_cor": 151, "get_torch_vers": [145, 445], "get_torchvision_map": 225, "get_tuning_histori": 465, "get_unquantized_node_set": 406, "get_weight_from_input_tensor": 133, "get_weight_scal": 31, "get_weights_detail": 465, "get_windows_numa_info": 154, "get_woq_tuning_config": [439, 481], "get_workspac": 161, "getdefaultencod": 451, "getenv": 520, "gholami": 542, "gigant": [474, 479, 550], "git": [489, 527, 532], "github": [3, 135, 177, 178, 188, 209, 227, 228, 231, 232, 234, 262, 439, 476, 489, 492, 525, 532, 533, 536, 548], "give": [156, 494, 552], "given": [1, 3, 30, 52, 53, 55, 89, 90, 101, 133, 141, 145, 152, 194, 225, 230, 262, 324, 325, 327, 392, 398, 406, 409, 413, 427, 433, 442, 447, 451, 477, 481, 495, 542, 550, 551], "global": [100, 175, 195, 280, 389, 465, 476, 477, 478, 490, 536, 542, 552], "global_config": 192, "global_st": 465, "global_step": 180, "globalaveragepool": 14, "globalaveragepooloper": 14, "glorot_uniform": [292, 293, 294, 298], "glue": [227, 234, 535, 536], "gluon": [1, 235, 262, 538], "glx": 527, "gm": 406, "go": [528, 547, 551], "goal": [151, 235, 262, 481, 487, 494, 521, 541, 544, 552], "goe": 471, "good": [478, 488, 544, 552], "googl": [473, 492, 520, 537, 543], "googlenet": 553, "got": [133, 385, 494, 527], "gp": 266, "gpt": [474, 492, 529, 534, 542, 550, 553], "gptq": [31, 392, 428, 431, 437, 439, 441, 477, 483, 487, 492, 520, 534, 545, 547], "gptq_arg": [476, 547], "gptq_config": 547, "gptq_config_path": 547, "gptq_entri": 437, "gptq_g128asym": 547, "gptq_g32asym": 547, "gptq_g32asym_disable_last_matmul": 547, "gptq_quantiz": 31, "gptq_related_block": 420, "gptqconfig": [437, 439, 451, 476, 481], "gptquantiz": 420, "gptqw4g128asym": 553, "gptqw4g128sym": 553, "gptqw4g32asym": 553, "gptqw4g32sym": 553, "gpu": [74, 75, 82, 140, 195, 346, 353, 396, 413, 443, 476, 480, 518, 531, 536, 537, 544, 545], "gracefulli": 488, "grad": [182, 187], "gradient": [169, 439, 476, 487, 492, 531, 536, 542, 543, 553], "gradient_accumulate_step": [418, 439, 476], "gradient_accumulation_step": 536, "gradientcriterion": 169, "gradual": [190, 542], "grain": [186, 477, 542, 543, 552], "gram": 228, "granular": [292, 293, 294, 297, 298, 409, 472, 487, 493, 494, 495, 528, 531, 539, 544, 550], "graph": [33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 90, 91, 92, 93, 94, 95, 97, 98, 99, 102, 115, 117, 121, 124, 127, 128, 130, 131, 132, 133, 173, 208, 236, 243, 261, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 360, 362, 370, 372, 376, 379, 380, 382, 383, 384, 385, 390, 406, 441, 470, 475, 487, 490, 493, 524, 530, 538, 544, 545, 546], "graph_bas": [72, 344], "graph_convert": [96, 361], "graph_converter_without_calib": 96, "graph_cse_optim": [61, 333], "graph_def": [39, 125, 126, 133, 235, 243, 261, 262, 283, 286, 311, 385, 390, 457], "graph_def_sess": [243, 390], "graph_modul": 435, "graph_nam": 87, "graph_node_name_map": 133, "graph_optimization_level": [195, 544], "graph_output": 90, "graph_rewrit": [96, 361], "graph_sess": [243, 390], "graph_transform_bas": [130, 382], "graph_util": [96, 361], "graphanalyz": [95, 360], "graphconvert": [33, 306], "graphconverterwithoutcalib": 34, "graphcseoptim": [59, 331], "graphdef": [59, 133, 243, 261, 331, 385, 390, 538], "graphfoldconstantoptim": [48, 320], "graphmodel": 406, "graphmodul": [145, 406, 435, 490, 546], "graphrewriterbas": [71, 343], "graphrewriterhelp": [95, 360], "graphtrac": [413, 433], "graphtransform": [129, 381], "graphtransformbas": [129, 381], "grappler": [60, 332, 528], "grappler_optim": 528, "grappler_pass": [61, 333], "grappleroptim": [60, 332], "greater": [133, 391, 465, 480, 542, 552], "greatest": 552, "greatli": [476, 545, 547], "grei": [476, 545], "grid": [195, 542], "ground": [231, 232], "ground_truth": [231, 232], "groundtruth": [195, 230], "groundtruth_box": 230, "groundtruth_boxes_list": 230, "groundtruth_class": 230, "groundtruth_classes_list": 230, "groundtruth_dict": 230, "groundtruth_is_crowd": 230, "groundtruth_mask": 230, "group": [31, 189, 292, 426, 433, 476, 487, 492, 531, 542, 547, 551, 552, 553], "group_dim": [439, 476, 547], "group_norm": 526, "group_siz": [31, 142, 145, 280, 426, 429, 433, 439, 451, 476, 481, 547], "grouplasso": 189, "groupnorm": 550, "grow": [476, 487, 547], "grown": 542, "growth": [472, 473, 536, 537, 539, 542], "gt": [474, 476, 550, 551], "guangxuan": [476, 487, 547, 550], "guarante": [195, 536], "guess_output_rank": 30, "gui": [531, 542], "guid": [209, 473, 480, 490, 492, 520, 532], "guidelin": [491, 492], "gz": 211, "h": [31, 195, 225, 524, 551], "h384": 553, "h5": 538, "ha": [52, 53, 55, 59, 140, 179, 180, 227, 281, 324, 325, 327, 331, 391, 396, 404, 420, 443, 473, 478, 480, 487, 489, 493, 494, 495, 521, 526, 531, 536, 537, 542, 544, 546, 549, 550, 552], "habana": [471, 492, 532], "habana_visible_devic": 492, "habanalab": 492, "hack": 227, "haihao": [533, 542], "half": [399, 401, 406, 439, 473, 476, 537], "half_away_from_zero": [292, 293, 294, 297, 298], "half_precision_convert": 400, "half_precision_rewrit": 407, "halfprecisionconvert": 399, "halfprecisionmodulewrapp": 401, "hand": [477, 480], "handl": [46, 133, 149, 159, 318, 385, 393, 413, 423, 462, 490, 491, 520, 521, 550], "handler": [398, 451, 465, 552], "hanj": 3, "hanwen": 533, "harass": 488, "hard": [195, 521], "hardswish": 526, "hardtanh": 550, "hardwar": [161, 447, 472, 475, 483, 492, 493, 531, 536, 539, 542, 543], "harm": 488, "harmon": [232, 234], "has_zp": 31, "hassoun": 542, "hat": 553, "have": [3, 59, 68, 126, 133, 140, 170, 174, 176, 183, 207, 227, 230, 234, 262, 280, 281, 286, 331, 340, 385, 396, 412, 413, 417, 472, 473, 474, 476, 481, 487, 488, 489, 494, 495, 520, 521, 524, 528, 533, 535, 536, 537, 539, 540, 542, 544, 545, 547, 550, 552], "haven": 542, "hawq": [135, 269, 552], "hawq_metr": 136, "hawq_top": 135, "hawq_v2": [195, 270], "hawq_v2_loss": 552, "hawq_v2tunestrategi": 269, "hbm": 532, "he": 493, "head": [171, 173, 177, 184, 192, 476, 542], "head_mask": 184, "header": [161, 465, 527], "heavi": [476, 523], "height": [179, 221, 225, 524, 551], "hellaswag": 553, "helloworld": [537, 551], "help": [145, 166, 433, 469, 481, 487, 520, 534, 538, 547, 552], "helper": [30, 95, 101, 133, 145, 209, 210, 211, 224, 243, 360, 385, 390, 417, 456, 457, 458, 463], "here": [230, 281, 471, 474, 475, 476, 479, 480, 483, 487, 494, 524, 525, 526, 528, 534, 535, 544, 548, 549, 550, 553], "herebi": 550, "herlper": [124, 379], "hesit": 542, "hessian": [31, 135, 269, 476, 547, 552], "hessian_trac": 135, "hessiantrac": 135, "heterogen": 543, "hf": [141, 398, 431, 441, 447, 483, 534, 550, 553], "hicham": 476, "hidden": [174, 179, 493], "high": [30, 212, 213, 387, 471, 480, 532, 543, 552], "higher": [152, 195, 198, 199, 235, 262, 443, 448, 471, 476, 483, 487, 490, 526, 535, 542, 544, 547, 549], "higher_is_bett": [195, 234, 262, 552], "highest": 552, "highli": [476, 543, 547], "highlight": 490, "hint": [465, 527], "histogram": [3, 391, 452, 465], "histogramcollector": 3, "histori": [195, 464, 465, 552], "history_cfg": 464, "hoc": 227, "hold": [230, 266], "holder": 216, "hook": [135, 162, 166, 184, 398, 454, 523, 536, 542, 550], "hope": 526, "horizont": [225, 551], "horovod": 524, "host": [492, 524], "hostconst": [82, 353], "hour": 552, "how": [31, 140, 162, 169, 175, 181, 182, 187, 195, 225, 396, 433, 447, 469, 473, 475, 476, 477, 478, 479, 480, 487, 489, 490, 491, 493, 521, 523, 524, 530, 535, 536, 542, 543, 544, 550, 551, 552], "howev": [140, 396, 476, 483, 487, 542, 547, 550], "howpublish": 533, "hp_dtype": [439, 471], "hpex": 445, "hpo": [198, 542], "hpoconfig": 195, "hpu": [429, 441, 443, 471, 477], "hpu_acceler": 443, "hpuweightonlylinear": 429, "hqq": [428, 439, 477, 492], "hqq_arg": 476, "hqq_blog": [439, 476], "hqq_entri": 437, "hqqconfig": [437, 439, 476], "hqqlinear": [423, 427], "hqqmodul": 422, "hqqmoduleconfig": 422, "hqqtensorhandl": 423, "hqquantiz": 427, "hqt": 471, "hqt_output": [439, 471], "hroughput": 482, "ht": 553, "html": [490, 492, 494, 519, 524, 531, 532, 544], "htmllabel": 552, "http": [3, 135, 169, 177, 178, 187, 188, 209, 211, 227, 228, 230, 231, 232, 234, 262, 420, 439, 476, 490, 492, 532, 533, 536, 542, 548], "hub": [141, 398, 431, 441, 447, 492, 525], "hue": 551, "hug": [141, 398, 447, 492, 543], "huge": [523, 542, 545], "hugginfac": [431, 441], "huggingfac": [173, 184, 209, 431, 441, 461, 472, 492, 525, 539, 550, 553], "huggingface_model": 188, "human": [154, 552], "hvd": [234, 524], "hw": 471, "hybirdblock": [235, 262], "hybrid": 483, "hybridblock": 538, "hyper": [167, 476], "hyperparamet": [195, 487, 549, 550, 552], "i": [1, 30, 31, 33, 34, 36, 39, 40, 45, 49, 55, 67, 70, 90, 117, 128, 133, 135, 138, 140, 144, 145, 150, 151, 153, 156, 161, 162, 165, 166, 169, 173, 174, 180, 185, 186, 187, 188, 189, 191, 192, 195, 198, 199, 200, 207, 208, 209, 210, 211, 212, 213, 216, 218, 221, 225, 227, 230, 232, 234, 235, 245, 249, 250, 253, 262, 267, 272, 280, 281, 306, 308, 311, 312, 317, 321, 327, 339, 342, 372, 380, 385, 387, 391, 396, 397, 406, 408, 409, 413, 417, 420, 426, 427, 431, 433, 435, 439, 441, 443, 445, 447, 448, 451, 461, 464, 465, 470, 471, 472, 473, 474, 475, 476, 477, 479, 480, 481, 482, 483, 487, 488, 489, 490, 492, 493, 494, 495, 496, 498, 504, 507, 510, 518, 519, 520, 521, 523, 524, 526, 527, 528, 531, 532, 533, 535, 536, 537, 538, 539, 540, 541, 542, 543, 544, 545, 546, 547, 548, 549, 550, 551, 552, 553], "ic": [532, 543], "id": [151, 224, 227, 229, 230, 231, 232, 535, 549, 552], "idea": [487, 492, 542, 550, 552], "ideal": 473, "ident": [59, 65, 174, 331, 337, 488], "identifi": [52, 53, 55, 140, 230, 243, 324, 325, 327, 390, 396, 481, 542, 547], "idx1": 211, "idx3": 211, "ieee": [135, 473, 487, 537, 550], "ignor": [465, 476, 487, 519, 547, 550, 552], "ignore_attr": 465, "ignore_kei": 465, "ii": 552, "illinoi": 3, "illustr": [476, 494, 495, 523, 552], "imag": [210, 211, 214, 216, 221, 225, 230, 473, 487, 524, 526, 542, 550, 551, 553], "image_format": 216, "image_height": 230, "image_id": [230, 535], "image_list": 214, "image_tensor": 536, "image_width": 230, "imageclassifi": 211, "imagefold": [211, 524, 536], "imagenet": [211, 214, 221, 478, 536, 542, 551, 553], "imagenet_dataset": 215, "imagenet_transform": 222, "imagenetraw": 214, "imagerecord": 524, "imageri": 488, "img": 492, "img1": 214, "img2": 214, "img_dir": 210, "imgx": 214, "iml": 543, "immedi": 542, "impact": [269, 542, 548, 552], "imper": 490, "implement": [95, 128, 132, 140, 198, 199, 204, 207, 208, 209, 211, 227, 235, 245, 262, 269, 360, 380, 384, 392, 396, 448, 476, 495, 521, 535, 536, 542, 544, 547, 548, 552], "implicitli": [140, 156, 396], "import": [133, 151, 153, 161, 195, 235, 245, 262, 281, 385, 431, 441, 445, 448, 465, 469, 470, 471, 472, 473, 474, 475, 476, 477, 478, 479, 480, 481, 483, 487, 490, 492, 495, 518, 521, 523, 524, 526, 529, 535, 536, 537, 538, 539, 540, 541, 542, 544, 545, 546, 548, 549, 550, 551, 552], "importerror": [138, 397, 527], "impract": 476, "improv": [186, 473, 475, 476, 487, 489, 492, 519, 520, 536, 542, 543, 544, 546, 547, 552, 553], "in_featur": [403, 423, 429], "in_graph": [133, 385], "in_graph_is_binari": [133, 385], "in_mp": 30, "inappropri": 488, "inc": [225, 301, 305, 429, 431, 441, 480, 481, 488, 494, 534, 543, 548, 552], "inc_model": [526, 538], "inc_target_devic": [443, 477], "incbench": 482, "incept": 553, "incid": 488, "incit": [474, 550], "includ": [138, 163, 169, 173, 175, 189, 191, 195, 209, 211, 218, 225, 281, 392, 397, 418, 431, 437, 441, 447, 465, 471, 476, 477, 480, 481, 483, 488, 493, 494, 495, 521, 532, 533, 534, 535, 536, 542, 544, 546, 547, 552], "include_lay": 452, "include_nod": 1, "include_tensors_kl": 1, "include_tensors_minmax": 1, "inclus": 488, "incompat": 527, "incorpor": [476, 494, 495, 523, 542, 552], "incorrect": [140, 396], "incquantizationconfigmixin": 451, "increas": [195, 472, 476, 522, 531, 539, 547, 552], "increasingli": 542, "increment": 552, "incub": 3, "incur": [472, 539], "incweightonlylinear": 429, "independ": [184, 257, 261, 495], "index": [52, 53, 55, 90, 151, 192, 195, 203, 207, 211, 324, 325, 327, 387, 465, 487, 492, 532, 535, 547, 550], "indexdataset": 207, "indexerror": [138, 397], "indexfetch": [203, 387], "indic": [140, 152, 162, 195, 203, 207, 209, 230, 387, 396, 409, 426, 443, 480, 490, 521, 527], "individu": [126, 175, 257, 261, 286, 487, 488, 542, 550], "industri": [535, 543], "infer": [1, 30, 90, 125, 145, 173, 243, 245, 262, 283, 301, 305, 390, 417, 433, 448, 473, 474, 475, 476, 479, 480, 487, 493, 494, 519, 523, 529, 536, 537, 540, 542, 543, 544, 547, 550, 552], "infer_onnx_shape_dtyp": 90, "infer_shap": 30, "inferenc": [472, 539], "influenc": [145, 542], "info": [30, 145, 154, 161, 177, 178, 192, 223, 239, 391, 412, 413, 417, 442, 447, 461, 462, 465, 490, 520, 538], "inform": [1, 135, 154, 169, 170, 173, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 195, 198, 199, 234, 389, 426, 465, 471, 472, 474, 476, 480, 482, 483, 488, 489, 491, 492, 493, 494, 495, 496, 498, 504, 507, 510, 519, 520, 528, 536, 538, 539, 542, 546, 547, 548, 550, 553, 554], "infrastructur": 522, "ingest": 230, "inherit": [162, 163, 185, 186, 190, 206, 225, 392, 493, 494], "init": [0, 4, 29, 148, 164, 170, 172, 193, 535, 552], "init_alpha": [413, 439], "init_quantize_config": 101, "init_tun": 153, "initi": [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 19, 21, 22, 23, 25, 26, 29, 30, 31, 90, 101, 133, 140, 153, 163, 180, 198, 199, 206, 209, 262, 278, 282, 285, 287, 291, 292, 293, 294, 295, 296, 297, 298, 300, 385, 396, 400, 409, 447, 448, 477, 480, 487, 495, 535, 542, 544, 550, 552], "initial_op_tuning_cfg": 277, "initial_tuning_cfg_with_quant_mod": 278, "initialize_int8_avgpool": 297, "initialize_int8_conv2d": 292, "initialize_int8_dens": 293, "initialize_int8_depthwise_conv2d": 294, "initialize_int8_maxpool": 297, "initialize_int8_separable_conv2d": 298, "initialize_name_count": 90, "inject": [44, 316, 536], "injectdummybiasaddoptim": [44, 316], "inlin": [133, 385], "innov": 543, "inplac": [29, 412, 413, 442, 477], "input": [1, 2, 29, 30, 31, 39, 45, 49, 52, 53, 55, 56, 57, 59, 67, 68, 70, 71, 90, 94, 95, 101, 107, 126, 133, 134, 142, 144, 145, 149, 154, 173, 174, 192, 195, 198, 199, 209, 210, 211, 213, 221, 224, 225, 234, 235, 239, 243, 262, 286, 311, 317, 321, 324, 325, 327, 328, 329, 331, 339, 340, 342, 343, 359, 360, 385, 387, 390, 391, 408, 411, 413, 417, 425, 429, 433, 435, 442, 447, 448, 456, 457, 458, 461, 464, 465, 470, 475, 476, 477, 487, 493, 494, 518, 519, 521, 523, 524, 526, 528, 530, 535, 536, 537, 538, 542, 544, 547, 550, 551], "input2tupl": 145, "input_data": [29, 521], "input_desc": 1, "input_dtyp": 90, "input_fil": 225, "input_fn": [133, 243, 390], "input_func": [145, 433], "input_graph": [116, 121, 128, 258, 261, 371, 376, 380, 493], "input_graph_def": [52, 53, 55, 324, 325, 327], "input_id": [209, 225, 536], "input_mask": [225, 536], "input_max": 413, "input_max_ab": 413, "input_min": 413, "input_minmax": 413, "input_model": 538, "input_model_tensor": 465, "input_nam": [52, 53, 87, 127, 195, 243, 324, 325, 390, 457, 458, 526], "input_name_to_nod": 456, "input_node_map": [52, 53, 324, 325], "input_node_nam": [69, 116, 121, 133, 341, 371, 376, 385], "input_output_nam": [60, 332], "input_pb": [129, 131, 132, 381, 383, 384], "input_scal": [142, 398, 413, 429], "input_shap": [90, 213, 387], "input_tensor": [133, 243, 385, 390], "input_tensor_data": 466, "input_tensor_ids_op_nam": [145, 417], "input_tensor_nam": [133, 243, 385, 390], "input_valu": [145, 433], "inputbatch": 225, "inputcapturemodul": 413, "inputfeatur": [209, 225], "inputs_as_nchw": [127, 457], "insecur": [140, 396], "insensit": 443, "insert": [62, 90, 92, 94, 98, 131, 149, 288, 334, 357, 359, 383, 413, 433, 442, 475, 476, 477, 479, 487, 490, 494, 521, 531, 536, 542, 544, 546, 547, 550], "insert_log": [130, 382], "insert_newlin": 465, "insert_print_nod": [61, 333], "insert_qdq_pattern": [91, 356], "insertlog": [131, 383], "insertprintminmaxnod": [62, 334], "inset": 536, "insid": [230, 476, 523, 527, 542, 545, 552], "insight": [543, 548, 552], "inspect": 548, "inspect_tensor": 493, "inspect_typ": 493, "inspir": [476, 547], "instal": [391, 480, 524, 527, 529, 554], "instanc": [100, 101, 151, 154, 195, 198, 199, 231, 232, 234, 235, 262, 266, 280, 409, 448, 465, 476, 482, 488, 489, 490, 493, 518, 529, 536, 547, 552, 553], "instance_index": 154, "instance_norm": 526, "instancenorm": [53, 325, 550], "instances_val2017": 210, "instanti": 541, "instead": [195, 208, 465, 475, 542, 547], "institut": 211, "instruct": [473, 474, 487, 494, 495, 532, 537, 542, 543, 544, 550, 553], "insuffici": 482, "insult": 488, "int": [1, 3, 29, 30, 31, 90, 125, 133, 143, 145, 152, 156, 161, 171, 195, 208, 209, 210, 221, 225, 228, 230, 234, 251, 257, 261, 280, 281, 283, 284, 288, 301, 302, 305, 385, 404, 413, 417, 418, 423, 425, 426, 429, 433, 439, 451, 457, 458, 461, 465, 476, 480, 520, 521, 535, 536, 547, 551], "int32": [429, 461, 476, 547], "int4": [487, 534, 544, 553], "int8": [5, 6, 30, 31, 72, 108, 109, 110, 116, 118, 119, 120, 121, 128, 133, 150, 151, 195, 221, 278, 280, 292, 293, 294, 297, 298, 299, 303, 344, 363, 364, 365, 371, 373, 374, 375, 376, 380, 409, 433, 439, 441, 456, 457, 458, 464, 465, 471, 472, 474, 476, 477, 478, 480, 487, 489, 490, 493, 494, 495, 518, 523, 528, 534, 536, 537, 539, 543, 544, 546, 547, 548, 549, 550, 551], "int8_conv_config": 494, "int8_model": [457, 458], "int8_model_path": 545, "int8_node_name_revers": 133, "int8_onnx_config": [195, 526], "int8_sequ": [33, 306], "int_label": 535, "int_max": 30, "integ": [162, 179, 180, 195, 230, 234, 281, 474, 476, 479, 487, 493, 495, 519, 544, 547, 550, 552], "integerop": 553, "integr": [133, 163, 385, 473, 477, 480, 487, 493, 536, 547], "intel": [154, 165, 177, 178, 188, 226, 233, 234, 246, 262, 270, 276, 290, 302, 303, 304, 305, 391, 392, 394, 436, 437, 438, 439, 440, 441, 442, 444, 445, 446, 447, 449, 451, 455, 467, 469, 471, 473, 474, 475, 476, 477, 478, 480, 481, 482, 484, 487, 488, 489, 491, 493, 494, 495, 519, 522, 523, 525, 526, 527, 528, 529, 533, 534, 537, 538, 540, 541, 542, 543, 544, 546, 547, 548, 550, 552, 553], "intel_extension_for_pytorch": [445, 475], "intelcaff": 543, "intellig": 543, "intelon": 543, "inteltensorflow": [214, 216], "intend": 489, "inter": 195, "inter_area": 221, "inter_num_of_thread": [195, 257, 261, 536], "inter_pol": 221, "interact": [492, 549], "interest": [488, 492], "interfac": [71, 98, 154, 301, 343, 390, 392, 454, 473, 475, 477, 480, 487, 531, 536, 544, 548], "interleav": 210, "intermedi": [30, 135, 163, 195, 487, 490, 531, 544], "intermediatelayersknowledgedistillationloss": 163, "intermediatelayersknowledgedistillationlossconfig": 195, "intern": [135, 207, 278, 387, 471, 521, 535, 542], "internal_pattern": 278, "internet": 211, "interpol": [186, 225, 535, 542, 551], "intersect": [234, 406, 493, 535], "interv": [186, 542], "intra": 195, "intra_num_of_thread": [195, 257, 261, 536], "introduc": [59, 331, 469, 476, 487, 493, 494, 495, 528, 536, 544, 547, 548, 550], "introduct": 469, "intuit": [476, 487, 547, 550], "inturn": 535, "inuput": 30, "invalid": 413, "invalid_lay": 175, "invent": [487, 544], "invers": [476, 547], "investig": [488, 520], "invok": [230, 494], "involv": 475, "io": [1, 140, 396, 439, 476, 492, 532], "iou": 234, "iou_thr": [230, 234, 535], "iou_typ": 230, "ipc": 492, "ipex": [145, 195, 411, 412, 413, 417, 437, 441, 445, 464, 473, 474, 531, 534, 536, 537, 550], "ipex_config": [145, 413], "ipex_config_path": [145, 413, 417], "ipexmodel": 244, "ir_vers": 29, "is_asymmetr": 494, "is_b_transpos": 30, "is_ckpt_format": [133, 385], "is_dynam": 409, "is_fused_modul": 145, "is_glob": 175, "is_hpex_avail": 445, "is_imposs": 225, "is_int8_model": 464, "is_ipex_avail": 445, "is_ipex_import": 445, "is_large_model": 30, "is_leaf": 420, "is_list_or_tupl": 90, "is_measur": 245, "is_model_quant": 1, "is_onnx_domain": 90, "is_package_avail": 445, "is_perchannel": 494, "is_qat": 144, "is_saved_model_format": [133, 385], "is_subgraph": 87, "is_transformers_import": 445, "isa": 473, "isiter": 1, "isn": [52, 53, 55, 324, 325, 327], "issu": [413, 487, 488, 489, 491, 492, 532, 544], "item": [30, 192, 195, 224, 278, 391, 465, 487, 519, 524, 542, 550, 552], "item_list": 30, "item_typ": 278, "itemstyl": 552, "iter": [1, 2, 90, 125, 133, 145, 151, 174, 180, 187, 190, 195, 198, 199, 203, 207, 211, 212, 235, 262, 283, 301, 305, 385, 387, 413, 417, 418, 425, 433, 439, 448, 451, 454, 476, 480, 481, 490, 493, 518, 521, 536, 542, 544, 550, 552], "iter_bar": 536, "iter_op": [133, 385], "iterabledataset": [207, 211], "iterablefetch": [203, 387], "iterablesampl": [207, 387], "iteration_list": 493, "iterativeschedul": 190, "iterator_sess_run": [133, 385], "itex": [32, 94, 195, 289, 359, 457, 480, 537, 544, 550], "itex_instal": 391, "itex_mod": [32, 33, 74, 92, 116, 121, 289, 306, 346, 357, 371, 376], "itex_qdq_mod": [56, 57, 328, 329], "itrex": [195, 418, 439, 474, 550], "its": [30, 45, 81, 133, 135, 173, 182, 185, 187, 192, 195, 205, 211, 225, 228, 229, 266, 317, 352, 406, 408, 456, 473, 476, 481, 487, 488, 533, 535, 537, 542, 547, 549, 551, 552], "itself": 542, "j": [474, 487, 492, 534, 542, 550, 553], "jan": 543, "jason": 550, "jbla": 31, "jeffrei": 519, "ji": [476, 487, 547], "jit": [173, 475, 550], "jitbasicsearch": 173, "jitter": 551, "john": [391, 465], "join": 492, "joint": 543, "jonathanhuang": 230, "journei": 543, "jpeg": 551, "jpg": [210, 214, 216, 492], "json": [145, 160, 210, 225, 411, 413, 417, 464, 476, 538, 547, 551], "json_file_path": [411, 464], "judg": 420, "juli": 543, "jun": 543, "june": [492, 543], "just": [82, 200, 223, 225, 245, 353, 387, 413, 475, 480, 487, 527, 536, 541, 544, 550, 551, 552], "k": [234, 262, 535, 542], "k_block": 31, "kappa": 425, "keep": [140, 161, 184, 192, 267, 396, 490, 493, 520, 548], "keep_mask_lay": 175, "keepdim": [487, 550], "kei": [133, 135, 140, 141, 173, 184, 192, 195, 243, 281, 390, 391, 396, 398, 413, 433, 452, 454, 465, 476, 487, 492, 494, 543, 547, 552], "kept": 179, "kera": [55, 101, 165, 173, 192, 195, 211, 218, 238, 243, 287, 290, 302, 305, 327, 390, 391, 478, 480, 494, 521, 524, 538], "keras_model": 237, "keras_sess": [243, 390], "kerasadaptor": 288, "kerasbasepattern": 175, "kerasbaseprun": 180, "kerasbasicprun": 181, "kerasconfigconvert": 288, "kerasmodel": [238, 390], "keraspatternnxm": 179, "kerasqueri": 288, "kerassurgeri": 288, "kernel": [31, 149, 195, 476, 493, 494, 552], "kernel_constraint": [292, 293], "kernel_initi": [292, 293], "kernel_regular": [292, 293], "kernel_s": [292, 294, 298], "keutzer": 542, "key_layer_nam": 184, "keynot": 543, "keyword": [140, 195, 396, 413, 431, 441], "kim": 542, "kind": [145, 536], "kit\u4e3aai\u5e94\u7528\u5e26\u6765\u9ad8\u6548\u5f02\u6784\u52a0\u901f\u670d\u52a1": 543, "kl": [1, 3, 195, 409, 413, 439, 452, 460, 494, 495, 519, 528, 536, 552], "kl_diverg": 459, "klcalibr": 3, "know": [520, 524, 548], "knowledg": [162, 163, 195, 479, 523, 525, 531, 536, 538], "knowledgedistillationframework": 163, "knowledgedistillationloss": [163, 536], "knowledgedistillationlossconfig": [195, 523, 536, 541], "known": [140, 266, 396, 471, 472, 536, 539, 542, 544, 552], "kriz": 211, "kullback": 495, "kwarg": [2, 30, 90, 107, 108, 109, 110, 111, 112, 113, 114, 117, 118, 119, 120, 122, 123, 141, 145, 171, 195, 211, 223, 225, 234, 235, 236, 238, 240, 242, 243, 244, 262, 277, 279, 281, 292, 293, 294, 297, 298, 363, 364, 365, 366, 367, 368, 369, 372, 373, 374, 375, 377, 378, 390, 398, 399, 418, 420, 429, 431, 433, 437, 439, 441, 447, 448, 451, 461, 462, 464, 465, 521], "kwon": 542, "l": [476, 482, 519, 552], "l1": 195, "l12": 553, "l2": [195, 542], "l6": 553, "l954": 227, "l983": 227, "label": [195, 198, 199, 209, 211, 212, 213, 214, 217, 221, 225, 227, 229, 234, 235, 262, 387, 413, 448, 480, 490, 521, 535, 536, 544, 551], "label_fil": [209, 225, 551], "label_list": [209, 234], "label_map": 535, "label_shap": [213, 387], "label_shift": [221, 551], "labelbalancecocorawfilt": 217, "labelbalancecocorecordfilt": 217, "labelshift": [221, 551], "lack": [521, 527], "lake": [473, 532, 537, 543], "lambada": [474, 550], "lambada_openai": [534, 553], "lambda": [140, 396, 545], "lamini": [474, 542, 550], "land": 543, "languag": [29, 149, 227, 413, 431, 441, 471, 472, 474, 476, 477, 479, 480, 487, 488, 526, 539, 543, 545, 547, 550], "laplacian": 476, "larei": 542, "larg": [29, 30, 149, 413, 471, 472, 474, 476, 477, 479, 480, 487, 521, 536, 539, 543, 545, 547, 550, 553], "larger": [152, 443, 476, 487, 494, 542, 547, 550], "lasso": [189, 531, 542], "lassounbalanc": 553, "last": [145, 169, 192, 195, 413, 471, 473, 474, 476, 521, 537, 544, 547, 550], "last_batch": [200, 202, 205, 206, 208, 387, 521], "last_conv_or_matmul_quant": [195, 544], "latenc": [549, 552], "latency_pattern": 482, "later": [140, 149, 396, 413, 443, 470, 520], "latest": [473, 477, 492, 532, 543, 548], "latin1": [140, 396], "launch": [482, 537], "launcher": 523, "layer": [32, 101, 102, 103, 104, 106, 107, 137, 139, 141, 149, 163, 166, 171, 173, 174, 175, 179, 184, 192, 194, 195, 288, 289, 291, 391, 395, 398, 413, 420, 429, 452, 454, 465, 469, 474, 475, 477, 487, 493, 494, 495, 523, 527, 531, 542, 547, 548], "layer1": [173, 195, 536, 542, 544], "layer2": [173, 536, 542, 544], "layer3": [536, 542], "layer_1": 174, "layer_2": 174, "layer_idx": 192, "layer_initi": 295, "layer_input": 192, "layer_map": [163, 195], "layer_nam": [195, 413, 542], "layer_norm": 526, "layer_tensor": 452, "layer_wis": [394, 464, 545], "layer_wise_qu": [136, 195, 545], "layerhistogramcollector": 452, "layernorm": [55, 327, 487, 550], "layerwisequ": 139, "layout": [39, 311], "layoutlmv2": 553, "layoutlmv3": 553, "lazi": [161, 465], "lazyimport": [161, 465], "ld_library_path": 527, "lead": [195, 473, 476, 480, 487, 520, 536, 537, 542, 547, 550], "leadership": 488, "leaky_relu": 526, "leakyrelu": [40, 312, 550], "learn": [469, 472, 473, 476, 477, 480, 487, 492, 493, 494, 521, 526, 530, 531, 532, 536, 537, 539, 542, 543, 544, 550, 552], "learning_r": [195, 536], "least": [188, 489, 536, 542, 552], "leav": 101, "lee": 542, "left": [221, 225, 487, 550, 551], "legal": [492, 554], "leibler": 495, "len": [135, 195, 225, 524, 551], "length": [184, 195, 209, 225, 230, 418, 476, 487, 535, 543, 544, 547, 551], "less": [40, 133, 145, 195, 312, 391, 433, 465, 518, 536, 542], "let": [495, 528, 542], "level": [31, 156, 173, 267, 281, 462, 471, 472, 487, 488, 539, 550, 552], "levelwis": 173, "leverag": [60, 332, 461, 470, 471, 475, 478, 481, 487, 526, 541, 544, 547, 552], "lib": 527, "libgl": 527, "libgl1": 527, "libglib2": 527, "librari": [174, 226, 257, 467, 473, 480, 492, 532, 536, 537, 543, 544], "licens": 489, "lie": 519, "light": 523, "lightn": 492, "lightweight": [483, 542], "like": [59, 81, 83, 133, 140, 156, 173, 192, 195, 198, 199, 200, 211, 234, 243, 262, 331, 352, 354, 385, 387, 390, 396, 448, 451, 473, 476, 480, 487, 489, 490, 492, 493, 494, 523, 531, 541, 542, 544, 547, 548, 550, 552], "limit": [138, 266, 397, 465, 472, 476, 477, 480, 492, 534, 539, 544, 547], "lin": [476, 487, 547], "line": [494, 520, 524, 531], "linear": [30, 142, 145, 149, 171, 173, 174, 179, 184, 192, 194, 195, 403, 413, 423, 427, 429, 433, 471, 474, 475, 476, 487, 490, 526, 536, 542, 547, 550, 552], "linear2linearsearch": 173, "linear_lay": 184, "linear_pattern": 174, "linearcompress": 174, "linearcompressioniter": 174, "linearli": 30, "link": [195, 209, 234, 262, 471, 477, 519, 526, 547, 553], "linkedin": 543, "linux": [154, 482, 483, 518, 527], "list": [1, 29, 30, 31, 39, 90, 125, 133, 135, 143, 145, 151, 152, 153, 154, 156, 173, 174, 179, 184, 188, 192, 194, 195, 198, 199, 203, 209, 221, 225, 227, 228, 230, 231, 232, 234, 235, 243, 249, 250, 253, 262, 277, 281, 283, 299, 302, 303, 305, 311, 385, 390, 398, 406, 413, 417, 418, 420, 433, 438, 439, 447, 448, 452, 457, 458, 465, 471, 474, 477, 479, 480, 490, 492, 493, 526, 528, 532, 534, 536, 540, 542, 544, 546, 550, 552], "liter": 281, "llama": [474, 483, 492, 534, 542, 543, 545, 547, 550, 553], "llama2": 492, "llamanorm": 550, "llm": [125, 126, 283, 286, 420, 439, 471, 472, 474, 475, 476, 479, 487, 529, 539, 542, 543, 545, 547, 550], "llm_weight_minmax": [92, 357], "lm": [476, 542], "lm_head": [476, 542, 547], "lm_head_config": 476, "ln": 527, "load": [133, 138, 140, 141, 160, 209, 224, 225, 235, 243, 262, 385, 390, 395, 397, 398, 408, 411, 412, 413, 415, 417, 431, 441, 444, 447, 464, 465, 471, 480, 494, 521, 527, 544, 545, 550], "load_and_cache_exampl": 209, "load_config_map": 160, "load_data_from_pkl": 465, "load_empty_model": [141, 398, 447, 476, 483, 545], "load_entri": 440, "load_huggingfac": [459, 536], "load_layer_wise_quantized_model": [141, 398], "load_modul": 398, "load_saved_model": [243, 390], "load_state_dict": [140, 396], "load_tensor": [141, 398], "load_tensor_from_shard": [141, 398], "load_valu": 398, "load_vocab": 224, "load_weight_onli": 464, "loadannot": 230, "loaded_model": 476, "loader": [1, 125, 198, 199, 235, 262, 283, 301, 305, 431, 448, 461, 521, 544], "loadformat": [431, 444], "loc": [140, 396], "local": [175, 195, 431, 441, 465, 476, 478, 492, 527, 532, 542, 549], "local_config": [192, 195], "local_config_fil": [32, 288, 289], "locat": [140, 146, 192, 225, 396, 413, 475, 480, 524, 544, 548, 551], "lock": [185, 531, 541, 542], "log": [131, 151, 159, 161, 173, 249, 250, 253, 383, 393, 413, 462, 482, 490, 549, 552], "log2": [472, 539], "log_fil": [151, 256, 260], "log_interv": 524, "log_process": 161, "log_quantizable_layers_per_transform": 420, "logfile_dict": 154, "logger": [161, 452, 459, 465], "logic": [421, 425, 443, 477], "logical_cpu": 154, "login": 549, "loglevel": 552, "logo": 533, "long": [225, 476, 520, 527, 547, 551], "long_str": 520, "longer": [209, 225, 418, 483, 551], "longest": [225, 551], "look": [133, 184, 479, 493, 495, 528, 535, 550], "lookup": 173, "loop": [448, 490, 494, 495, 528, 549, 552], "loss": [29, 153, 163, 195, 234, 448, 473, 475, 476, 480, 487, 519, 523, 524, 525, 534, 535, 536, 537, 541, 542, 543, 544, 547, 550, 552], "loss_func": [170, 188], "loss_sum": 536, "loss_typ": [163, 195, 536], "loss_weight": [163, 195, 536], "lossi": [487, 544], "lot": [487, 490, 550], "low": [30, 198, 199, 212, 213, 235, 387, 471, 473, 476, 481, 487, 493, 494, 518, 519, 524, 536, 537, 543, 544, 547, 550, 552], "low_cpu_mem_usag": 418, "low_gpu_mem_usag": [418, 439, 476], "low_memory_usag": 195, "lower": [224, 225, 232, 267, 413, 470, 471, 472, 475, 480, 487, 523, 539, 542, 543, 544, 550, 551, 552], "lowerbitssampl": 277, "lowercas": 209, "lowest": [542, 552], "lp_norm": 425, "lpot": [543, 548], "lr": [195, 418, 439, 451, 476, 524, 536], "lr_schedul": [418, 439, 476, 536, 542], "lstm": 16, "lstmoper": 17, "lvwerra": 553, "lwq": 476, "m": [30, 135, 177, 178, 195, 413, 433, 482, 489, 532, 542, 553], "machin": [154, 227, 476, 480, 483, 526, 532, 543, 550], "maco": 532, "made": [269, 487, 493, 544, 548, 552], "mae": [234, 535], "magnitud": [169, 191, 195, 234, 413, 531, 542], "magnitude_progress": 195, "magnitudecriterion": [169, 191], "mahonei": 542, "mai": [3, 133, 138, 140, 281, 385, 396, 397, 471, 473, 476, 477, 479, 487, 488, 489, 492, 494, 519, 520, 526, 527, 533, 537, 543, 544, 547, 550, 552], "mail": 488, "main": [3, 165, 184, 188, 301, 302, 305, 420, 437, 438, 442, 443, 476, 477, 478, 480, 482, 483, 487, 490, 521, 524, 536, 542, 544, 547], "mainli": [162, 190, 487, 492, 529, 536, 542, 544], "mainstream": [469, 492], "maintain": [234, 475, 476, 480, 487, 488, 489, 520, 538, 542, 547, 548], "mainten": 493, "major": [487, 530, 544, 550], "make": [30, 90, 128, 150, 175, 180, 188, 190, 207, 380, 465, 473, 474, 476, 479, 487, 488, 492, 493, 494, 518, 520, 521, 528, 535, 536, 542, 544, 545, 546, 547, 549, 550, 552], "make_dquant_nod": 30, "make_matmul_weight_only_nod": 31, "make_modul": 1, "make_nam": 90, "make_nc_model": 1, "make_nod": 30, "make_onnx_inputs_output": 90, "make_onnx_shap": 90, "make_quant_nod": 30, "make_sub_graph": 29, "make_symbol_block": 1, "makeiter": [133, 385], "male": 465, "malici": [140, 396], "manag": [152, 448, 454, 536], "mandatori": [198, 199, 262, 536], "mani": [31, 234, 262, 433, 476, 480, 487, 520, 521, 532, 547, 552], "manipul": [87, 88], "manner": [521, 538], "manual": [211, 542], "mao": 519, "map": [1, 30, 90, 133, 140, 145, 160, 195, 225, 229, 231, 232, 234, 396, 427, 442, 456, 458, 476, 487, 492, 520, 524, 535, 536, 542, 544, 547], "map_kei": 234, "map_loc": [140, 396], "map_numpy_to_onnx_dtyp": 90, "map_onnx_to_numpy_typ": 90, "map_point": [230, 234, 535], "map_tensorflow_dtyp": 90, "mar": 543, "mark": 519, "marketplac": [492, 543], "mask": [169, 175, 177, 180, 182, 186, 187, 209, 230, 542, 553], "mask_padding_with_zero": 209, "massiv": 542, "master": [3, 177, 178, 188, 227, 228, 231, 232, 234, 262, 536, 552], "match": [63, 87, 140, 173, 230, 231, 335, 396, 406, 475, 480, 482, 492, 547], "match_datatype_pattern": 145, "math": [51, 323, 487, 544], "mathemat": [474, 479, 487, 550], "matmul": [16, 31, 38, 44, 50, 58, 79, 94, 113, 122, 179, 195, 303, 310, 316, 322, 330, 350, 359, 368, 377, 528, 547, 552], "matmul_weight_only_nod": 31, "matmulfpq4": 31, "matmulnbit": 31, "matmuloper": 18, "matric": [487, 550], "matrix": [31, 234, 262, 479, 487], "matter": [207, 546], "max": [30, 89, 128, 150, 195, 225, 231, 232, 266, 380, 413, 433, 439, 465, 472, 476, 480, 487, 492, 532, 536, 539, 542, 544, 547, 550, 551, 552], "max_answer_length": [225, 551], "max_dim": [225, 551], "max_filter_tensor": 465, "max_grad_norm": 536, "max_inclusive_opset_vers": 89, "max_input_chars_per_word": 224, "max_length": 209, "max_min_data": [74, 75, 346], "max_num_class": 230, "max_ord": 228, "max_output": 490, "max_query_length": [225, 551], "max_seq_length": [209, 225, 420, 551], "max_shard_s": 431, "max_sparsity_ratio_per_op": [175, 180, 195, 536, 542], "max_trial": [153, 195, 473, 481, 536, 552], "max_x": 413, "maxab": [439, 471], "maxabs_hw": [439, 471], "maxabs_hw_opt_weight": 471, "maxabs_pow2": 471, "maxim": [536, 542, 552], "maximum": [40, 153, 175, 180, 195, 209, 225, 228, 243, 266, 312, 390, 413, 425, 431, 476, 487, 495, 519, 536, 542, 544, 550, 551], "maxpool": [16, 114, 123, 297, 369, 378, 528], "maxpooling2d": 297, "maxpooloper": 19, "mbzuai": [474, 550], "mckinstri": 519, "md": [177, 178, 195, 234, 262], "md5": 211, "mean": [29, 31, 175, 184, 195, 221, 225, 232, 234, 271, 413, 425, 431, 441, 471, 476, 478, 487, 490, 494, 495, 521, 524, 528, 535, 536, 542, 544, 545, 547, 550, 551, 552, 553], "mean_valu": [221, 551], "meaning": [536, 541], "meanwhil": 545, "measur": [133, 235, 385, 439, 460, 471, 476, 480, 487, 493, 518, 529, 535, 536, 547, 552], "measure_exclud": [439, 471], "mechan": [138, 169, 397, 469, 542, 549], "media": [488, 543], "median": [125, 283], "medium": [492, 543], "meet": [195, 201, 263, 265, 476, 478, 480, 481, 487, 490, 494, 540, 543, 544, 547, 552], "member": [488, 493], "memomeri": 139, "memori": [59, 145, 245, 331, 413, 433, 465, 471, 472, 473, 474, 476, 477, 479, 482, 487, 519, 521, 523, 536, 537, 539, 540, 542, 544, 545, 547, 550, 552, 553], "mention": [476, 487, 542, 547], "merg": [93, 202, 278, 358, 387, 482, 552], "merge_duplicated_qdq": [91, 356], "mergeduplicatedqdqoptim": [93, 358], "mesa": 527, "messag": [90, 131, 383, 482, 489, 552], "met": [153, 481, 487, 528, 544], "meta": [81, 352, 426, 483, 492, 534, 543, 553], "meta_info": 426, "meta_op_optim": [80, 351], "metaclass": 274, "metadata": [140, 396], "metagraphdef": [243, 390], "metainfochangingmemopoptim": [81, 352], "metal": [492, 527, 532], "metaop": [81, 352], "meteor": 532, "method": [31, 126, 128, 138, 140, 145, 189, 195, 203, 207, 208, 209, 211, 218, 225, 278, 280, 286, 380, 392, 396, 397, 417, 431, 441, 454, 459, 461, 462, 471, 476, 477, 478, 480, 487, 490, 492, 519, 520, 521, 523, 535, 536, 541, 542, 544, 546, 547, 550, 551, 552], "meticul": [472, 539], "metric": [153, 162, 195, 198, 199, 226, 235, 262, 448, 454, 469, 479, 493, 494, 524, 536, 537, 544, 549, 550, 552, 553], "metric_cl": [234, 262, 536], "metric_criterion": 245, "metric_fn": [231, 232], "metric_max_over_ground_truth": [231, 232], "metric_registri": 234, "metric_typ": 234, "metric_weight": 245, "mha": [176, 183, 542], "mha_compress": 184, "mha_head_s": 184, "mha_modul": 184, "mha_nam": 184, "mha_scor": 184, "mha_spars": [171, 542], "mhacompress": 184, "microcod": 553, "microsc": 477, "microsoft": [3, 472, 492, 493, 539], "middl": [487, 550], "migacz": 519, "might": [192, 473, 490, 520, 552], "migrat": [469, 474, 479, 487, 550], "mimic": [487, 544], "min": [128, 150, 195, 380, 433, 465, 472, 476, 480, 487, 539, 542, 544, 547, 550, 551, 552], "min_dim": [225, 551], "min_filter_tensor": 465, "min_max": 425, "min_sparsity_ratio_per_op": [175, 195, 536, 542], "min_train_sampl": 195, "min_x": 413, "mini": 553, "minilm": [543, 553], "minim": [128, 150, 266, 380, 471, 475, 476, 480, 487, 494, 495, 519, 525, 535, 536, 542, 544, 552], "minimum": [175, 195, 413, 425, 472, 495, 519, 536, 539, 542, 550, 552], "minmax": [1, 3, 303, 409, 413, 439, 475, 494, 495, 519, 528, 544], "minmax_file_path": 465, "minmax_lr": [418, 439, 451, 476], "minmaxcalibr": 3, "miou": 234, "misc": [138, 397, 533], "miss": [487, 542, 544], "mistral": 534, "mistralai": 534, "mitig": [476, 547], "mix": [134, 195, 235, 264, 278, 400, 437, 439, 469, 477, 492, 493, 499, 529, 531], "mix_precis": [195, 226, 281, 536, 537], "mixed_precis": [235, 394, 536], "mixed_precision_entri": 437, "mixed_precision_model": 134, "mixedprecis": [195, 536], "mixedprecisionconfig": [195, 235, 281, 437, 439, 473, 536, 537], "mixin": 451, "mixprecisionconfig": 437, "ml": 543, "mla": [493, 537, 544], "mleffici": 543, "mlp": [477, 542], "mlperf": [543, 553], "mm": 553, "mnist": [211, 524], "mnli": [209, 535, 553], "mobil": [536, 553], "mobilebert": 209, "mobilenet": [526, 549, 553], "mobilenetv2": 553, "mobiusml": [439, 476], "mod": 427, "mod_dict": 439, "mode": [28, 29, 30, 95, 140, 157, 161, 218, 230, 243, 278, 360, 390, 396, 404, 413, 437, 439, 442, 447, 464, 465, 471, 476, 477, 493, 494, 531, 544, 546, 547, 552], "model": [1, 2, 3, 16, 28, 29, 30, 31, 33, 34, 35, 36, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 54, 56, 57, 58, 59, 60, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 73, 74, 75, 76, 77, 78, 79, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 92, 93, 94, 101, 103, 125, 126, 127, 133, 134, 135, 139, 140, 141, 143, 144, 145, 149, 151, 153, 156, 162, 170, 171, 173, 180, 181, 182, 185, 187, 188, 190, 192, 195, 198, 199, 205, 208, 209, 211, 225, 226, 234, 235, 245, 256, 260, 261, 262, 263, 264, 266, 267, 271, 273, 274, 280, 281, 283, 286, 288, 301, 302, 305, 306, 307, 308, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 326, 328, 329, 330, 331, 332, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 345, 346, 347, 348, 349, 350, 352, 353, 354, 355, 357, 358, 359, 385, 388, 390, 391, 392, 396, 398, 406, 408, 411, 412, 413, 415, 417, 420, 431, 432, 433, 435, 437, 438, 441, 442, 447, 448, 449, 456, 457, 458, 461, 464, 465, 467, 469, 470, 471, 472, 473, 476, 477, 478, 479, 480, 483, 487, 489, 490, 493, 495, 499, 518, 519, 520, 521, 523, 524, 525, 529, 530, 531, 533, 535, 537, 540, 541, 543, 544, 548, 549, 551, 552], "model_attr": 156, "model_forward": [413, 433], "model_forward_per_sampl": 413, "model_info": 439, "model_level": 156, "model_loss": 552, "model_nam": [101, 195, 492], "model_name_or_path": [209, 431, 441, 492, 536, 545], "model_origin": [195, 262, 546], "model_path": [125, 133, 283, 385, 420, 439, 476], "model_proto": 90, "model_slim": [170, 184], "model_slim_ffn2": 171, "model_slim_mha": 171, "model_state_dict_path": [476, 483], "model_typ": [209, 465], "model_wis": 536, "model_wrapp": [2, 136, 388], "modelproto": [31, 235, 456, 538], "models": [195, 245, 536, 540], "modelwisetuningsampl": 277, "modern": [476, 487, 547], "modif": [489, 493, 528], "modifi": [184, 211, 261, 280, 471, 490, 495, 524, 528, 542], "modified_pickl": [137, 395], "modul": [136, 137, 155, 158, 170, 176, 183, 395, 407, 410, 414, 424, 428, 434, 446, 469, 471, 473, 476, 477, 481, 490, 492, 500, 520, 521, 529, 531, 535, 536, 538, 542, 546, 547], "module_debug_level1": 281, "module_hook_config": [145, 433], "module_nam": [141, 161, 169, 170, 180, 181, 182, 183, 185, 186, 187, 189, 191, 398, 465], "module_name_list": [145, 433], "module_node_map": 458, "module_typ": 420, "module_wrapp": 400, "modulelist": 420, "mold": 153, "momentum": [169, 531, 536, 542], "momentumbalanc": 553, "momentumunbalanc": 553, "monitor": [153, 442, 477], "more": [29, 133, 149, 156, 177, 178, 225, 385, 413, 439, 469, 471, 472, 473, 474, 476, 477, 480, 487, 491, 492, 494, 519, 520, 524, 526, 531, 532, 534, 536, 537, 539, 540, 541, 542, 546, 547, 550, 552, 553], "mosaicml": [474, 550, 553], "mose": 227, "mosesdecod": 227, "mosh": 542, "most": [195, 234, 471, 473, 476, 480, 487, 536, 537, 542, 544, 547, 550, 552, 553], "mostli": 520, "move": [63, 140, 335, 396, 413, 433, 476, 487, 490, 547, 548], "move_input_devic": 145, "move_input_to_devic": [413, 433], "move_squeeze_after_relu": [61, 333], "movesqueezeafterreluoptim": [63, 335], "mp": 480, "mpi": 552, "mpirun": 552, "mpt": [474, 542, 550, 553], "mrpc": [209, 234, 535, 542, 552, 553], "mscoco": 230, "mse": [31, 145, 195, 234, 262, 270, 465, 476, 487, 535, 547, 548], "mse_metric_gap": 465, "mse_v2": [195, 270], "mse_v2tunestrategi": 272, "mseloss": [487, 550], "msetunestrategi": 271, "msfp": [472, 539], "msft": 543, "msg": 462, "mt": 553, "mteval": 227, "much": [162, 169, 195, 225, 487, 550, 551], "mul": [40, 50, 51, 54, 149, 312, 322, 323, 326, 476, 526, 547, 550], "mullinear": [142, 429], "multi": [151, 154, 171, 173, 184, 230, 234, 262, 482, 521, 531, 536, 540, 542, 544, 552], "multi_object": 540, "multiclass": 535, "multilabel": 535, "multilingu": 553, "multiobject": 245, "multipl": [152, 165, 171, 196, 197, 201, 202, 209, 210, 212, 213, 214, 215, 216, 220, 222, 225, 235, 236, 237, 239, 245, 480, 518, 526, 529, 536, 541, 542, 549, 550, 552], "multipli": [3, 195, 470, 472, 476, 539, 547], "must": [225, 230, 451, 489, 490, 494, 518, 521, 532, 544, 551], "mx": [1, 402, 404, 439, 472, 477, 492, 529, 539], "mx_quant": 394, "mx_quant_entri": 437, "mx_spec": [403, 404], "mxfp4": [472, 539], "mxfp6": [472, 539], "mxfp8": [472, 539], "mxint8": [472, 539], "mxlinear": 403, "mxnet": [0, 1, 3, 195, 204, 208, 211, 214, 218, 225, 234, 235, 240, 262, 493, 494, 519, 521, 525, 528, 531, 536, 537, 538, 552], "mxnet_model": 237, "mxnetcifar10": 211, "mxnetcifar100": 211, "mxnetcropresizetransform": 225, "mxnetcroptoboundingbox": 225, "mxnetdataload": 204, "mxnetdataset": 211, "mxnetfashionmnist": 211, "mxnetfilt": 218, "mxnetimagefold": 211, "mxnetimagenetraw": 214, "mxnetmetr": 234, "mxnetmnist": 211, "mxnetmodel": 240, "mxnetnormalizetransform": 225, "mxnettransform": 225, "mxnettranspos": 225, "mxquantconfig": [437, 439, 472, 539], "mxquantiz": 403, "my": 489, "mydataload": [478, 480, 481], "n": [177, 178, 195, 210, 225, 228, 281, 487, 495, 520, 534, 542, 544, 550, 551], "n_best_siz": [225, 551], "n_bit": [487, 550], "n_block": [476, 547], "n_gpu": 536, "n_iter": 266, "n_sampl": [31, 145, 413, 451, 476], "n_warmup": 266, "na": [195, 239, 480, 531, 553], "name": [1, 30, 39, 52, 53, 55, 89, 90, 95, 101, 125, 133, 135, 140, 141, 144, 145, 146, 151, 152, 153, 156, 160, 166, 169, 173, 175, 180, 183, 184, 188, 189, 190, 191, 192, 194, 195, 209, 210, 211, 214, 218, 223, 225, 229, 234, 239, 243, 245, 262, 278, 280, 283, 292, 293, 297, 311, 324, 325, 327, 360, 385, 390, 391, 396, 398, 403, 412, 413, 417, 418, 420, 427, 433, 439, 442, 443, 445, 447, 452, 454, 456, 457, 458, 465, 471, 472, 475, 476, 477, 478, 489, 490, 495, 520, 524, 526, 528, 533, 535, 536, 538, 539, 542, 544, 548, 549, 552, 553], "namecollector": 1, "named_paramet": 524, "namespac": 520, "namhoon": 542, "nan": [41, 313], "narrow": [472, 539], "narrow_rang": 98, "nasconfig": 195, "nation": [211, 488], "nativ": 495, "natur": [227, 476, 526], "nbest_predict": [225, 551], "nbit": 426, "nblock": [418, 439], "nbsp": [552, 553], "nc": [549, 552], "nc_model": 1, "nc_resnet50_v1": 524, "nc_workspac": 195, "nchw": [39, 221, 311], "ncmodel": 1, "ndarrai": [1, 29, 30, 52, 53, 55, 225, 324, 325, 327, 452, 527, 551], "ndarray_to_devic": 1, "nearest": [173, 225, 439, 476, 477, 487, 547, 551], "nearst": 31, "necessari": [30, 188, 488, 494, 538, 542, 549, 552], "necessarili": [138, 397], "need": [1, 29, 90, 94, 151, 156, 173, 188, 195, 198, 199, 200, 207, 208, 211, 218, 225, 234, 235, 245, 262, 271, 359, 387, 404, 411, 413, 431, 441, 448, 458, 464, 465, 476, 479, 481, 483, 487, 490, 493, 520, 521, 524, 527, 531, 536, 542, 544, 545, 546, 547, 548, 550, 551, 552], "need_appli": [305, 442], "need_spac": 413, "neelnanda": [418, 451], "neither": 544, "neo": [529, 553], "neox": [534, 553], "nepoch": 536, "nest": [145, 391, 417, 465], "nesterov": 536, "net": [241, 391, 492], "netflix": 543, "nets_factori": 237, "network": [135, 169, 175, 176, 269, 439, 472, 473, 487, 519, 523, 526, 536, 539, 543, 544, 550, 552], "neural": [1, 135, 151, 154, 162, 165, 175, 176, 177, 178, 188, 195, 221, 222, 225, 226, 233, 234, 235, 239, 246, 262, 269, 270, 276, 290, 302, 303, 304, 305, 389, 392, 394, 436, 437, 438, 439, 440, 441, 442, 444, 445, 446, 447, 449, 451, 455, 467, 469, 471, 472, 473, 474, 475, 476, 477, 478, 480, 481, 482, 484, 487, 489, 493, 494, 495, 518, 519, 520, 522, 523, 524, 525, 526, 527, 528, 529, 530, 533, 534, 537, 538, 539, 540, 541, 543, 544, 547, 548, 550, 551, 552, 553], "neural_compressor": [470, 471, 472, 473, 474, 475, 476, 477, 478, 479, 480, 481, 483, 490, 492, 495, 518, 520, 521, 523, 524, 526, 529, 530, 535, 536, 537, 538, 539, 540, 541, 542, 544, 545, 546, 548, 549, 550, 551, 552], "neurip": 543, "neuron": 542, "never": [140, 396, 552], "nevertheless": [472, 539], "new": [1, 3, 31, 133, 151, 200, 211, 225, 245, 385, 387, 392, 413, 433, 443, 451, 469, 473, 474, 475, 476, 487, 489, 494, 524, 536, 537, 542, 543, 544, 547, 548, 549, 551], "new_api": [33, 34, 56, 57, 62, 64, 77, 84, 116, 121, 128, 306, 328, 329, 334, 336, 348, 371, 376, 380], "new_dtyp": 30, "new_func": [133, 385], "new_graph_def": [133, 385], "new_init": 31, "new_metr": 535, "new_modul": [141, 145, 398, 413, 433, 447], "new_quantized_nam": 30, "newapi": [79, 350], "newdataload": 521, "newli": [536, 542], "newlin": [232, 465], "newmetr": 535, "next": [45, 203, 281, 317, 387, 476, 487, 492, 494, 495, 521, 547, 552], "next_annotation_id": 230, "next_tune_cfg": 552, "nextplatform": 543, "nf4": [433, 476, 547], "nfl": 232, "ngram": [227, 535], "nhwc": [39, 221, 311], "ni_workload_nam": 195, "ninm": 176, "nll_loss": 524, "nlp": [188, 195, 473, 477, 480, 487, 542, 544], "nn": [141, 142, 145, 173, 174, 184, 194, 195, 235, 262, 398, 408, 412, 413, 417, 420, 427, 429, 431, 433, 435, 437, 438, 441, 442, 447, 458, 461, 464, 471, 476, 477, 487, 490, 536, 538, 547, 550], "nncf": 135, "no_absorb_lay": [145, 433], "node": [1, 29, 30, 31, 35, 39, 40, 41, 42, 45, 47, 49, 52, 53, 55, 59, 62, 65, 67, 68, 69, 83, 87, 88, 90, 95, 117, 125, 133, 154, 173, 243, 261, 283, 307, 311, 312, 313, 314, 317, 319, 321, 324, 325, 327, 331, 334, 337, 339, 340, 341, 354, 360, 372, 385, 390, 406, 413, 433, 443, 456, 458, 482, 493, 524, 545, 552, 553], "node1": 524, "node2": 524, "node_candidate_list": 406, "node_collector": 135, "node_def": [52, 53, 55, 324, 325, 327], "node_from_map": [52, 53, 55, 324, 325, 327], "node_index": 154, "node_list": 406, "node_map": [52, 53, 55, 324, 325, 327], "node_nam": [52, 53, 55, 133, 243, 251, 324, 325, 327, 390, 494], "node_name_from_input": [52, 53, 55, 324, 325, 327], "node_name_list": [131, 383], "node_op": 494, "node_set_from_user_config": 406, "nodedef": [52, 53, 55, 324, 325, 327], "non": [3, 465, 471, 473, 476, 490, 547, 552], "nondigit_punct_r": 227, "none": [1, 28, 30, 31, 32, 33, 34, 48, 74, 87, 89, 90, 95, 101, 127, 133, 135, 139, 140, 141, 142, 145, 151, 152, 153, 156, 161, 162, 163, 169, 170, 171, 173, 177, 188, 192, 195, 198, 199, 200, 202, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 216, 221, 225, 230, 234, 235, 245, 256, 260, 261, 262, 263, 264, 266, 267, 271, 273, 274, 278, 281, 284, 288, 289, 292, 293, 294, 297, 298, 299, 301, 302, 303, 305, 306, 320, 346, 360, 385, 387, 391, 392, 396, 398, 403, 404, 405, 413, 417, 418, 420, 423, 426, 429, 431, 432, 433, 435, 438, 439, 441, 442, 447, 448, 451, 452, 454, 457, 458, 461, 464, 465, 471, 472, 476, 477, 480, 482, 492, 493, 494, 521, 535, 539, 544, 547, 551, 552], "nor": 544, "norm": [16, 476], "normal": [3, 20, 225, 232, 476, 487, 536, 540, 547, 550, 551], "normalfloat": [476, 547], "normalizationoper": 20, "normalize_answ": 232, "normalizetftransform": 225, "normalizetransform": 225, "not_use_best_ms": [418, 439, 476], "notat": [195, 465], "note": [40, 138, 153, 179, 230, 272, 312, 392, 397, 469, 470, 471, 473, 474, 475, 476, 479, 482, 487, 492, 494, 495, 520, 521, 524, 526, 528, 529, 532, 534, 536, 542, 544, 547, 550, 552], "notebook": 469, "noteworthi": 519, "noth": [230, 552], "notic": [128, 150, 380, 473, 476, 533, 537, 548], "notimplementederror": 447, "nov": 543, "novel": 523, "now": [195, 225, 490, 495, 524, 551, 552], "np": [30, 225, 266, 524, 550, 551, 552], "np_dtype": 90, "npu": [195, 544], "npy": 210, "npy_dir": 210, "npz": 211, "nr": 90, "nsampl": [418, 420, 439, 547], "nsdf3": 211, "nuanc": 476, "num": [433, 465], "num_bin": [1, 3, 452], "num_bit": [31, 98, 142, 145, 413, 429, 487, 550], "num_c": 482, "num_class": 234, "num_cor": [209, 210, 214], "num_cores_on_numa": 482, "num_cores_per_inst": [154, 482], "num_correct": 234, "num_cpu": 154, "num_detect": [230, 234, 535, 536], "num_gt_box": 230, "num_i": 482, "num_inst": [154, 482], "num_of_inst": [151, 195, 518, 536], "num_of_process": 524, "num_quantized_bin": 3, "num_replica": 524, "num_sampl": 234, "num_train_epoch": [536, 542], "num_work": [200, 202, 205, 206, 208, 387, 521, 536, 544], "numa": [154, 482], "numa_index": 154, "numa_info": 154, "numa_node_index": 154, "numactl": [151, 154, 527], "number": [3, 31, 52, 53, 90, 125, 145, 152, 153, 161, 171, 177, 178, 195, 207, 210, 221, 225, 231, 232, 234, 257, 261, 266, 281, 283, 324, 325, 387, 413, 418, 426, 433, 443, 454, 465, 470, 476, 481, 482, 487, 518, 521, 524, 535, 542, 544, 547, 549, 550, 551, 552], "number_of_process": 552, "numer": [195, 234, 472, 473, 476, 480, 495, 537, 539, 543, 544, 547], "numpi": [29, 30, 52, 53, 55, 90, 133, 225, 230, 324, 325, 327, 527, 550, 551], "nvidia": [492, 519, 531, 532, 553], "nxm": [176, 186, 195, 542], "o": [140, 281, 396, 492, 520, 532], "o0": [267, 552], "o1": 552, "obj": [1, 90, 170, 192, 208, 235, 245, 262, 448, 454, 465], "obj1": 465, "obj2": 465, "obj_cl": 245, "obj_criterion": 245, "obj_weight": 245, "object": [1, 29, 30, 31, 59, 71, 90, 101, 117, 133, 134, 135, 138, 140, 144, 145, 151, 153, 160, 162, 169, 170, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 195, 198, 199, 200, 209, 210, 211, 225, 226, 230, 234, 235, 243, 244, 257, 261, 262, 266, 280, 331, 343, 372, 385, 387, 390, 391, 396, 397, 399, 406, 409, 411, 413, 417, 433, 447, 448, 451, 454, 464, 465, 469, 475, 477, 480, 490, 494, 499, 518, 520, 521, 527, 535, 536, 538, 541, 542, 544, 551, 552, 553], "object_detect": [195, 230], "objective_cfg": 245, "objective_cl": 245, "objective_custom_registri": 245, "objective_registri": 245, "oblig": 488, "observ": [145, 417, 439, 442, 470, 471, 475, 476, 477, 495, 547, 549, 552], "obstacl": [472, 539], "obtain": [171, 173, 182, 187, 189, 192, 487, 490, 494, 542, 549, 550, 552], "occupi": [472, 539], "occur": 475, "ocp": [472, 539], "oct": 543, "off": [3, 52, 53, 55, 324, 325, 327, 476, 487, 489, 547], "offens": 488, "offer": [472, 476, 480, 539], "offici": [133, 227, 231, 232, 385, 488, 550], "offlin": [465, 474, 479, 480, 487, 488, 536, 544, 550], "offset_height": [225, 551], "offset_width": [225, 551], "ofir": 542, "often": [192, 476, 521, 541, 542], "old": [391, 465, 474, 536, 548], "old_hist": [391, 465], "oliv": [492, 543], "omit": [471, 547], "omp_num_thread": 483, "ompi_mca_btl_vader_single_copy_mechan": 492, "on_after_compute_loss": [448, 523, 536, 541], "on_after_optimizer_step": [536, 542], "on_before_optimizer_step": [448, 523, 536, 541, 542], "on_epoch_begin": [448, 454, 523, 536, 541], "on_epoch_end": [448, 454, 523, 536, 541], "on_step_begin": [448, 454, 523, 536, 541, 542], "on_step_end": [448, 454, 523, 536, 541], "on_train_begin": [448, 490, 523, 536, 541, 542, 544], "on_train_end": [448, 523, 536, 541, 542, 544], "onc": [133, 140, 165, 190, 263, 265, 385, 396, 480, 494, 495, 521, 542, 543, 552, 553], "one": [31, 94, 95, 100, 140, 145, 151, 175, 179, 184, 187, 188, 190, 225, 227, 230, 234, 359, 360, 396, 413, 417, 433, 473, 476, 477, 480, 481, 482, 487, 493, 519, 523, 524, 528, 531, 532, 535, 536, 537, 540, 541, 542, 544, 545, 547, 548, 550, 551, 552], "oneapi": [469, 473, 532, 543], "onednn": [473, 480, 537, 544], "onednn_max_cpu_isa": 473, "ones": [140, 230, 396, 542], "oneshotschedul": 190, "onli": [29, 31, 39, 48, 55, 71, 94, 100, 128, 140, 149, 150, 151, 165, 170, 176, 183, 195, 209, 262, 272, 280, 281, 311, 320, 327, 343, 359, 380, 396, 413, 428, 429, 431, 432, 433, 439, 441, 458, 465, 469, 471, 473, 477, 481, 482, 493, 494, 495, 518, 519, 520, 521, 524, 527, 528, 529, 534, 536, 537, 542, 543, 544, 545, 550, 552], "onlin": [476, 488, 549], "onnx": [2, 3, 16, 28, 30, 31, 72, 127, 149, 195, 205, 235, 242, 257, 456, 457, 458, 463, 489, 492, 493, 494, 496, 521, 525, 526, 528, 531, 537, 538, 539, 543, 547, 550, 552], "onnx_graph": 86, "onnx_ml_pb2": [235, 538], "onnx_model": [237, 256], "onnx_nod": [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 86], "onnx_qlinear_to_qdq": 456, "onnx_quant": [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27], "onnx_schema": 86, "onnx_typ": 90, "onnxbilinearimagenettransform": 221, "onnxcommunitymeetup2023": 543, "onnxgraph": 87, "onnxmodel": [31, 242, 256], "onnxnod": 88, "onnxopschema": 89, "onnxprofilingpars": 249, "onnxqlinear2qdq": 195, "onnxqlinear2qdqconfig": 195, "onnxresizecropimagenettransform": 221, "onnxrt": [29, 30, 31, 209, 211, 218, 225, 234, 256, 463, 493, 537, 544, 553], "onnxrt_cuda_ep": [195, 537, 544], "onnxrt_dataload": 256, "onnxrt_dml_ep": [195, 544], "onnxrt_dnnl_ep": [195, 537, 544], "onnxrt_integ": 536, "onnxrt_integerop": [211, 218, 225], "onnxrt_qdq": [211, 218], "onnxrt_qlinear": 536, "onnxrt_qlinearop": [211, 218, 225], "onnxrt_qlinearopsadaptor": 493, "onnxrt_trt_ep": [195, 537, 544], "onnxrtaug": 2, "onnxrtbertdataload": 205, "onnxrtbertdataset": 209, "onnxrtcroptoboundingbox": 225, "onnxrtdataload": [205, 256], "onnxrtglu": 234, "onnxrtimagenetdataset": 214, "onnxrtitdataset": 211, "onnxrtitfilt": 218, "onnxrtitmetr": 234, "onnxrtittransform": 225, "onnxrtparserfactori": 248, "onnxrtqldataset": 211, "onnxrtqlfilt": 218, "onnxrtqlmetr": 234, "onnxrtqltransform": 225, "onnxruntim": [3, 195, 205, 211, 218, 257, 493, 519, 521, 531, 532, 537], "onto": [140, 396], "op": [1, 16, 36, 38, 50, 51, 52, 53, 54, 55, 56, 57, 59, 63, 66, 70, 73, 76, 77, 78, 79, 81, 90, 92, 94, 108, 109, 110, 116, 118, 119, 120, 121, 126, 128, 131, 133, 135, 144, 145, 149, 173, 195, 257, 261, 267, 269, 271, 278, 279, 280, 286, 308, 310, 322, 323, 324, 325, 326, 327, 328, 329, 331, 335, 338, 342, 345, 347, 348, 349, 350, 352, 357, 359, 363, 364, 365, 371, 373, 374, 375, 376, 380, 383, 385, 412, 413, 417, 433, 437, 447, 456, 458, 460, 465, 473, 474, 477, 487, 493, 494, 495, 528, 536, 537, 542, 544, 546, 548, 550, 552], "op_block_lst": 277, "op_cfg": 139, "op_defin": 251, "op_dict": 536, "op_dtyp": 277, "op_dtype_dict": 277, "op_infos_from_cfg": [145, 412, 413, 417], "op_level": 156, "op_list": 493, "op_nam": [145, 195, 279, 413, 417, 433, 447, 465, 466, 475, 494, 536, 542], "op_name_dict": [195, 475, 536, 544, 552], "op_name_or_module_typ": [152, 299, 303, 439], "op_name_typ": 278, "op_quant_mod": 279, "op_registri": 21, "op_run": 251, "op_typ": [21, 125, 126, 133, 194, 279, 283, 286, 303, 413, 417, 474, 475], "op_type_dict": [195, 475, 495, 544, 547, 552], "op_type_level": 156, "op_types_to_quant": 28, "op_user_cfg": 280, "op_user_cfg_modifi": 280, "op_wis": 536, "op_wise_config": [92, 116, 121, 357, 371, 376, 494], "op_wise_sequ": [116, 121, 371, 376], "open": [140, 226, 396, 454, 467, 488, 492, 526, 527, 536, 543], "openai": [474, 550], "opencv": 527, "opentri": 465, "openvinotoolkit": 135, "oper": [4, 30, 89, 95, 125, 133, 152, 156, 173, 174, 179, 195, 221, 257, 261, 283, 299, 360, 385, 406, 413, 470, 471, 473, 474, 475, 476, 477, 478, 479, 480, 487, 490, 518, 521, 526, 542, 544, 547, 550, 551, 552], "operator_name_or_list": 477, "operatorconfig": [299, 439], "ops_lst": [145, 417], "ops_nam": [145, 417], "opset": [29, 87, 89, 90, 195, 457, 458, 526], "opset_vers": [90, 127, 195, 457, 458, 526], "opt": [188, 474, 487, 492, 534, 542, 550, 552, 553], "opt_cfg": [60, 332], "opt_model": [470, 475, 536], "opt_param": 425, "optdecoderlay": 550, "optim": [39, 59, 60, 64, 65, 101, 103, 133, 164, 167, 168, 170, 173, 182, 187, 195, 266, 311, 331, 332, 336, 337, 385, 424, 439, 448, 450, 452, 465, 469, 475, 476, 479, 480, 481, 483, 487, 492, 518, 520, 523, 524, 528, 531, 532, 534, 536, 538, 543, 544, 546, 547, 549, 550, 552], "optimize_lay": 102, "optimize_qdq": [115, 370], "optimize_weights_proximal_legaci": 425, "optimized_model_tensor": 465, "optimized_tensor_data": 466, "optimizedmodel": 461, "optimizeqdqgraph": [116, 371], "optimizer_registri": 165, "optimizer_typ": 165, "optimum": [471, 547], "option": [3, 31, 90, 140, 145, 156, 161, 175, 195, 198, 199, 209, 225, 230, 234, 235, 262, 278, 280, 281, 391, 392, 396, 398, 408, 409, 413, 415, 418, 425, 431, 433, 435, 437, 438, 439, 441, 442, 447, 448, 457, 458, 459, 461, 465, 476, 477, 480, 487, 494, 495, 520, 521, 528, 532, 536, 542, 544, 547, 549, 550, 551, 552], "optuningconfig": [277, 278, 279], "optyp": [1, 195, 456, 494], "optype_wise_": 494, "optypes_to_exclude_output_qu": [28, 195, 544], "optypewis": 494, "optypewisetuningsampl": 277, "opwis": 494, "opwisetuningsampl": 277, "orchestr": [448, 469, 531], "order": [139, 145, 153, 227, 228, 266, 271, 280, 476, 481, 487, 490, 535, 547, 550, 552], "ordered_op": 145, "ordereddefaultdict": 280, "ordereddict": [403, 412, 416, 419, 430, 520], "ordinari": 549, "org": [169, 187, 230, 420, 439, 490, 492, 532, 542], "orient": 488, "orig_answer_text": 225, "orig_lay": [142, 429], "orig_model": 476, "orig_sav": 477, "orig_text": 225, "origin": [30, 31, 125, 133, 141, 145, 173, 185, 192, 195, 209, 225, 267, 280, 283, 385, 398, 413, 427, 431, 433, 441, 442, 461, 465, 476, 477, 478, 480, 487, 489, 542, 544, 547, 551, 552], "original_model": [431, 441, 476], "ort": 257, "ortsmoothqu": 29, "other": [52, 53, 55, 138, 149, 208, 232, 243, 324, 325, 327, 390, 397, 413, 472, 477, 480, 487, 488, 490, 494, 495, 500, 520, 528, 529, 531, 533, 536, 538, 539, 540, 542, 544, 550, 551, 552, 553], "otherwis": [140, 211, 225, 396, 406, 413, 427, 451, 465, 476, 488, 494, 547, 551], "ouput_dir": 545, "our": [128, 145, 195, 380, 413, 472, 492, 526, 536, 539, 549], "out": [178, 195, 209, 210, 211, 412, 413, 476, 478, 480, 487, 489, 490, 492, 542, 544, 547], "out_dtyp": 439, "out_featur": [403, 423, 429], "out_graph_def": [133, 385], "out_graph_fil": [133, 385], "outcom": 234, "outer": [202, 387], "outlier": [125, 283, 474, 476, 479, 487, 494, 519, 547, 550], "outlin": [494, 495], "outofcheeseerror": 520, "outperform": 476, "output": [29, 30, 31, 36, 39, 44, 59, 83, 90, 95, 133, 145, 166, 173, 174, 179, 192, 195, 198, 199, 227, 234, 235, 243, 262, 308, 311, 316, 331, 354, 360, 385, 390, 391, 408, 413, 415, 417, 425, 431, 433, 439, 442, 448, 457, 458, 461, 462, 465, 471, 476, 477, 478, 487, 490, 493, 494, 523, 524, 526, 528, 530, 535, 536, 538, 541, 542, 544, 547, 550, 551, 552], "output_data": 29, "output_dict": 31, "output_dir": [139, 408, 415, 431, 461, 477, 536], "output_fn": 225, "output_func": [145, 433], "output_graph": 195, "output_graph_def": 479, "output_handl": [161, 465], "output_index_map": [234, 535], "output_mod": 209, "output_model": [281, 536], "output_nam": [87, 127, 195, 243, 390, 457, 458, 526], "output_node_nam": [68, 69, 116, 117, 121, 133, 340, 341, 371, 372, 376, 385], "output_path": 230, "output_process": 166, "output_shap": 87, "output_tensor": [133, 243, 385, 390], "output_tensor_id_op_nam": [412, 413, 417], "output_tensor_ids_op_nam": [145, 413, 417], "output_tensor_nam": [133, 243, 385, 390], "output_valu": [145, 433], "outputs_to_valu": 90, "over": [90, 140, 211, 234, 396, 494, 525, 531, 535, 542, 550, 552], "overal": [476, 495, 547], "overflow": [487, 544], "overhead": [476, 550], "overli": 520, "overrid": [195, 465, 477, 520], "overridden": 552, "overview": [492, 529, 552], "overwrit": 211, "overwrite_exist": 151, "own": [59, 140, 207, 225, 245, 331, 396, 469, 487, 494, 521, 531, 535, 540, 547, 549], "p": [3, 476, 483, 487, 547], "p_conf": [536, 541], "pack": [30, 46, 318, 421, 426], "packag": [89, 445, 492, 493, 520, 527, 532, 543, 548, 552], "package_nam": 445, "packer": 421, "pad": [16, 31, 56, 57, 209, 225, 292, 294, 297, 298, 328, 329, 551], "pad_max_length": 547, "pad_tensor": 31, "pad_token": 209, "pad_token_segment_id": 209, "paddedcentercroptransform": 225, "padding_mod": 551, "pade": 31, "padoper": 22, "page": [488, 489], "pager": 520, "pain": [487, 544], "pair": [92, 195, 357, 406, 473, 475, 494, 521, 536, 537], "paper": [474, 476, 487, 542, 547, 550], "paragraph": [231, 232], "parallel": [210, 257, 261, 536, 552], "param": [145, 151, 154, 156, 165, 200, 234, 266, 387, 465, 471, 493, 538, 552], "param1": 281, "param2": 281, "param3": 281, "param_alia": 465, "param_dict": [163, 165], "param_nam": [398, 465], "paramet": [1, 3, 29, 30, 31, 52, 53, 55, 71, 90, 101, 117, 125, 126, 133, 134, 135, 140, 141, 144, 145, 146, 151, 152, 153, 154, 156, 160, 161, 162, 163, 165, 167, 169, 170, 171, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 194, 195, 198, 199, 208, 209, 211, 218, 221, 225, 227, 228, 230, 231, 232, 234, 235, 239, 243, 245, 257, 261, 262, 266, 274, 278, 280, 281, 283, 286, 301, 305, 324, 325, 327, 343, 372, 385, 390, 391, 396, 398, 404, 406, 408, 409, 411, 412, 413, 415, 417, 418, 420, 422, 425, 427, 431, 433, 435, 437, 438, 439, 441, 442, 443, 445, 447, 448, 454, 456, 457, 458, 461, 462, 464, 465, 472, 474, 475, 476, 479, 480, 482, 487, 490, 494, 521, 524, 531, 535, 536, 539, 542, 544, 545, 547, 549, 550, 551, 552], "parameter": 542, "parameter1": 281, "parameter2": 281, "paramlevel": 156, "params_list": [152, 156], "parent": [185, 186, 190, 413, 433], "pars": [90, 133, 145, 154, 209, 210, 221, 225, 249, 250, 253, 385, 390, 412, 413, 417, 494, 495, 551], "parse_auto_slim_config": [171, 542], "parse_cfg": 417, "parse_last_linear": 192, "parse_last_linear_tf": 192, "parse_saved_model": [133, 385], "parse_str2list": 154, "parse_to_prun": 192, "parse_to_prune_tf": 192, "parse_tune_config": 1, "parse_valid_pruner_typ": 183, "parsedecodebert": 209, "parsedecodecoco": 210, "parsedecodeimagenet": [221, 551], "parsedecodeimagenettransform": 221, "parsedecodevoctransform": 225, "parserfactori": 247, "part": [145, 171, 180, 433, 469, 473, 487, 490, 532, 537, 542, 545, 550], "parti": [230, 487, 489, 533, 544], "partial": [184, 480, 542, 544], "particip": 488, "particular": [492, 542, 547], "particularli": 480, "partit": [524, 542], "partner": 543, "parzen": 552, "pascal": 211, "paser_cfg": 145, "pass": [62, 133, 138, 140, 151, 161, 234, 262, 334, 385, 391, 396, 397, 411, 413, 431, 441, 464, 465, 476, 487, 489, 490, 493, 518, 523, 524, 530, 535, 536, 542, 544, 546, 550], "past": [476, 487, 493, 547], "pat": 543, "patch": 427, "patch_hqq_moduil": 427, "path": [90, 125, 133, 141, 145, 160, 173, 188, 192, 209, 210, 211, 225, 235, 243, 261, 262, 278, 283, 385, 390, 398, 405, 412, 413, 415, 416, 417, 431, 442, 457, 458, 461, 465, 471, 475, 476, 477, 483, 490, 493, 524, 530, 535, 536, 537, 538, 541, 547, 551], "path_to_sav": 448, "pathlik": [140, 396], "pattern": [43, 44, 46, 63, 81, 92, 93, 94, 116, 121, 145, 169, 170, 173, 174, 180, 181, 182, 183, 185, 187, 189, 195, 211, 278, 315, 316, 318, 335, 352, 357, 358, 359, 371, 376, 406, 470, 475, 479, 482, 493, 520, 528, 531, 536, 541, 550, 552, 553], "pattern_analyz": 172, "pattern_detector": 136, "pattern_factori": 406, "pattern_lock": [183, 195], "pattern_lst": [143, 417], "pattern_pair": 406, "pattern_to_intern": 278, "pattern_to_path": 278, "patternmha": 177, "patternpair": 406, "pb": [151, 195, 235, 243, 262, 390, 480, 518, 524, 536, 538, 553], "pbound": 266, "pc": 489, "pdf": 3, "peak": [245, 482, 540], "pegasu": 553, "peleenet": 553, "penal": 542, "penalti": [227, 228, 535], "pend": 527, "pentium": 533, "peopl": [487, 544], "pep": [281, 520], "per": [29, 30, 31, 149, 151, 195, 398, 413, 433, 437, 460, 471, 472, 474, 476, 482, 493, 495, 521, 539, 542, 546, 547, 553], "per_channel": [98, 409, 439, 494, 495, 528, 544], "per_channel_symmetr": 495, "per_tensor": [292, 293, 294, 297, 298, 299, 303, 409, 439, 478, 494, 495, 528, 544], "per_tensor_symmetr": 495, "percdamp": [31, 439, 476, 547], "percent": 31, "percentag": [232, 476, 519, 547], "percentil": [3, 31, 125, 283, 303, 433, 519], "percentilecalibr": 3, "perceptron": 542, "perchannel": 31, "perform": [81, 125, 151, 189, 195, 209, 221, 234, 245, 262, 267, 271, 283, 284, 352, 413, 470, 471, 473, 475, 476, 477, 478, 480, 481, 482, 483, 487, 489, 490, 492, 493, 494, 518, 522, 523, 525, 526, 529, 531, 532, 535, 536, 537, 538, 540, 541, 542, 543, 544, 545, 546, 547, 550, 552, 553], "performance_onli": [32, 33, 34, 92, 116, 121, 132, 289, 306, 357, 371, 376, 384, 536], "perm": [225, 551], "perman": [171, 488, 542], "permiss": 488, "permut": [225, 551], "perplex": 553, "persist": 538, "person": [391, 465, 488, 543], "perspect": 552, "phase": [146, 447, 480, 487, 536, 542, 544, 546, 552], "phi": 533, "philip": 542, "philosophi": [475, 480, 544], "physic": [151, 154, 488, 518], "physical_cpu": 154, "pickl": [138, 140, 396, 397], "pickle_load_arg": [140, 396], "pickle_modul": [140, 170, 396], "pickle_protocol": 170, "pickleerror": [138, 397], "pickler": [138, 397], "pickletool": [138, 397], "picklingerror": [138, 397], "piec": [224, 227, 476, 487, 535, 547], "pil": [225, 551], "pile": [418, 451], "pin": 521, "pin_memori": [200, 202, 205, 206, 208, 387, 521], "ping_memori": [536, 544], "pip": [492, 524, 527, 529, 532, 548], "pipe": 520, "pipelin": [153, 162, 489, 523, 536, 541], "piqa": 553, "pixel": 551, "pkl": 465, "pl": 227, "place": [412, 413, 433, 442, 477, 523, 532, 542, 552], "placehold": [42, 207, 314, 387, 409, 520], "placeholder_dtyp": 173, "placeholder_shap": 173, "plai": [236, 390, 476, 487, 543, 547, 550], "plan": [477, 531], "platform": [465, 482, 487, 531, 543, 544], "platinum": 553, "pleas": [29, 135, 149, 169, 177, 178, 179, 187, 188, 195, 209, 210, 211, 214, 234, 262, 281, 413, 420, 469, 471, 473, 474, 475, 476, 477, 478, 479, 487, 490, 491, 492, 493, 518, 519, 523, 524, 526, 532, 534, 535, 537, 542, 544, 546, 547, 548, 549, 550, 552], "plu": 537, "plug": 543, "png": 211, "point": [30, 31, 221, 231, 232, 266, 425, 433, 465, 470, 471, 472, 473, 474, 475, 476, 479, 487, 535, 539, 544, 547, 550, 551, 552], "pointwise_constraint": 298, "pointwise_initi": 298, "pointwise_regular": 298, "polici": [263, 265, 271, 481, 488, 492, 554], "polit": 488, "pollut": 520, "pont": 532, "pool": 16, "pool2d": 295, "pool_siz": 297, "pooloper": 23, "poor": 477, "popen": 520, "popular": [226, 467, 469, 477, 481, 487, 492, 493, 494, 519, 525, 526, 534, 536, 542, 544, 547, 552], "popularli": 535, "port": [52, 53, 55, 324, 325, 327], "portabl": [138, 397], "portion": 209, "pose": [472, 539, 545], "posit": [225, 442, 488, 535], "possibl": [140, 396, 406, 471, 541, 542, 545, 546, 552], "post": [29, 82, 83, 149, 187, 195, 198, 199, 262, 353, 354, 413, 420, 439, 472, 474, 475, 476, 477, 479, 481, 487, 488, 492, 493, 494, 523, 524, 526, 531, 532, 539, 542, 543, 545, 547, 550, 552], "post_batch": 1, "post_hostconst_convert": [80, 351], "post_node_nam": [62, 334], "post_quantized_op_cs": [80, 351], "post_training_auto_qu": 552, "post_training_dynamic_qu": [536, 552], "post_training_static_qu": [536, 552], "postcompressionutil": 174, "postcseoptim": [83, 354], "posterior": 552, "postfix": [74, 75, 346], "posthostconstconvert": [82, 353], "postposttrainingquantconfig": 546, "postprocess": [195, 222, 225, 234, 262, 454, 493, 536, 551], "postprocess_cfg": 454, "postprocess_cl": [223, 536], "postprocess_model": 447, "posttrainingquantconfig": [195, 262, 490, 495, 521, 526, 535, 536, 538, 544, 545, 546, 547, 549, 550, 552], "power": [471, 472, 480, 536, 539, 543], "pp": 542, "pr": [489, 521, 535, 548], "practic": [472, 539], "pre": [64, 101, 141, 173, 198, 199, 209, 235, 262, 336, 398, 439, 448, 475, 476, 481, 487, 520, 523, 536, 542, 543, 544, 547, 552], "pre_batch": 1, "pre_node_nam": [62, 334], "pre_optim": [61, 333], "pre_post_process_quant": [195, 544], "pre_process": 524, "preced": [227, 487, 550, 552], "precis": [134, 195, 198, 199, 232, 234, 235, 245, 264, 267, 278, 289, 399, 400, 401, 406, 437, 439, 465, 469, 471, 472, 475, 476, 477, 481, 487, 492, 493, 494, 499, 518, 519, 523, 524, 528, 529, 531, 539, 543, 544, 547, 550, 552], "pred": [133, 234, 385, 535], "pred_list": 234, "pred_text": 225, "predefin": 481, "predict": [133, 225, 227, 231, 232, 234, 262, 385, 476, 487, 535, 547, 550, 551], "prefer": [151, 262, 476, 487, 542, 547], "prefix": [133, 140, 141, 144, 145, 151, 154, 385, 396, 398, 433, 471], "preoptim": [64, 336], "prepar": [1, 31, 145, 392, 412, 415, 431, 437, 442, 447, 470, 471, 472, 474, 475, 476, 477, 480, 483, 487, 490, 492, 524, 529, 542, 544], "prepare_compress": [195, 448, 490, 523, 536, 541, 542, 544], "prepare_dataload": 1, "prepare_input": 31, "prepare_model": 1, "prepare_model_data": 1, "prepare_prun": [170, 542], "prepared_model": [470, 474, 475, 476, 483, 529], "preprint": [472, 476, 487, 519, 539, 542, 547, 550], "preprocess": [145, 195, 209, 225, 280, 433, 454, 524, 551], "preprocess_user_cfg": 280, "present": [52, 53, 55, 324, 325, 327, 487, 543, 550], "preserv": [169, 472, 476, 519, 539, 542, 547], "pretrain": [420, 461], "pretrained_model_name_or_path": [139, 141, 398, 447], "prettyt": 465, "preval": [476, 487, 547], "previou": [192, 469, 477, 487, 494, 495, 536, 542, 548, 550, 552, 553], "previous": 521, "primari": [481, 519, 552], "primit": [140, 396], "print": [62, 135, 173, 234, 281, 334, 420, 425, 465, 482, 487, 524, 535, 536, 542, 550, 552], "print_iter": 173, "print_op_list": 465, "print_tabl": 465, "printer": [161, 465], "prior": [1, 73, 345, 552], "prioriti": [152, 443, 445, 520], "privat": 488, "prob": 490, "probabl": [3, 195, 460, 476, 487, 547], "problem": [138, 209, 234, 397, 473, 535, 537], "proce": [181, 182, 187], "procedur": [542, 552], "proceed": [487, 550], "process": [101, 125, 135, 151, 153, 159, 161, 175, 180, 181, 182, 188, 190, 192, 195, 198, 199, 209, 210, 211, 221, 225, 235, 262, 263, 265, 266, 283, 412, 413, 447, 448, 464, 465, 470, 471, 472, 475, 476, 479, 480, 481, 483, 487, 493, 494, 495, 519, 521, 523, 524, 526, 536, 539, 541, 542, 544, 545, 547, 550, 551], "process_and_check_config": 192, "process_config": 192, "process_weight_config": 192, "process_yaml_config": 192, "processor": [161, 439, 447, 473, 483, 487, 492, 534, 537, 543, 544, 546], "processor_typ": [439, 483], "processortyp": [161, 439, 447], "product": [169, 473, 487, 531, 537, 543, 544, 549, 552], "profession": 488, "profil": [151, 195, 226], "profilerfactori": [254, 255, 259], "profilingpars": 250, "profilingresult": 251, "program": [475, 492, 524, 533], "progress": [30, 183, 211, 542, 544], "project": [225, 468, 488, 489, 543, 549, 552, 554], "promis": [471, 523, 536, 542], "promot": [472, 476, 539], "prompt": 524, "prone": 542, "propag": [1, 85, 355], "properti": [209, 280, 533], "proport": 234, "propos": [473, 476, 487, 493, 537, 547, 550], "protect": [476, 547], "protected_nod": [65, 337], "proto": [221, 225, 551], "protobuf": [90, 243, 390], "prototyp": 490, "prove": [476, 487, 519, 547, 550], "provid": [29, 30, 31, 87, 90, 95, 173, 198, 199, 225, 230, 235, 262, 360, 409, 413, 448, 459, 461, 469, 471, 473, 474, 475, 476, 477, 478, 479, 480, 481, 482, 483, 484, 487, 492, 493, 494, 495, 518, 521, 523, 524, 525, 529, 531, 532, 534, 535, 536, 537, 538, 542, 544, 547, 550, 552, 553], "proxi": 490, "prune": [162, 169, 170, 171, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 189, 190, 191, 192, 195, 465, 469, 492, 524, 525, 528, 529, 531, 541, 543], "prune_conf": 536, "prune_config": 192, "pruner": [536, 542], "pruner2": 542, "pruner_class": 187, "pruner_info": 188, "pruners_info": 192, "pruning_class": 188, "pruning_config": [195, 536, 542], "pruning_end": 542, "pruning_frequ": [180, 195, 536, 542], "pruning_func": 536, "pruning_op_typ": [195, 536, 542], "pruning_pattern": 542, "pruning_scop": [195, 536, 542], "pruning_start": 542, "pruning_typ": [195, 536, 542], "pruningcallback": 162, "pruningconfig": 448, "pruningcriterion": [169, 191], "pruningschedul": 190, "pseudo": [198, 199, 262, 448, 476, 547], "pt": [140, 396, 464, 476, 492, 529, 532, 538, 543, 544, 546, 547], "pt2e": [405, 407, 409, 435, 437, 441], "pt2e_dynamic_quant_entri": 437, "pt2e_export": 434, "pt2e_quant": 394, "pt2e_static_quant_entri": 437, "pt_fp32_model": 458, "pt_int8_model": 458, "ptq": [195, 262, 474, 475, 479, 480, 490, 524, 531, 536, 544, 550, 552], "public": [281, 488], "publish": [473, 488, 533, 534, 537, 550], "pull": [52, 53, 55, 324, 325, 327], "punct_nondigit_r": 227, "punctuat": [224, 227, 232], "pure": 542, "purif": 543, "purpos": [473, 474, 475, 476, 478, 528, 537, 544], "push": [472, 476, 487, 489, 539, 542, 547, 550], "put": [140, 211, 396], "py": [3, 133, 135, 151, 154, 180, 195, 228, 230, 231, 232, 281, 385, 443, 478, 482, 483, 490, 493, 520, 524, 532, 536, 544, 548], "pycocotool": [230, 527], "pyhessian": 135, "pylanc": 520, "pyobject": 527, "pypi": 532, "pytest": 489, "python": [3, 60, 133, 138, 140, 161, 211, 226, 281, 332, 385, 396, 397, 443, 465, 467, 483, 490, 492, 520, 524, 527, 532, 536, 542, 543, 551], "python3": 527, "pythonmultiheadattentionprun": 184, "pytorch": [163, 165, 166, 170, 173, 176, 179, 180, 183, 188, 194, 195, 208, 209, 211, 214, 218, 225, 234, 235, 244, 262, 272, 392, 394, 435, 436, 437, 438, 439, 440, 441, 442, 444, 445, 446, 447, 458, 459, 465, 472, 477, 489, 490, 492, 493, 494, 495, 500, 519, 520, 521, 523, 525, 528, 529, 531, 532, 534, 536, 537, 538, 539, 542, 543, 547, 548, 550, 552], "pytorch_cpu": 495, "pytorch_fx": [211, 218, 536], "pytorch_ipex": [211, 218, 536], "pytorch_prun": 188, "pytorchalignimagechannel": 225, "pytorchbasemodel": 244, "pytorchbasepattern": [175, 189], "pytorchbaseprun": 180, "pytorchbasicprun": 181, "pytorchbertdataset": 209, "pytorchblockmaskprun": 182, "pytorchcifar10": 211, "pytorchcifar100": 211, "pytorchcriterion": 163, "pytorchcropresizetransform": 225, "pytorchcrossentropyloss": 163, "pytorchdataload": 206, "pytorchdataset": 211, "pytorchdynamo": 477, "pytorchfashionmnist": 211, "pytorchfilt": 218, "pytorchfxmodel": 244, "pytorchimagenetraw": 214, "pytorchintermediatelayersknowledgedistillationloss": 163, "pytorchintermediatelayersknowledgedistillationlosswrapp": 163, "pytorchknowledgedistillationloss": [163, 536], "pytorchknowledgedistillationlosswrapp": 163, "pytorchloss": 234, "pytorchmetr": 234, "pytorchmnist": 211, "pytorchmodel": 244, "pytorchmxnettransform": 225, "pytorchmxnetwrapdataset": 211, "pytorchmxnetwrapfunct": [211, 225], "pytorchnormalizetransform": 225, "pytorchoptim": 165, "pytorchpatternlockprun": 185, "pytorchpatternninm": 178, "pytorchpatternnxm": 179, "pytorchprogressiveprun": 186, "pytorchretrainfreeprun": 187, "pytorchselfknowledgedistillationloss": 163, "pytorchselfknowledgedistillationlosswrapp": 163, "pytorchsgd": 165, "pytorchtransform": 225, "pytorchtranspos": 225, "q": [30, 31, 92, 94, 116, 357, 359, 371, 470, 475, 477, 487, 547, 550], "q_conf": 523, "q_config": [28, 145, 292, 293, 294, 297, 298, 458, 493], "q_dataload": [198, 199, 263, 264, 266, 267, 271, 273, 274, 530, 552], "q_func": [198, 199, 263, 264, 266, 267, 271, 273, 274, 413, 493, 494, 536, 552], "q_hook": [198, 199, 263, 264, 266, 267, 271, 273, 274], "q_max": [487, 550], "q_min": [487, 550], "q_model": [135, 139, 195, 262, 301, 305, 417, 470, 474, 475, 479, 481, 490, 521, 524, 526, 530, 535, 536, 538, 544, 545, 546, 547], "q_tensor": 433, "q_weight": [31, 423], "q_x": [487, 550], "qa": [231, 232, 492], "qactivationoper": 5, "qargmaxoper": 6, "qas_id": 225, "qat": [97, 144, 195, 243, 492, 523, 524, 529, 531, 536, 544], "qat_clone_funct": 101, "qat_op_name_dict": 195, "qattent": 7, "qattentionoper": 7, "qavgpool2d": 297, "qbinari": 8, "qbinaryoper": 8, "qconcat": 9, "qconcatoper": 9, "qconfig": [1, 145, 417, 464, 471, 476, 492, 547], "qconfig_file_path": 160, "qconv2d": 292, "qconvoper": 10, "qd": 475, "qdens": 293, "qdepthwiseconv2d": 294, "qdirect": 11, "qdirectoper": 11, "qdq": [29, 72, 97, 98, 127, 145, 195, 288, 344, 362, 433, 456, 457, 458, 479, 493, 526, 531, 544, 550], "qdq_enabl": [33, 306], "qdq_op_fp32_bia": 195, "qdq_op_fp32_bias_qdq": 195, "qdq_op_int32_bia": 195, "qdq_quantiz": 412, "qdq_tensor": 31, "qdq_weight_actor": 433, "qdq_weight_asym": 433, "qdq_weight_sym": 433, "qdqlayer": [398, 429], "qembedlayernorm": 12, "qembedlayernormalizationoper": 12, "qgather": 13, "qgatheroper": 13, "qgemm": 15, "qgemmoper": 15, "qglobalaveragepooloper": 14, "qintegerop": [531, 544], "qkv": 184, "qkv_modul": 184, "qkv_name": 184, "qlinear": [195, 211, 218, 234, 456, 493], "qlinear2qdq": 455, "qlinearaveragepool": 23, "qlinearconv": 10, "qlinearglobalaveragepool": 14, "qlinearmatmul": 18, "qlinearop": [456, 531, 544, 553], "qlora": [476, 487, 547], "qmatmuloper": 18, "qmax": 145, "qmaxpool": 19, "qmaxpool2d": 297, "qmaxpooloper": 19, "qmin": 145, "qmodel": [135, 478, 480], "qnli": [209, 535, 553], "qop_registri": 21, "qoper": [5, 21, 195, 526], "qpad": 22, "qpadoper": 22, "qpooloper": 23, "qqp": [209, 535, 553], "qresiz": 25, "qresizeoper": 25, "qscheme": 495, "qseparableconv2d": 298, "qsplit": 26, "qsplitoper": 26, "qsym_model": 1, "qt_config": [33, 306], "qtensor": [423, 424], "qtensor_to_tensor": 1, "qtensorconfig": 422, "qtensormetainfo": 426, "qtype": [29, 30, 493], "quadrat": [439, 476], "quala": 543, "qualiti": [227, 520], "quant": [31, 133, 145, 195, 278, 285, 287, 288, 289, 299, 303, 413, 416, 433, 438, 439, 476, 487, 490, 520, 534, 536, 544], "quant_axi": [292, 293, 294, 297, 298], "quant_block_list": [418, 439], "quant_config": [288, 289, 301, 305, 391, 392, 403, 405, 412, 416, 418, 419, 420, 427, 430, 432, 442, 447, 470, 472, 474, 475, 476, 477, 478, 479, 480, 483, 529, 539], "quant_dequant_data": 29, "quant_dequant_w_v1": 413, "quant_dequant_x_v1": 413, "quant_format": [195, 458, 526], "quant_level": [195, 547, 550, 552], "quant_lm_head": [420, 439, 451, 476], "quant_max": 495, "quant_min": 495, "quant_mod": [32, 278, 289, 292, 293, 294, 297, 298, 494, 495], "quant_mode_from_pattern": 278, "quant_narrow_rang": [292, 293, 294, 297, 298], "quant_opt": 280, "quant_round_mod": [292, 293, 294, 297, 298], "quant_scal": [439, 476], "quant_statu": [292, 293, 294, 297, 298], "quant_t": [292, 293, 294, 297, 298], "quant_tensor": [31, 433], "quant_typ": 280, "quant_weight_w_scal": 433, "quant_zero": [439, 476], "quantformat": 30, "quantif": [474, 476, 479, 547, 550], "quantil": [433, 552], "quantit": 476, "quantiz": [1, 3, 4, 29, 30, 31, 33, 34, 73, 77, 79, 81, 84, 92, 97, 98, 99, 100, 101, 102, 103, 104, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 134, 135, 137, 141, 142, 145, 149, 151, 153, 157, 159, 161, 162, 195, 198, 199, 221, 226, 267, 269, 271, 280, 283, 284, 286, 288, 289, 290, 291, 292, 293, 294, 295, 297, 298, 392, 395, 398, 402, 403, 404, 405, 408, 409, 411, 412, 413, 415, 416, 417, 418, 419, 420, 422, 423, 424, 425, 426, 429, 430, 431, 432, 433, 434, 435, 436, 447, 448, 451, 452, 458, 460, 461, 464, 465, 469, 473, 479, 481, 484, 493, 499, 500, 520, 521, 524, 525, 528, 529, 530, 531, 535, 538, 541, 543, 548, 551, 552], "quantizable_nod": 1, "quantizable_op": [145, 413, 417], "quantization_aware_training_conf": 536, "quantization_cfg": 493, "quantization_config": 450, "quantization_param": 28, "quantizationawaretrainingcallback": 162, "quantizationawaretrainingconfig": [195, 448, 490, 523, 526, 536, 544, 546, 552], "quantizationmethod": 451, "quantizationmod": 30, "quantizationspec": 409, "quantize_4bit": 433, "quantize_config": [99, 494], "quantize_data": 30, "quantize_data_per_channel": 30, "quantize_data_with_scale_zero": 30, "quantize_elemwise_op": 404, "quantize_graph": [96, 361], "quantize_graph_bas": [97, 362], "quantize_graph_bn": [97, 362], "quantize_graph_common": [96, 361], "quantize_graph_concatv2": [97, 362], "quantize_graph_conv": [97, 362], "quantize_graph_for_intel_cpu": [97, 362], "quantize_graph_matmul": [97, 362], "quantize_graph_pool": [97, 362], "quantize_help": 99, "quantize_lay": 99, "quantize_layer_add": 102, "quantize_layer_bas": 102, "quantize_layer_bn": 102, "quantize_model": [305, 478, 479, 480, 487], "quantize_model_with_single_config": 305, "quantize_mx_op": 404, "quantize_nod": 458, "quantize_nparrai": 30, "quantize_per_channel": [487, 550], "quantize_per_tensor_absmax": [487, 550], "quantize_rang": 30, "quantize_recip": 101, "quantize_sym_model": 1, "quantize_wrapp": 99, "quantizeconfig": [100, 101], "quantized_data": 30, "quantized_dict": 135, "quantized_model": [476, 483, 529], "quantized_nod": [92, 357], "quantized_value_typ": 30, "quantizedconcatv2": [109, 119, 364, 374], "quantizedconv": [76, 77, 347, 348], "quantizeddeconv": [76, 347], "quantizediniti": 30, "quantizedinput": [221, 551], "quantizedmatmul": [78, 79, 349, 350], "quantizedmatmulwithbiasanddequant": [79, 350], "quantizedrnnconvert": 84, "quantizedvalu": 30, "quantizedvaluetyp": 30, "quantizegraph": [117, 372], "quantizegraphbas": [117, 372], "quantizegraphforintel": [121, 376], "quantizegraphhelp": [124, 379], "quantizelay": 105, "quantizelayeradd": 104, "quantizelayerbas": 105, "quantizelayerbatchnorm": 106, "quantizelinear": 30, "quantizenodebas": [117, 372], "quantizer_cl": 447, "quantizev2": [83, 354], "quantizewrapp": [101, 107], "quantizewrapperbas": 107, "quantiztaion": [195, 417], "quantopt": 280, "quanttyp": [30, 280], "queri": [1, 32, 133, 145, 173, 184, 195, 288, 289, 417, 447, 487, 494, 495, 544], "query_framework_cap": 494, "query_fused_pattern": 493, "query_fw_cap": [493, 495], "query_layer_nam": 184, "query_quantizable_nod": 1, "querybackendcap": [493, 494], "question": [225, 231, 232, 487, 488, 489, 492, 493, 532, 542, 550, 551, 553], "question_text": 225, "quick": [469, 483, 528, 537, 542], "quickli": [481, 534, 552], "quint8": [30, 413], "quit": 542, "qweight_config_path": 547, "qwen2": [492, 543], "r": [30, 128, 150, 380, 474, 475, 476, 478, 480, 482, 487, 532, 544, 553], "r1": [133, 385], "r34": 490, "race": 488, "rais": [52, 53, 55, 90, 138, 140, 145, 170, 176, 183, 192, 230, 235, 281, 324, 325, 327, 396, 397, 413, 433, 435, 447, 492, 520, 542, 543], "ram": [140, 396, 476, 483], "ran": 162, "rand": [418, 439, 476, 487, 550], "randn": [195, 526], "random": [41, 133, 161, 195, 221, 225, 266, 270, 313, 391, 418, 465, 476, 536, 542, 551], "random_crop": [221, 551], "random_flip_left_right": [221, 551], "random_se": [195, 266, 536], "randomcrop": 551, "randomcroptftransform": 225, "randomcroptransform": 225, "randomhorizontalflip": [225, 536, 551], "randomli": [225, 266, 487, 550, 551, 552], "randomresizedcrop": [536, 551], "randomresizedcropmxnettransform": 225, "randomresizedcroppytorchtransform": 225, "randomresizedcroptftransform": 225, "randomresizedcroptransform": 225, "randomst": 266, "randomtunestrategi": 273, "randomverticalflip": [225, 551], "rang": [212, 213, 225, 281, 387, 433, 448, 461, 470, 472, 473, 476, 477, 480, 482, 487, 492, 493, 495, 519, 523, 524, 536, 539, 541, 542, 544, 547, 550, 551], "rank": 524, "rapid": [532, 534], "rate": [476, 487, 536, 542, 544], "rather": [476, 530, 547], "ratio": [31, 128, 150, 175, 180, 192, 195, 221, 225, 380, 534, 536, 542, 551, 553], "ratiospars": 553, "raw": [30, 151, 210, 214, 217, 271, 412, 415, 431, 437, 535, 552], "raw_cmd": [151, 154], "raw_func": 445, "raw_imag": 211, "rawgptquant": 420, "rb": [140, 396], "rcnn": 526, "re": 547, "reach": [153, 175, 190, 195, 489, 521, 542, 552], "read": [90, 133, 140, 214, 225, 385, 396, 546, 549], "read_graph": [133, 385], "read_squad_exampl": 225, "read_tensorflow_node_attr": 90, "readabl": [154, 520], "readi": 542, "readlin": [140, 396], "readm": 524, "real": [30, 212, 387, 487, 494, 519, 524, 543, 544], "realdiv": [51, 54, 323, 326], "realiz": [524, 540, 546, 549], "rearrang": [31, 187, 476, 542, 547], "reason": [476, 487, 488, 494, 521, 547, 552], "rebuild": [133, 385], "recal": [232, 234], "receiv": 549, "recent": [473, 536, 537], "recip": [33, 173, 195, 306, 472, 481, 492, 529, 536, 539, 545, 547, 550, 552], "recipe_sampl": 173, "recipesearch": 173, "recogn": [227, 447, 552], "recognit": [473, 524, 526, 542], "recognitionimagenet": 553, "recommend": [234, 445, 471, 473, 483, 492, 493, 528, 529, 542, 552], "recommendation_system": 195, "reconstruct": [133, 385, 543], "reconstruct_saved_model": [133, 385], "record": [135, 145, 163, 166, 209, 210, 211, 217, 433, 465, 481, 547, 549, 552], "record_max_info": [303, 413], "record_output": 166, "recov": [29, 411, 413, 433, 464, 465, 493, 523], "recover_config": 34, "recover_forward": 433, "recover_model_from_json": [411, 464], "rectangl": [476, 545], "recurs": [194, 465], "recursivescriptmodul": 415, "red": 553, "redpajama": [474, 550], "reduc": [16, 195, 439, 473, 474, 475, 476, 479, 480, 487, 493, 519, 523, 536, 537, 542, 543, 544, 545, 546, 547, 550, 552], "reduce_rang": [2, 28, 29, 195, 495], "reducemax": 24, "reducemin": 24, "reduceminmaxoper": 24, "reduceoper": 24, "reduct": [542, 545], "redund": [76, 78, 347, 349, 447], "ref": [3, 133, 385], "refer": [29, 135, 149, 169, 177, 178, 179, 187, 188, 192, 195, 209, 227, 228, 234, 262, 281, 413, 420, 439, 471, 473, 474, 475, 477, 478, 479, 480, 490, 492, 493, 494, 518, 521, 523, 524, 526, 530, 532, 533, 535, 536, 537, 540, 545, 548, 551, 552], "reference_corpu": 228, "refin": [443, 480, 530, 542], "reflect": [535, 551], "reg": [170, 181, 182, 187, 195], "reg_term": 189, "regard": [488, 546], "regardless": 488, "region": [474, 550], "regist": [3, 21, 138, 140, 146, 152, 163, 165, 169, 170, 175, 176, 180, 183, 188, 189, 190, 191, 211, 218, 225, 234, 245, 274, 280, 299, 391, 396, 397, 398, 413, 439, 443, 447, 493, 520, 524, 535, 536, 540, 550, 552], "register_acceler": 443, "register_algo": [391, 447, 520], "register_autotun": 413, "register_config": [152, 520], "register_criterion": [169, 191], "register_customer_metr": 234, "register_packag": [140, 396], "register_pattern": 175, "register_prun": [180, 188], "register_reg": 189, "register_schedul": 190, "register_supported_configs_for_fwk": 152, "register_weight_hook": 398, "registr": [146, 211, 218, 225], "registri": [152, 169, 175, 180, 188, 189, 190, 191, 443], "registry_criterion": 163, "regress": [209, 489], "regul": [181, 182, 187], "regular": [189, 227], "regulariz": 189, "reinstal": 527, "reject": 488, "rel": [195, 245, 536, 552, 553], "relat": [174, 189, 230, 280, 407, 410, 414, 424, 446, 454, 495, 529, 542, 547], "relationship": 195, "relative_loss": 153, "releas": [470, 475, 492, 529, 532, 554], "relev": [266, 494, 495, 520, 542], "reli": [477, 536, 550], "religion": 488, "reload": 160, "relu": [59, 63, 94, 331, 335, 359, 490, 528, 550], "relu6": [59, 331, 528], "remain": [431, 441], "remaind": 519, "remap": [55, 140, 327, 396], "remov": [5, 30, 36, 42, 45, 59, 65, 68, 69, 70, 81, 83, 125, 171, 184, 232, 283, 308, 314, 317, 331, 337, 340, 341, 342, 352, 354, 447, 488, 536, 542], "removableactivationoper": 5, "remove_init_from_model_input": 30, "remove_training_nod": [61, 333], "removetrainingnodesoptim": [65, 337], "renam": [66, 338, 477, 548], "rename_batch_norm": [61, 333], "renamebatchnormoptim": [66, 338], "repeat": 552, "repercuss": 488, "replac": [3, 141, 145, 232, 398, 406, 413, 427, 433, 470, 472, 475, 520, 524, 536, 539, 548], "replace_forward": 433, "replace_pattern": 406, "replacement_fn": 427, "replic": 552, "replica": 552, "repo": [209, 468, 489, 525, 554], "repo_id": [141, 398, 447], "repo_typ": [141, 398, 447], "report": [488, 489, 492, 549], "repositori": 489, "repr": 451, "repres": [30, 152, 153, 156, 157, 175, 179, 180, 188, 189, 192, 211, 216, 230, 232, 234, 406, 426, 475, 476, 480, 487, 488, 495, 519, 526, 542, 544, 545, 552], "represent": [30, 138, 397, 472, 476, 487, 488, 490, 519, 523, 539, 542, 544], "reproduc": 418, "requant": [77, 79, 348, 350], "requantize_cfg": 145, "request": [475, 492, 544], "requir": [145, 195, 201, 243, 261, 390, 433, 471, 473, 475, 476, 480, 487, 490, 493, 494, 518, 519, 521, 523, 524, 527, 528, 536, 537, 538, 542, 544, 547, 548, 549, 550, 552], "requirements_pt": [527, 532], "requirements_tf": 532, "rerang": [132, 384], "rerange_quant": [132, 384], "rerange_quantized_concat": [130, 382], "rerangequantizedconcat": [132, 384], "rerewrit": [36, 308], "resblock": 195, "rescal": [221, 225, 551], "rescalekeraspretraintransform": 225, "rescaletftransform": 225, "rescaletransform": 225, "research": [477, 492, 533, 550, 553], "reserv": [198, 199], "reset": 535, "reset_none_to_default": 192, "reshap": [46, 52, 53, 58, 318, 324, 325, 330, 413, 487, 550], "reshape_in0_ndef": [52, 53, 324, 325], "reshape_in1_ndef": [52, 53, 324, 325], "reshape_in_channel_to_last": 413, "reshape_scale_as_input": 413, "reshape_scale_as_weight": 413, "reshuffl": 521, "resid": [140, 396], "resiz": [16, 209, 210, 221, 225, 551], "resize_method": 221, "resize_shap": 216, "resize_sid": [221, 551], "resizecropimagenet": [524, 551], "resizemxnettransform": 225, "resizeoper": 25, "resizepytorchtransform": 225, "resizetftransform": 225, "resizetransform": 225, "resizewithaspectratio": 221, "resizewithratio": [225, 551], "resnest50": 553, "resnet": [524, 553], "resnet101": 553, "resnet18": [471, 492, 537, 553], "resnet34": [490, 553], "resnet50": [195, 478, 492, 524, 526, 537, 542, 544, 549, 553], "resnet50_fp32_pretrained_model": 524, "resnet50_v1": [524, 536], "resnetv2": 553, "resnext101_32x8d": 553, "resolut": 519, "resolv": [490, 491], "resort": 536, "resourc": 552, "respect": [487, 488, 528, 542, 550], "respons": [249, 250, 253, 478, 544], "rest": [145, 433], "restor": [476, 547], "restrict": [55, 140, 195, 327, 396, 542, 549], "restructuredtext": 281, "result": [30, 133, 135, 145, 221, 225, 227, 230, 231, 232, 234, 262, 269, 385, 406, 408, 417, 448, 451, 464, 465, 469, 470, 471, 474, 476, 479, 481, 482, 487, 488, 492, 521, 524, 531, 533, 535, 536, 540, 542, 543, 544, 547, 549, 550, 551, 552, 553], "resum": [195, 198, 199, 263, 264, 266, 267, 271, 273, 274], "resume_from": [161, 195, 465], "retain": 519, "retrac": 546, "retrain": [187, 475, 523], "retrain_fre": [169, 183, 542], "retrainfreecriterion": 169, "retrainfreeprun": [187, 188], "retri": 413, "retriev": [152, 159, 207, 387, 406, 413, 542], "return": [1, 3, 31, 39, 52, 53, 55, 59, 90, 101, 133, 134, 135, 140, 144, 145, 146, 151, 152, 154, 160, 161, 163, 165, 170, 173, 175, 176, 180, 183, 188, 189, 190, 192, 194, 198, 199, 211, 218, 221, 225, 227, 228, 230, 231, 232, 234, 235, 239, 243, 245, 257, 261, 262, 266, 274, 278, 280, 281, 299, 301, 303, 305, 311, 324, 325, 327, 331, 385, 390, 391, 396, 398, 404, 406, 408, 409, 411, 412, 413, 415, 417, 418, 420, 425, 427, 431, 433, 435, 437, 438, 439, 441, 442, 445, 447, 448, 451, 454, 458, 464, 465, 473, 477, 478, 481, 487, 490, 494, 495, 521, 524, 535, 538, 540, 542, 544, 547, 550, 552], "return_int": [433, 547], "reus": 477, "revers": [133, 154], "reversed_numa_info": 154, "revert": [272, 280, 552], "reverted_data_typ": 280, "review": [488, 489, 492, 543], "revis": [141, 398, 431, 441, 447], "rewrit": [35, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 91, 92, 93, 94, 170, 307, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 406], "rgb": 221, "right": [140, 221, 230, 396, 487, 488, 489, 490, 550, 551], "rmax": [30, 480, 487, 544], "rmin": [30, 472, 480, 487, 539, 544], "rmse": [234, 535, 552], "rnn": 84, "rnn_convert": 80, "rnn_detail": 84, "roberta": [209, 553], "roc": 234, "role": [236, 390, 476, 487, 547, 550], "rollov": [200, 202, 205, 206, 208, 387, 521], "romanian": 542, "root": [173, 209, 210, 211, 214, 234, 524, 535, 536], "root_linear": 174, "root_rank": 524, "roughli": [476, 487, 547], "rouhani": [472, 539], "round": [31, 128, 150, 380, 404, 439, 470, 471, 476, 477, 487, 492, 543, 544, 547, 550], "round_": [487, 550], "round_method": 439, "round_multipli": 171, "roundingmod": 404, "row": [465, 487, 550], "rowi": 31, "rte": [209, 535, 553], "rtn": [31, 145, 303, 392, 428, 437, 438, 439, 477, 483, 487, 520, 545, 547], "rtn_algo_entri": 520, "rtn_arg": [476, 545, 547], "rtn_entri": 437, "rtn_g32asym": 547, "rtn_quantiz": 31, "rtnconfig": [437, 438, 439, 447, 451, 476, 477, 481, 529], "rtnquantiz": 430, "rtnw4g32asym": 553, "rtnw4g32sym": 553, "rule": [480, 542], "run": [1, 125, 133, 140, 151, 180, 192, 195, 198, 199, 208, 224, 235, 262, 266, 283, 385, 396, 413, 448, 471, 473, 476, 477, 480, 482, 483, 487, 492, 493, 518, 524, 527, 528, 536, 543, 544, 547, 548, 549, 552], "run_arg": [438, 442, 477], "run_cmd": 552, "run_fn": [412, 413, 438, 442, 474, 475, 476, 477], "run_forward": 1, "run_inst": 151, "run_multi_instance_command": 154, "runtim": [470, 487, 489, 492, 493, 494, 496, 521, 525, 528, 531, 537, 539, 547, 552], "rw": 553, "s1": 552, "s2": 552, "s3": 552, "s4": 552, "s5": 552, "s6": 552, "s7": 552, "s8": [292, 293, 294, 297, 298, 458], "sa_optim": 167, "sacrif": [472, 539, 543], "safe": [431, 489], "safe_seri": 431, "safetensor": 492, "salient": [31, 476, 542, 547], "same": [68, 126, 133, 153, 187, 195, 209, 225, 230, 286, 340, 385, 413, 465, 471, 472, 476, 481, 482, 487, 493, 495, 518, 521, 524, 528, 536, 539, 542, 544, 547, 550, 551, 552], "sampl": [31, 62, 145, 153, 195, 203, 207, 209, 210, 211, 221, 225, 234, 266, 334, 387, 413, 418, 476, 480, 481, 482, 487, 521, 525, 531, 544, 547, 550, 551, 552, 553], "sampler": [153, 200, 202, 205, 206, 208, 277, 387, 418, 439, 476, 481, 521, 524], "sampling_s": 536, "samsum": 553, "sapphir": [532, 534], "satisfi": [208, 532], "satur": 551, "save": [90, 133, 139, 140, 160, 170, 195, 211, 243, 262, 385, 390, 396, 398, 408, 411, 415, 431, 442, 448, 452, 457, 458, 461, 465, 471, 477, 478, 487, 490, 492, 493, 530, 536, 537, 538, 541, 544, 545, 547, 550], "save_config_map": 160, "save_for_huggingface_upstream": [461, 536], "save_load": [158, 407, 410, 414, 428], "save_path": [457, 458, 493, 538], "save_protobuf": 90, "save_q_input": 413, "save_to_disk": 493, "saved_dir": [461, 547], "saved_model": [133, 385, 480, 545], "saved_model_sess": [243, 390], "saved_model_tag": [243, 390], "saved_path": 398, "saved_result": [408, 415, 431, 441, 476, 477, 538, 547], "savedmodel": [235, 243, 262, 390], "scalabl": [473, 480, 487, 492, 532, 534, 537, 543, 544, 546], "scalar": [198, 199, 235, 262, 448, 535, 544, 552], "scale": [3, 30, 31, 85, 126, 128, 142, 145, 149, 150, 221, 225, 286, 292, 293, 294, 297, 298, 355, 380, 413, 422, 425, 426, 429, 433, 470, 471, 472, 474, 475, 476, 480, 487, 539, 544, 547, 549, 550, 551, 552], "scale_bit": 404, "scale_c": [128, 150, 380], "scale_dtyp": [418, 429, 439, 451, 461, 476, 547], "scale_info": 465, "scale_method": [439, 471], "scale_nam": 30, "scale_param": 439, "scale_propag": [80, 351], "scale_quant_group_s": [439, 476], "scale_shar": [413, 439], "scale_valu": 30, "scalepropagationtransform": [85, 355], "scaler": 285, "scales_per_op": [126, 286, 303], "scan": [489, 492], "scenario": [476, 477, 487, 493, 518, 536, 542, 547], "scene": 542, "schedul": [170, 180, 181, 182, 187, 189, 195, 476, 536, 541], "schema": [89, 433], "scheme": [29, 30, 31, 142, 145, 413, 417, 429, 433, 493, 494, 495, 521, 528, 547, 552], "scienc": 532, "scipi": 266, "scope": [133, 385, 477, 489, 494, 536], "score": [169, 175, 180, 184, 191, 195, 227, 228, 230, 231, 232, 234, 269, 454, 490, 535, 540, 542, 549, 552], "script": [154, 173, 227, 228, 231, 232, 489, 492, 524, 531, 543], "seamlessli": [472, 539, 542, 552], "search": [133, 173, 187, 195, 198, 199, 227, 266, 406, 420, 433, 465, 469, 476, 477, 479, 492, 520, 531, 535, 542, 543, 547, 550, 552], "search_algorithm": 195, "search_clip": 433, "search_pattern": 406, "search_spac": 195, "searcher": [173, 195], "searching_result": 173, "sec": [482, 553], "second": [49, 140, 174, 195, 209, 267, 321, 396, 465, 476, 483, 487, 536, 547, 550, 552], "section": [281, 495, 520, 523, 542, 547], "secur": [138, 397, 492, 543, 554], "sed": 548, "see": [138, 225, 227, 397, 471, 476, 487, 488, 489, 490, 491, 520, 533, 536, 547, 550, 552], "seed": [133, 161, 195, 391, 418, 439, 465, 476, 536], "seek": [140, 396, 547], "seem": 520, "seen": [465, 493], "segment": [209, 228, 230, 489], "segment_id": [225, 536], "select": [189, 192, 195, 209, 433, 437, 443, 461, 471, 476, 487, 490, 519, 531, 532, 542, 544, 547, 552], "self": [48, 145, 173, 195, 245, 320, 433, 477, 493, 494, 521, 531, 535, 549, 552], "selfknowledg": 163, "selfknowledgedistillationloss": 163, "selfknowledgedistillationlossconfig": [195, 536], "selfmhasearch": 173, "semant": [493, 528], "send": [489, 494], "senior": 519, "sensit": [169, 531, 542], "sensitivitybalanc": 553, "sentenc": 520, "sep": [492, 543], "separ": [298, 418, 488, 520, 530, 532, 533, 541], "separable_conv2d": 295, "separableconv2d": 298, "seq_len": 451, "seq_length": 209, "seqlen": [418, 439, 476], "seqtyp": 90, "sequenc": [48, 90, 174, 177, 178, 195, 209, 224, 225, 228, 232, 320, 418, 476, 487, 493, 528, 542, 547, 551], "sequencediagram": [494, 495], "sequenti": [153, 207, 263, 265, 387, 391, 420, 481, 552], "sequentialsampl": [153, 207, 387], "seri": [221, 492, 532, 536, 543, 551], "serial": [138, 140, 396, 397, 431], "serv": [195, 243, 390, 487], "server": [161, 483], "servic": [492, 543], "sess": [133, 243, 385, 390], "session": [31, 133, 208, 243, 385, 390, 536], "sessionopt": 257, "set": [1, 30, 36, 81, 90, 100, 133, 140, 145, 151, 152, 153, 154, 161, 165, 192, 195, 198, 199, 200, 209, 211, 214, 225, 230, 234, 235, 243, 261, 262, 281, 288, 302, 308, 352, 385, 387, 389, 390, 396, 406, 409, 413, 431, 433, 438, 439, 441, 447, 448, 465, 471, 473, 474, 476, 477, 478, 479, 481, 482, 483, 487, 488, 492, 494, 518, 521, 524, 526, 527, 528, 530, 531, 535, 536, 537, 542, 544, 547, 549, 550, 552], "set_all_env_var": 151, "set_cores_for_inst": 154, "set_eager_execut": 261, "set_env_var": 151, "set_epoch": 524, "set_loc": [470, 474, 475, 476, 477, 478], "set_modul": [145, 413, 433, 447], "set_nam": 90, "set_random_se": [161, 195, 465], "set_resume_from": [161, 195, 465], "set_tensor": 493, "set_tensorboard": [161, 195, 465], "set_workspac": [161, 195, 465], "settings_recommend": 520, "setup": [492, 528, 532, 542], "sever": [124, 190, 225, 379, 472, 473, 483, 487, 523, 531, 536, 537, 539, 542, 545, 550, 551, 552], "sex": [465, 488], "sexual": 488, "sf": 527, "sgd": [165, 195, 536], "shaji": 476, "shape": [30, 31, 90, 133, 175, 212, 213, 221, 225, 230, 385, 387, 420, 426, 435, 476, 480, 487, 528, 536, 547, 550, 551], "shape_overrid": 127, "shard": [141, 398, 431], "share": [30, 31, 67, 83, 94, 126, 286, 339, 354, 359, 433, 476, 487, 527, 528, 547, 550, 552], "share_qdq_y_pattern": [91, 356], "shared_criterion": [413, 439, 550], "shareqdqforitexypatternoptim": [94, 359], "shell": [154, 492], "shen": [533, 542], "shift": [128, 150, 221, 380, 551], "shop": 520, "short": 552, "shortcut": 209, "shorter": [209, 225, 551], "shot": [169, 187, 190, 476, 480, 531, 536, 542, 543, 547], "should": [40, 100, 101, 140, 162, 171, 173, 184, 195, 198, 199, 207, 209, 211, 225, 228, 234, 235, 262, 281, 301, 305, 312, 396, 413, 427, 431, 441, 448, 458, 465, 475, 477, 478, 479, 480, 482, 487, 490, 493, 494, 495, 524, 535, 536, 540, 542, 544, 547, 551, 552], "show": [180, 465, 472, 487, 488, 524, 536, 539, 550, 552], "show_memory_info": 465, "show_nam": [131, 383], "show_op": [131, 383], "shown": [471, 472, 474, 487, 521, 535, 536, 539, 540, 541, 542, 545, 550, 552], "shrink": 542, "shuffl": [200, 202, 205, 206, 208, 387, 521, 536, 544], "shufflenet": 553, "side": [225, 492, 551], "sigmoid": 526, "sign": [280, 439, 476, 487, 489, 492, 495, 519, 543, 544, 547, 549], "signatur": [243, 390], "signed_flag": 280, "signifi": 90, "signific": [480, 487, 542, 543, 545, 550], "significantli": [473, 476, 536, 537, 542, 552], "signround": 476, "sigopt": [197, 543], "sigopt_api_token": [536, 549, 552], "sigopt_experiment_id": 549, "sigopt_experiment_nam": [536, 549, 552], "sigopt_project_id": [536, 549, 552], "sigopttunestrategi": 198, "silicon": [472, 539], "similar": [184, 487, 536, 550, 552], "similarli": [487, 550], "simpl": [156, 225, 471, 480, 487, 536, 542, 549, 550, 552], "simple_attr": 156, "simple_infer": [145, 417], "simple_progress_bar": 30, "simplest": 519, "simpli": [524, 538], "simplic": [487, 550], "simplifi": [542, 543], "simul": [168, 477, 495], "simultan": [184, 541], "sinc": [195, 227, 471, 476, 487, 526, 535, 541, 547], "since_vers": 89, "singl": [169, 190, 195, 203, 209, 225, 230, 234, 262, 305, 387, 406, 413, 476, 490, 492, 532, 542, 545, 550], "single_output": 234, "singleton": [95, 161, 360, 391, 465], "site": 548, "situat": [195, 477, 524, 542], "sixteen": [473, 537], "size": [83, 153, 177, 178, 202, 203, 208, 211, 217, 221, 225, 243, 245, 354, 387, 390, 418, 426, 431, 433, 465, 472, 475, 476, 487, 488, 494, 521, 524, 527, 536, 539, 540, 542, 544, 545, 547, 550, 551, 553], "skip": [140, 396, 552], "skip_convers": 88, "skip_first": 277, "skip_verified_config": 153, "skylak": 532, "slave": [280, 552], "slice": 90, "slim": [171, 172, 173, 230, 241, 243, 390, 391, 538, 542], "slim_sess": [243, 390], "slower": [476, 547], "small": [3, 52, 53, 54, 55, 269, 324, 325, 326, 327, 476, 487, 542, 547, 552, 553], "smaller": [55, 225, 327, 472, 536, 539, 542, 551], "smbo": 552, "smooth": [3, 125, 126, 133, 149, 195, 283, 284, 285, 286, 301, 303, 412, 413, 437, 439, 477, 492, 520, 529, 542, 552], "smooth_distribut": 3, "smooth_quant": [4, 139, 145, 148, 195, 394, 417, 520, 544, 550], "smooth_quant_arg": [195, 544, 550], "smooth_quant_calibr": 96, "smooth_quant_config": 301, "smooth_quant_en": [145, 417], "smooth_quant_entri": [301, 437, 520], "smooth_quant_scal": 96, "smoother": 282, "smoothquant": [29, 145, 149, 284, 410, 412, 413, 439, 469, 474, 476, 477, 479, 487, 534, 543, 547], "smoothquant_scale_info": [145, 413], "smoothquantcalibr": [125, 283], "smoothquantcalibrationllm": [125, 283], "smoothquantconfig": [284, 301, 303, 437, 439, 474, 479, 480], "smoothquantquant": 412, "smoothquantsampl": 277, "smoothquantscal": [126, 286], "smoothquantscalerllm": [126, 286], "smt": 227, "snapshot": 464, "snip": [169, 195, 531, 542, 553], "snip_momentum": [169, 195, 536, 542], "snip_momentum_progress": 195, "snip_progress": 195, "snipcriterion": 169, "snipmomentumcriterion": 169, "snippet": [520, 531], "so": [31, 90, 153, 225, 280, 442, 469, 471, 472, 476, 477, 480, 487, 490, 492, 493, 527, 531, 537, 539, 544, 546, 547, 550, 551], "social": [488, 543], "socio": 488, "socket": [151, 154, 465, 553], "soft": 195, "softwar": [492, 533, 542, 543, 548], "solut": [128, 150, 380, 474, 476, 479, 487, 492, 493, 494, 527, 543, 547, 548, 550, 552], "solv": [487, 489, 544, 548], "some": [171, 173, 195, 209, 476, 477, 487, 492, 494, 495, 520, 526, 529, 532, 535, 536, 540, 542, 544, 546, 547, 550, 552], "someth": [198, 199, 211, 262, 448], "sometim": [90, 487, 490, 544], "somewhat": 494, "soon": 534, "sort": [195, 271, 476, 547, 552], "sota": 543, "sound": 532, "sourc": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 73, 74, 75, 76, 77, 78, 79, 81, 82, 83, 84, 85, 87, 88, 89, 90, 92, 93, 94, 95, 98, 100, 101, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 131, 132, 133, 134, 135, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 149, 150, 151, 152, 153, 154, 156, 157, 159, 160, 161, 162, 163, 165, 166, 169, 170, 171, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 194, 195, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 216, 217, 218, 221, 223, 224, 225, 226, 227, 228, 230, 231, 232, 234, 235, 236, 238, 239, 240, 241, 242, 243, 244, 245, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 271, 272, 273, 274, 277, 278, 279, 280, 281, 283, 284, 286, 288, 289, 292, 293, 294, 297, 298, 299, 301, 302, 303, 305, 306, 307, 308, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 345, 346, 347, 348, 349, 350, 352, 353, 354, 355, 357, 358, 359, 360, 363, 364, 365, 366, 367, 368, 369, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 383, 384, 385, 387, 389, 390, 391, 392, 396, 397, 398, 399, 401, 403, 404, 405, 406, 408, 409, 411, 412, 413, 415, 416, 417, 418, 419, 420, 421, 422, 423, 425, 426, 427, 429, 430, 431, 432, 433, 435, 437, 438, 439, 441, 442, 443, 444, 445, 447, 448, 451, 452, 454, 456, 457, 458, 460, 461, 462, 463, 464, 465, 466, 467, 490, 492, 533, 536, 543], "space": [151, 181, 182, 187, 195, 198, 199, 232, 235, 262, 266, 271, 278, 477, 481, 487, 488, 489, 493, 494, 495, 520, 542, 544, 550], "spacetobatchnd": [43, 315], "spanbert": 553, "spars": [171, 185, 543], "sparse_dummy_v2": 213, "sparse_gpt": 542, "sparse_ratio": 213, "sparsecategoricalcrossentropyloss": 163, "sparsedummydataset": 213, "sparsegpt": [188, 542], "sparsegptprun": 188, "sparsiti": [175, 177, 178, 180, 181, 182, 185, 187, 190, 192, 195, 465, 469, 476, 492, 531, 536, 553], "sparsity_decay_typ": [195, 536, 542], "speak": [476, 487, 547], "special": [101, 140, 173, 245, 396, 477, 490, 521, 535, 536, 540, 542, 547], "specif": [29, 89, 101, 151, 152, 154, 165, 192, 195, 209, 210, 211, 212, 216, 218, 234, 262, 387, 389, 409, 413, 431, 447, 472, 473, 475, 476, 477, 480, 483, 488, 493, 494, 519, 520, 521, 528, 530, 534, 535, 536, 537, 538, 539, 540, 542, 547, 552], "specifi": [95, 140, 145, 151, 156, 192, 195, 198, 199, 225, 230, 234, 235, 262, 281, 360, 396, 404, 408, 413, 417, 418, 439, 441, 447, 448, 451, 464, 465, 477, 483, 487, 494, 495, 524, 528, 535, 536, 540, 542, 547, 551, 552], "speed": [471, 487, 519, 536, 542, 543, 544, 552], "speedup": [487, 525, 531, 544], "spellcheck": 489, "spent": 552, "spevif": 433, "spiq": [29, 149, 413, 487, 550], "split": [16, 30, 67, 224, 225, 339, 418, 487, 490, 545, 547, 550, 551], "split_shared_bia": 30, "split_shared_input": [61, 333], "splitoper": 26, "splitsharedinputoptim": [67, 339], "spot": [474, 550], "spr": [32, 289], "sprase": 171, "sq": [284, 412, 480, 534, 550], "sq_config": 479, "sq_weight_tensor": 133, "sq_weights_nod": 133, "sqlalchemi": 527, "sqlinearwrapp": 413, "sqrt": [54, 326], "squad": [209, 225, 231, 232, 234, 535, 542, 551, 553], "squadexampl": 225, "squadf1": [234, 535], "squadv1": [225, 551], "squar": [234, 271, 471, 476, 535, 552], "squeez": [63, 335, 490], "squeezenet": 553, "squeezer": 174, "squential": 207, "src": 90, "ssd": [490, 526, 553], "ssd_mobilenet_v1": 536, "ssh": 524, "sst": [542, 553], "st": [209, 535], "stabil": [476, 547], "stabilityai": [474, 550], "stabl": [492, 542, 543], "stablelm": [474, 550], "stack": [420, 492], "stage": [152, 161, 263, 265, 272, 542, 552], "stai": [474, 476, 477, 547, 550], "stand": [542, 552], "stand_norm": [212, 213, 387], "standard": [211, 225, 489, 494, 520, 526, 535, 551, 552], "star": 489, "start": [154, 195, 225, 230, 267, 469, 532, 543, 551, 552, 554], "start_epoch": 536, "start_posit": 225, "start_step": [180, 195, 536, 542], "stat": [154, 447], "state": [135, 174, 476, 483, 495, 542], "state_dict": [135, 398, 476, 524, 547], "statement": 520, "static": [28, 29, 32, 149, 173, 195, 262, 278, 287, 288, 289, 299, 301, 303, 413, 416, 417, 437, 439, 442, 458, 477, 492, 493, 494, 495, 526, 529, 531, 536, 545, 550, 552, 553], "static_config": 479, "static_graph": 173, "static_group": [439, 451, 476, 547], "static_qu": [282, 394, 478, 520], "static_quant_entri": [301, 437], "static_quant_export": 458, "staticmethod": [124, 379], "staticqu": [414, 416], "staticquantconfig": [288, 289, 299, 303, 391, 437, 439, 475, 478, 479, 480, 481], "staticquantquant": 416, "statist": [161, 465, 466, 471], "statu": [173, 477, 482, 488, 521, 539, 540, 542], "std": [221, 225, 536, 551], "std_valu": 221, "stderr": [391, 465], "step": [169, 179, 180, 181, 182, 186, 187, 190, 195, 448, 470, 474, 475, 476, 487, 494, 495, 523, 524, 536, 541, 542, 546, 547, 549, 550, 552], "step1": 278, "step2": 278, "step3": 278, "step4": 278, "step5": 278, "step_siz": 550, "still": [477, 479, 487, 519, 536, 543, 544, 546], "stock": [32, 289, 550], "stop": [153, 195, 469, 481, 536, 552], "stopgradi": [65, 337], "storag": [140, 396, 476, 487, 535, 547, 550], "store": [125, 169, 170, 173, 180, 181, 182, 183, 184, 185, 186, 187, 189, 191, 195, 211, 283, 408, 413, 530], "storywrit": 553, "str": [1, 29, 30, 31, 125, 135, 140, 141, 143, 144, 145, 146, 152, 154, 156, 160, 161, 163, 165, 170, 173, 194, 195, 209, 210, 211, 218, 221, 225, 227, 228, 230, 232, 234, 251, 256, 258, 260, 261, 277, 280, 281, 283, 299, 302, 303, 305, 391, 396, 398, 399, 404, 406, 408, 409, 413, 415, 417, 418, 425, 427, 431, 433, 435, 437, 439, 441, 442, 443, 445, 447, 451, 454, 457, 458, 461, 465, 466, 476, 477, 480, 520, 521, 535, 551], "str2arrai": 465, "str_label": 535, "straightforward": [476, 480, 487, 542, 547, 550], "strategi": [1, 145, 187, 195, 196, 211, 226, 469, 481, 487, 492, 493, 494, 495, 499, 519, 520, 521, 524, 531, 536, 543, 544, 546, 547, 548], "strategy_kwarg": [195, 549, 552], "strategy_registri": [274, 552], "stream": [391, 465, 553], "streamlin": [532, 543], "stretch": 471, "strftime": 195, "strict": 451, "stride": [90, 225, 292, 294, 297, 298, 551], "string": [30, 101, 133, 138, 140, 151, 161, 163, 165, 173, 175, 180, 188, 189, 190, 192, 195, 211, 227, 230, 239, 243, 385, 390, 391, 396, 397, 420, 447, 451, 454, 465, 471, 480, 535, 551], "strip": [52, 53, 55, 68, 69, 133, 324, 325, 327, 340, 341, 385], "strip_equivalent_nod": [61, 133, 333, 385], "strip_unused_lib": [133, 385], "strip_unused_nod": [61, 133, 333, 385], "stripequivalentnodesoptim": [68, 340], "stripunusednodesoptim": [69, 341], "stroke": 552, "structur": [174, 185, 186, 195, 279, 420, 465, 469, 477, 487, 531, 542, 543, 544, 553], "stsb": 553, "student": [162, 166, 195, 209, 523, 553], "student1_layer_name1": 195, "student1_layer_name2": 195, "student2_layer_name1": 195, "student2_layer_name2": 195, "student_layer_nam": 195, "student_layer_output_process": 195, "student_loss": 523, "student_model": [163, 195, 536], "student_output": 523, "style": [203, 216, 281, 520, 530], "style_fold": 216, "style_transfer_dataset": 215, "styletransferdataset": 216, "sub": [51, 145, 151, 173, 323, 417, 520, 552], "sub_class": [234, 262], "sub_modul": 520, "subclass": [3, 21, 146, 165, 175, 180, 188, 190, 204, 208, 211, 218, 225, 234, 245, 274, 413, 493], "subfold": 211, "subgraph": [40, 51, 90, 144, 312, 323, 545, 552], "subgraphstyl": 552, "subject": 533, "submit": [489, 543], "subpixel": 221, "subprocess": [154, 520, 521], "subsect": [487, 550], "subsequ": [184, 494], "subset": [211, 214], "subsidiari": 533, "substanti": 545, "substitut": [301, 305, 480], "success": 532, "successfulli": [490, 492, 524, 543], "successor": [76, 77, 78, 79, 347, 348, 349, 350], "sudo": 527, "suffici": 549, "suffix": [133, 385], "suggest": [477, 490, 520, 549], "suit": 532, "suitabl": 477, "sum": [195, 234], "summar": [131, 383, 520], "summari": [151, 154, 448, 553], "summary_benchmark": 151, "summary_latency_throughput": 154, "super": 232, "supplement": 480, "suppli": 1, "support": [1, 29, 30, 31, 82, 89, 149, 152, 163, 165, 170, 176, 183, 187, 195, 198, 199, 208, 209, 211, 218, 221, 225, 226, 234, 235, 239, 245, 262, 272, 278, 281, 353, 413, 437, 447, 448, 454, 460, 461, 465, 467, 469, 470, 475, 478, 481, 487, 492, 494, 520, 529, 534, 536, 543, 546, 549, 552], "supported_lay": [145, 420, 433], "supported_op_typ": [48, 320], "suppos": [487, 550], "suppress": [476, 487, 547, 550], "sure": [175, 180, 188, 190, 492, 518], "surg": [140, 396], "surrog": 552, "suyu": 533, "sweet": [474, 550], "switch": [70, 342], "switch_optim": [61, 333], "switchoptim": [70, 342], "sy": [391, 451, 465, 520], "sym": [29, 30, 31, 409, 413, 433, 451, 494, 495, 528, 544, 547], "sym_full_rang": 547, "sym_model": 1, "symbol": [1, 30, 144, 145, 227, 235, 262, 490, 538], "symbol_r": 227, "symbolblock": 1, "symbolic_trac": 136, "symmetr": [98, 409, 413, 461, 480, 495, 544, 547, 551, 552], "symnet": 1, "synchron": [445, 552], "syntax": 528, "sys_nic": 492, "system": [135, 140, 151, 154, 396, 465, 472, 473, 483, 518, 539, 542, 553], "systemat": [474, 479, 550], "szymon": 519, "t": [30, 52, 53, 55, 128, 140, 150, 175, 195, 225, 232, 324, 325, 327, 380, 396, 473, 474, 475, 480, 482, 490, 493, 520, 524, 536, 537, 542, 544, 547, 552], "t10k": 211, "t5": 542, "t5norm": 550, "tab": 232, "tabl": [173, 184, 465, 472, 492, 495, 526, 529, 539, 553], "table_entri": 465, "taco": [492, 543], "tag": [140, 243, 390, 396, 487, 550], "tail": 476, "tailor": [476, 483], "take": [3, 175, 195, 198, 199, 203, 225, 234, 235, 262, 266, 387, 448, 473, 476, 480, 483, 488, 490, 492, 521, 528, 536, 542, 544, 546, 547, 551, 552], "taken": [198, 199, 235, 262, 448, 544], "tamper": [140, 396], "tar": 211, "target": [1, 29, 30, 87, 145, 173, 190, 192, 195, 266, 288, 406, 420, 461, 471, 477, 524, 536, 542, 551, 552], "target_boxes_num": 535, "target_depth": [145, 417], "target_dtyp": [277, 406], "target_height": [225, 551], "target_lay": 173, "target_linear": 174, "target_op_lut": 173, "target_spars": [175, 195, 536, 542], "target_sparsity_ratio": 180, "target_width": [225, 551], "targetspac": 266, "task": [128, 209, 216, 234, 380, 471, 474, 476, 483, 487, 523, 526, 531, 535, 536, 542, 545, 547, 550, 553], "taskdataset": 553, "taskset": 483, "tbb": 527, "td": 552, "teacher": [162, 195, 523, 536, 553], "teacher_layer_nam": 195, "teacher_layer_name1": 195, "teacher_layer_name2": 195, "teacher_layer_output_process": 195, "teacher_logit": 536, "teacher_model": [163, 195, 523, 536], "team": [159, 232, 488, 546], "technic": 492, "techniqu": [226, 467, 469, 475, 480, 481, 487, 492, 529, 531, 536, 541, 542, 543, 544, 553], "technologi": [211, 472, 534, 536, 539], "tel2p1": 553, "tell": [140, 234, 262, 396], "temp_path": [125, 283], "temperatur": [163, 195, 536], "templat": [188, 536, 542], "template_config": 192, "temporari": [125, 145, 283, 413, 465, 488], "temporarili": 488, "ten": 483, "tencent": [492, 543], "tend": 542, "tensor": [1, 2, 3, 30, 31, 55, 90, 125, 133, 135, 140, 141, 145, 169, 170, 179, 180, 181, 182, 183, 184, 185, 186, 187, 189, 191, 195, 225, 243, 271, 283, 327, 385, 390, 391, 396, 398, 404, 406, 408, 411, 412, 413, 417, 422, 423, 425, 426, 433, 438, 442, 456, 458, 461, 464, 465, 470, 471, 472, 477, 480, 490, 495, 520, 521, 539, 542, 544, 548, 551, 552], "tensor2tensor": 228, "tensor_data": [74, 346, 391, 465, 466], "tensor_dict": 493, "tensor_dtyp": 90, "tensor_nam": [30, 133, 140, 141, 385, 396, 398], "tensor_to_nod": 1, "tensor_v": 133, "tensor_valu": 30, "tensorboard": [161, 195, 454, 465, 493, 536], "tensorcollector": 1, "tensordataset": 209, "tensorflow": [37, 39, 60, 61, 62, 72, 80, 86, 87, 88, 89, 90, 91, 95, 96, 97, 99, 102, 115, 125, 126, 127, 130, 133, 163, 165, 191, 195, 208, 209, 210, 211, 214, 216, 218, 225, 226, 228, 230, 234, 235, 243, 256, 257, 260, 261, 262, 272, 457, 458, 465, 479, 489, 493, 494, 500, 519, 520, 521, 523, 525, 528, 529, 531, 536, 537, 538, 539, 542, 543, 549, 550, 552], "tensorflow1": 208, "tensorflow_addon": 165, "tensorflow_dataload": 260, "tensorflow_itex": [211, 214, 216, 218, 521], "tensorflow_itexadaptor": [32, 289], "tensorflow_model": [237, 260], "tensorflowadam": 165, "tensorflowadamw": 165, "tensorflowadaptor": [32, 289], "tensorflowbasemodel": [243, 260, 390], "tensorflowbertdataload": 208, "tensorflowbertdataset": 209, "tensorflowcheckpointmodel": [243, 390], "tensorflowcifar10": 211, "tensorflowcifar100": 211, "tensorflowcocomap": 234, "tensorflowconfig": 289, "tensorflowconfigconvert": 289, "tensorflowcriterion": 163, "tensorflowcroptoboundingbox": 225, "tensorflowcrossentropyloss": 163, "tensorflowdataload": [208, 260], "tensorflowdataset": 211, "tensorflowfashionmnist": 211, "tensorflowfilt": 218, "tensorflowglobalconfig": 389, "tensorflowimagenetdataset": 214, "tensorflowimagenetraw": 214, "tensorflowimagerecord": 211, "tensorflowknowledgedistillationloss": 163, "tensorflowknowledgedistillationlossextern": 163, "tensorflowknowledgedistillationlosswrapp": 163, "tensorflowllmmodel": [243, 390], "tensorflowmap": 234, "tensorflowmetr": 234, "tensorflowmnist": 211, "tensorflowmodel": [243, 390], "tensorflowmodelzoobertdataload": 208, "tensorflowmodelzoobertdataset": [209, 210], "tensorflowoptim": 165, "tensorflowparserfactori": 252, "tensorflowprofilingpars": 253, "tensorflowqatmodel": 243, "tensorflowqdqtoonnxqdqconvert": 127, "tensorflowqueri": [32, 289, 493], "tensorflowrandomhorizontalflip": 225, "tensorflowrandomverticalflip": 225, "tensorflowresizecropimagenettransform": 221, "tensorflowresizewithratio": 225, "tensorflowsavedmodelmodel": [243, 390], "tensorflowsgd": 165, "tensorflowshiftrescal": 221, "tensorflowsparsecategoricalcrossentropi": 163, "tensorflowtfrecorddataset": 211, "tensorflowtopk": 234, "tensorflowtransform": 225, "tensorflowtranspos": 225, "tensorflowtransposelastchannel": 221, "tensorflowvocmap": 234, "tensorflowvocrecord": 211, "tensorflowwrapfunct": 225, "tensorproto": [30, 90], "tensorrt": [30, 519, 537, 544], "tensorrtexecutionprovid": [537, 544], "tensors_kl": 1, "tensors_minmax": 1, "teq": [428, 437, 439, 477, 492, 543, 545, 547], "teq_arg": 476, "teq_quantize_entri": 437, "teqconfig": [437, 439, 451, 476], "teqlinearfakequ": [142, 429], "tequant": 432, "term": [162, 181, 182, 187, 189, 477, 480, 489, 519, 533, 535, 540, 541, 552], "test": [151, 195, 225, 489, 492, 553], "test_func": 524, "text": [90, 188, 224, 225, 227, 232, 472, 474, 476, 487, 526, 533, 539, 542, 543, 547, 550, 551, 553], "tf": [90, 101, 126, 133, 173, 192, 208, 209, 210, 211, 225, 241, 243, 286, 303, 305, 361, 385, 387, 389, 390, 391, 478, 480, 492, 520, 524, 532, 538, 543, 546, 551], "tf1": [208, 538], "tf2": 538, "tf2onnx": [195, 455], "tf2onnx_convert": 96, "tf2onnx_util": 86, "tf2onnxconfig": [195, 526], "tf_criteria": 170, "tf_modul": 261, "tf_to_fp32_onnx": 457, "tf_to_int8_onnx": 457, "tfdatadataload": 208, "tfmodelzoocollecttransform": 225, "tfrecord": [209, 210, 211], "tfslimnetsfactori": [241, 391], "tfsquadv1modelzooposttransform": 225, "tfsquadv1posttransform": 225, "th": [74, 75, 346], "thalaiyasingam": 542, "than": [40, 133, 209, 225, 312, 391, 418, 443, 465, 472, 476, 487, 492, 518, 530, 539, 540, 541, 542, 544, 547, 549, 551, 552], "theblok": 492, "thei": [140, 281, 396, 473, 488, 520, 528, 536, 540], "them": [140, 173, 209, 396, 476, 477, 487, 490, 495, 521, 526, 528, 530, 532, 541, 542, 547, 552], "themselv": 544, "theoret": [476, 487, 544, 547], "therefor": [482, 487, 490, 536, 542, 544, 545, 548, 550], "thi": [29, 71, 95, 117, 124, 128, 132, 135, 138, 140, 145, 150, 152, 153, 154, 162, 166, 171, 173, 175, 177, 178, 179, 180, 184, 185, 186, 187, 188, 189, 190, 195, 198, 199, 208, 209, 210, 211, 212, 213, 214, 216, 225, 227, 230, 231, 232, 234, 235, 245, 262, 266, 271, 280, 281, 343, 360, 372, 379, 380, 384, 387, 396, 397, 413, 417, 442, 448, 464, 465, 469, 471, 473, 474, 475, 476, 478, 479, 480, 481, 487, 488, 489, 490, 492, 493, 494, 495, 519, 520, 521, 523, 524, 526, 527, 528, 531, 532, 533, 534, 535, 536, 537, 538, 542, 544, 546, 547, 548, 549, 550, 551, 552], "think": [476, 547], "third": [230, 489, 533], "those": [59, 140, 271, 331, 396, 465, 475, 480, 487, 523, 530, 536, 537, 541, 542, 544, 552], "though": [487, 550], "thread": [151, 195, 257, 261, 521, 527], "threaten": 488, "three": [59, 192, 209, 263, 265, 331, 473, 477, 481, 487, 490, 493, 494, 519, 532, 537, 541, 544, 546, 549, 550], "threshold": [1, 147, 452, 460, 535], "through": [135, 198, 199, 234, 235, 262, 475, 476, 477, 487, 492, 518, 528, 530, 531, 535, 540, 541, 542, 544, 547], "throughput_pattern": 482, "throw": 521, "thu": [230, 487, 536, 542, 544], "thudm": 534, "tian": 533, "tiiuae": [474, 534, 550, 553], "tile": 520, "till": [161, 465, 552], "tim": [476, 487, 547], "time": [133, 140, 161, 195, 225, 234, 245, 266, 385, 391, 396, 465, 475, 476, 477, 479, 481, 483, 487, 492, 494, 521, 524, 527, 536, 540, 542, 543, 544, 547, 549, 550, 551, 552], "time_limit": 465, "timeout": [195, 536, 552], "tinybert": 553, "tip": 483, "titl": [465, 533, 552], "tloss": 524, "tmp_file_path": [391, 465], "to_numpi": 30, "toarrai": [225, 551], "todo": [156, 209, 212, 230, 278, 387, 420, 443], "togeth": [152, 195, 225, 532, 543, 551], "togethercomput": [474, 550], "token": [209, 222, 225, 227, 228, 418, 431, 451, 461, 474, 476, 487, 535, 536, 547, 549, 550, 551, 552], "token_is_max_context": 225, "token_to_orig_map": 225, "token_type_id": [209, 536], "tokenzi": 224, "toler": [153, 480], "tolerable_loss": [153, 195, 481, 536, 552], "tolist": 550, "tondarrai": 551, "tondarraytransform": 225, "tool": [3, 133, 385, 457, 465, 487, 492, 493, 536, 542, 543, 544], "toolchain": [527, 543], "toolkit": [469, 490, 532, 543], "top": [225, 234, 489, 535, 551], "top1": [448, 535, 542, 544, 553], "topilimag": 551, "topk": [234, 262, 524, 535, 536, 544], "torch": [134, 135, 136, 137, 140, 141, 142, 143, 144, 145, 149, 153, 160, 170, 173, 174, 176, 184, 195, 226, 235, 262, 458, 461, 464, 470, 471, 472, 473, 474, 475, 476, 481, 483, 487, 490, 495, 496, 524, 526, 527, 529, 536, 537, 538, 539, 544, 547, 550], "torch2onnx": [195, 455], "torch2onnxconfig": [195, 526], "torch_dtyp": [492, 495], "torch_load": 137, "torch_model": 237, "torch_to_fp32_onnx": 458, "torch_to_int8_onnx": 458, "torch_util": [439, 545, 550], "torchbaseconfig": 439, "torchdynamo": 477, "torchfunctyp": 406, "torchimport": 477, "torchscript": [441, 526, 545, 550], "torchsmoothqu": [412, 413, 550], "torchvis": [225, 471, 492, 525], "toronto": 211, "torr": 542, "total": [30, 180, 225, 234, 418, 476, 542, 547, 551, 553], "total_block_arg": 145, "total_block_kwarg": 145, "total_execution_tim": 251, "total_valu": [145, 433], "totensor": [536, 551], "tow": 524, "toward": 488, "tpe": 197, "tpetunestrategi": 199, "tqdm": [30, 536], "trace": [135, 144, 145, 173, 195, 269, 408, 412, 413, 417, 438, 442, 458, 475, 477, 490, 552], "trace_and_fuse_sub_graph": 144, "trace_gptq_target_block": 420, "traceabl": 490, "traced_model": [144, 413], "tracer": 490, "track": [161, 549], "trackabl": [133, 385], "trade": [476, 487, 547], "tradit": [480, 542], "train": [29, 42, 65, 149, 162, 181, 182, 185, 187, 195, 198, 199, 209, 211, 225, 226, 262, 314, 337, 413, 420, 439, 454, 472, 473, 474, 475, 476, 477, 479, 481, 492, 493, 494, 499, 523, 526, 529, 531, 537, 539, 541, 543, 545, 547, 549, 550, 552], "train_cfg": 454, "train_dataload": [536, 542, 544], "train_dataset": [524, 544], "train_fn": 476, "train_fun": 536, "train_func": [448, 524, 536, 544], "train_kwarg": 524, "train_load": 524, "train_loop": [448, 536, 541], "train_sampl": 524, "trainabl": [432, 476, 492, 543, 547], "trainableequivalenttransform": 432, "trainer": 536, "training_arg": 536, "training_func": 536, "training_func_for_nc": 523, "trane": 477, "transact": 550, "transfer": [162, 216, 487, 523, 536, 550], "transform": [30, 35, 128, 130, 131, 132, 143, 187, 209, 210, 211, 212, 213, 214, 216, 218, 220, 307, 380, 382, 383, 384, 387, 406, 412, 413, 417, 420, 432, 439, 445, 474, 475, 476, 479, 487, 490, 492, 519, 523, 524, 525, 529, 534, 536, 542, 543, 546, 547, 550, 552], "transform_func": 225, "transform_graph": [96, 361], "transform_list": [225, 551], "transform_registri": 225, "transform_typ": 225, "transformer_block": 420, "transformerbasedmodelblockpatterndetector": [143, 417], "transformers_nam": 420, "transformers_pr": 420, "translat": [227, 228, 472, 539, 542, 552], "translation_corpu": 228, "transpos": [30, 58, 179, 221, 225, 330, 457, 547, 551], "travers": [481, 494, 495, 547, 552], "treat": [140, 396, 521], "tree": [188, 278], "tri": [152, 195, 520, 552], "trial": [153, 481, 552], "trigger": [151, 154, 180, 482], "troll": 488, "trt_env_setup": 30, "true": [1, 30, 31, 70, 98, 131, 133, 140, 151, 153, 195, 207, 209, 211, 212, 224, 225, 228, 234, 245, 262, 277, 281, 292, 293, 294, 298, 299, 303, 342, 383, 385, 387, 396, 398, 406, 412, 413, 418, 420, 423, 427, 429, 431, 432, 433, 439, 442, 451, 454, 458, 461, 464, 465, 470, 474, 475, 476, 477, 478, 480, 481, 482, 487, 494, 521, 524, 528, 535, 536, 544, 545, 547, 550, 551, 552], "true_sequenti": [439, 451, 476, 547], "truncat": [209, 225, 418, 551], "trust": [140, 396], "trust_remote_cod": [431, 441], "truth": [231, 232], "try": [207, 243, 390, 480, 487, 490, 492, 527, 542, 544, 550, 552], "try_cnt": [133, 385], "try_loading_kera": [243, 390], "tunabl": [152, 156], "tunable_typ": 156, "tune": [1, 151, 152, 153, 156, 159, 195, 198, 199, 209, 211, 235, 245, 262, 263, 264, 265, 266, 267, 268, 269, 271, 272, 273, 274, 277, 278, 279, 280, 302, 413, 438, 439, 448, 465, 473, 474, 475, 476, 477, 481, 484, 492, 493, 494, 519, 520, 521, 524, 529, 531, 533, 536, 537, 540, 542, 543, 546, 548, 549], "tune_cfg": [1, 134, 145, 412, 413, 417, 447, 493, 495, 552], "tune_config": [153, 302, 438, 473, 477, 478, 479, 480, 481, 494], "tuner": [198, 199, 235, 262, 448, 544], "tunestrategi": [274, 552], "tunestrategymeta": 274, "tuning_cfg_to_fw": 494, "tuning_config": 153, "tuning_criterion": [195, 536, 540, 549, 552], "tuning_history_path": 465, "tuning_items_prior": 277, "tuning_order_lst": 277, "tuning_param": 155, "tuning_sampl": 276, "tuning_spac": [276, 277, 279], "tuning_strategi": 195, "tuning_struct": [276, 277, 278], "tuningconfig": [153, 302, 438, 473, 477, 478, 479, 480, 481], "tuningcriterion": [195, 536, 540, 549, 552], "tuningitem": 278, "tuninglogg": [153, 159], "tuningmonitor": 153, "tuningord": 277, "tuningparam": 156, "tuningsampl": 277, "tuningspac": [277, 278], "tupl": [1, 90, 133, 145, 153, 195, 198, 199, 221, 225, 235, 262, 277, 302, 305, 399, 406, 408, 411, 412, 413, 417, 418, 425, 426, 435, 437, 438, 439, 442, 447, 448, 458, 464, 477, 480, 494, 520, 535, 536, 544, 551], "turbo": 553, "turn": [535, 545], "tutori": [469, 490, 543], "twitter": 543, "two": [133, 135, 140, 151, 174, 179, 186, 190, 211, 216, 230, 272, 396, 465, 471, 472, 473, 475, 476, 479, 481, 484, 487, 489, 490, 520, 521, 524, 526, 528, 536, 537, 539, 542, 544, 546, 547, 549, 550, 552], "txt": [214, 527, 532], "type": [1, 3, 29, 30, 31, 59, 81, 90, 101, 107, 117, 125, 133, 134, 135, 140, 145, 146, 152, 153, 154, 156, 160, 161, 163, 165, 173, 174, 175, 180, 188, 189, 190, 192, 194, 195, 207, 209, 211, 218, 225, 227, 228, 230, 234, 243, 245, 266, 267, 274, 278, 280, 281, 283, 301, 305, 331, 352, 372, 385, 390, 391, 396, 398, 403, 404, 406, 408, 409, 411, 413, 417, 418, 420, 425, 426, 427, 431, 433, 435, 437, 438, 439, 442, 447, 458, 464, 465, 469, 471, 472, 473, 474, 475, 476, 477, 478, 480, 483, 493, 494, 524, 526, 528, 531, 536, 537, 539, 544, 545, 547, 549, 551, 552], "typealia": 520, "types_to_splic": [65, 337], "typic": [492, 523, 525, 542, 553], "u": [128, 150, 380], "ubuntu": 532, "ubuntu22": 492, "ubyt": 211, "uint4": 495, "uint8": [30, 221, 230, 280, 409, 433, 439, 480, 487, 493, 528, 544, 551], "ultim": [487, 544], "ultra": [492, 532, 553], "unaccept": 488, "unari": 27, "unary_op": 16, "unarydirect8bitoper": 27, "unaryoper": 27, "unbalanc": 553, "uncas": [209, 225, 551, 553], "uncertain": 542, "undefin": [140, 192, 396], "under": [95, 195, 211, 360, 391, 447, 461, 464, 481, 489, 492, 533, 535, 536, 541, 542, 543, 545, 547, 552], "underli": [52, 53, 55, 140, 324, 325, 327, 396], "understand": [469, 487, 544], "understudi": 227, "unicod": 224, "unicodedecodeerror": [140, 396], "unicoderegex": 227, "unifi": [159, 392, 435, 493, 494, 495, 521, 530, 531, 535, 536, 538], "uniform": [476, 519, 547], "uniformli": [476, 547], "union": [152, 234, 435, 438, 439, 447, 448, 477, 480, 535], "uniqu": [230, 487, 544], "unique_id": 225, "unit": [175, 293, 489, 542], "unit_scal": 471, "unk": 224, "unk_token": 224, "unless": [140, 396, 528], "unlik": 480, "unnecessari": 536, "unpack": [421, 429], "unpack_weight": 429, "unpack_zp": 429, "unpackedweightonlylinearparam": 429, "unpickl": [138, 140, 396, 397], "unpicklingerror": [138, 397], "unpreced": 542, "unquant": 406, "unquantized_node_set": 406, "unsaf": [140, 396], "unseen": [480, 487, 544], "unset": 31, "unsign": [145, 280, 495, 547], "unstructur": [195, 531, 542, 553], "unsupport": [526, 536, 542], "until": [413, 471, 494, 552], "untrac": 490, "untrust": [140, 396], "unus": [69, 133, 341, 385, 447], "unwelcom": 488, "up": [1, 85, 184, 225, 355, 417, 471, 487, 492, 524, 525, 527, 528, 531, 542, 543, 544, 549, 551, 552], "up1": 528, "up2": 528, "updat": [59, 141, 145, 169, 175, 192, 234, 262, 331, 398, 413, 417, 469, 476, 527, 534, 535, 536, 542, 547, 550, 552], "update_config": 195, "update_modul": [141, 398], "update_param": 192, "update_sq_scal": [145, 413], "upgrad": 536, "upload": 531, "upstream": [431, 441], "url": [211, 420, 489, 492, 532, 533, 542], "us": [1, 3, 21, 29, 30, 31, 33, 34, 55, 88, 90, 101, 126, 135, 140, 145, 151, 152, 154, 161, 163, 165, 169, 173, 175, 180, 184, 185, 188, 190, 191, 195, 198, 199, 207, 208, 209, 210, 211, 212, 213, 216, 224, 225, 227, 228, 230, 234, 245, 257, 261, 262, 266, 269, 271, 274, 278, 280, 281, 286, 288, 289, 301, 305, 306, 327, 387, 391, 396, 404, 405, 406, 408, 409, 412, 413, 416, 417, 418, 425, 426, 427, 431, 433, 438, 441, 442, 443, 447, 448, 451, 452, 453, 454, 457, 458, 459, 461, 465, 471, 472, 473, 474, 475, 476, 477, 478, 480, 481, 483, 487, 488, 489, 490, 493, 494, 518, 519, 520, 523, 524, 526, 528, 529, 530, 533, 536, 537, 538, 539, 540, 542, 543, 544, 545, 546, 547, 548, 549, 551, 552, 553], "usabl": 492, "usag": [145, 152, 153, 156, 208, 230, 281, 391, 433, 443, 444, 447, 477, 478, 483, 487, 494, 524, 525, 540, 547, 551], "use_auto_clip": [439, 476], "use_auto_scal": [439, 476], "use_bf16": [33, 34, 306], "use_bia": [292, 293, 294, 298], "use_bp": 228, "use_double_qu": [439, 476], "use_full_length": 547, "use_full_rang": [439, 476], "use_layer_wis": [420, 439, 451, 476], "use_max_length": [420, 547], "use_mse_search": [439, 451, 476], "use_optimum_format": [429, 461, 547], "use_sym": [439, 476, 481], "user": [140, 151, 165, 173, 185, 192, 195, 198, 199, 211, 214, 218, 225, 234, 235, 245, 262, 267, 280, 396, 406, 413, 417, 439, 447, 448, 465, 472, 473, 474, 475, 476, 477, 478, 479, 480, 481, 483, 487, 490, 493, 494, 495, 499, 518, 520, 521, 523, 526, 528, 531, 534, 535, 536, 537, 538, 539, 540, 541, 542, 543, 544, 545, 546, 548, 550, 551, 552], "user_cfg": [413, 417], "user_config": 192, "user_eval_fns1": 153, "user_eval_fns2": 153, "user_eval_fns3": 153, "user_eval_fns4": 153, "user_metr": [234, 262], "user_model": [472, 529, 539], "user_obj_cfg": 245, "user_object": 245, "user_postprocess": 223, "user_processor_typ": 447, "userfloatmodel": [470, 475], "usr": 527, "usr_cfg": 245, "usual": [209, 480, 487, 494, 541, 542, 544, 545, 550], "utf": [140, 224, 396], "util": [0, 4, 90, 95, 96, 124, 127, 134, 135, 136, 137, 144, 152, 153, 155, 164, 170, 193, 195, 226, 228, 270, 290, 301, 302, 304, 305, 395, 402, 407, 410, 414, 418, 428, 436, 437, 439, 469, 471, 480, 483, 494, 495, 496, 519, 520, 524, 536, 542, 544, 552], "v": [542, 552], "v0": [474, 534, 550], "v1": [133, 221, 231, 232, 234, 243, 385, 390, 474, 485, 524, 526, 527, 535, 538, 542, 548, 549, 550, 553], "v14": 227, "v2": [135, 269, 474, 521, 524, 526, 527, 534, 548, 550, 552, 553], "v3": [485, 553], "v4": 553, "v5": 489, "v5s6": 553, "val": [133, 192, 211, 214, 426, 536], "val2017": 210, "val_dataload": [478, 536, 544], "val_dataset": [478, 536, 544], "val_load": 544, "val_map": 214, "valid": [40, 52, 53, 90, 159, 180, 183, 192, 195, 211, 230, 243, 292, 294, 297, 298, 312, 324, 325, 390, 409, 492, 493, 525, 528, 531, 533, 536, 542, 544, 547, 548], "valid_keras_format": 391, "valid_mixed_precis": 528, "valid_reshape_input": [52, 53, 324, 325], "validate_and_inference_input_output": [243, 390], "validate_graph_nod": [243, 390], "valu": [3, 30, 31, 41, 52, 53, 55, 74, 75, 90, 128, 133, 140, 145, 150, 151, 169, 173, 174, 184, 191, 192, 195, 198, 199, 209, 212, 213, 221, 225, 230, 234, 235, 262, 266, 271, 278, 280, 281, 313, 324, 325, 327, 346, 380, 387, 396, 398, 413, 417, 425, 429, 448, 452, 454, 465, 470, 471, 472, 473, 474, 476, 479, 480, 487, 490, 494, 495, 519, 528, 535, 536, 537, 539, 540, 542, 544, 547, 550, 551, 552], "valuabl": 542, "value_layer_nam": 184, "valueerror": [52, 53, 55, 145, 230, 281, 324, 325, 327, 433, 527], "valueinfo": 30, "values_from_const": [52, 53, 55, 324, 325, 327], "vanhouck": 519, "vanilla": [493, 494, 531], "vari": [542, 550, 553], "variabl": [30, 138, 151, 189, 195, 211, 266, 280, 397, 443, 473, 477, 483, 542, 552], "varianc": [128, 150, 380], "variant": 205, "varieti": [477, 481, 525, 552], "variou": [235, 392, 472, 475, 477, 480, 495, 531, 539, 542, 545], "vault": 492, "vcvtne2ps2bf16": [473, 537], "vcvtneps2bf16": [473, 537], "vdpbf16p": [473, 537], "vecchio": 532, "vector": 473, "ventura": 532, "verbos": [30, 266, 425, 458], "veri": [469, 476, 487, 536, 544, 547, 552], "verifi": [526, 534], "version": [1, 39, 89, 142, 145, 173, 195, 226, 311, 429, 445, 457, 458, 469, 474, 488, 490, 492, 493, 520, 528, 532, 533, 536, 543, 550, 552], "version1": [133, 391, 465], "version1_eq_version2": [133, 391, 465], "version1_gt_version2": [133, 391, 465], "version1_gte_version2": [133, 391, 465], "version1_lt_version2": [133, 391, 465], "version1_lte_version2": [133, 391, 465], "version2": [133, 391, 465], "vertic": [179, 225, 551], "vgg": 553, "vgg16": [526, 553], "vgg19": 553, "via": [439, 476, 487, 488, 492, 524, 531, 536, 542, 543], "view": [489, 492, 525, 548], "viewpoint": 488, "vincent": 519, "violat": [138, 397], "virtual": [280, 543], "visibl": 482, "vision": [471, 487, 492, 526, 550], "visit": 553, "visual": [195, 549, 552], "vit": 553, "vmware": 543, "vnni": [487, 525, 531, 544], "voc": [211, 234], "vocab": 224, "vocab_fil": [224, 225, 551], "vocabulari": [209, 224, 225, 551], "vocmap": 535, "vscode": 520, "vtune": 533, "w": [31, 225, 420, 474, 487, 542, 550, 551], "w8a8": [405, 470, 475, 476, 487, 545, 547], "w8a8pt2equant": 405, "w_algo": 439, "w_dq": [487, 550], "w_dtype": [439, 472, 474, 475, 539], "w_fp32": [128, 150, 380], "w_granular": 439, "w_int8": [128, 150, 380], "w_q": [487, 550], "w_scale": [487, 550], "w_sym": 439, "wa": [140, 195, 396, 472, 474, 493, 536, 539, 543, 552], "wai": [173, 210, 211, 214, 243, 390, 476, 479, 487, 495, 521, 535, 536, 541, 542, 544, 547, 550, 552], "wanda": 170, "want": [52, 53, 55, 173, 195, 207, 209, 267, 324, 325, 327, 448, 490, 493, 521, 524, 536, 540, 544, 547, 549, 552], "waq": 550, "warm": 417, "warmup": [195, 518, 536], "warn": [413, 462, 520], "wasn": [140, 396], "wasserblat": 542, "we": [29, 30, 52, 53, 55, 59, 71, 128, 140, 149, 150, 151, 153, 173, 177, 184, 195, 208, 227, 230, 269, 324, 325, 327, 331, 343, 380, 396, 413, 469, 470, 474, 475, 476, 477, 479, 480, 481, 482, 483, 487, 488, 490, 492, 493, 494, 495, 520, 521, 524, 526, 528, 529, 534, 535, 536, 540, 541, 542, 544, 545, 547, 548, 549, 550, 552], "web": 492, "websit": 532, "wechat": [492, 543], "wei": [476, 487, 547, 550], "weight": [29, 30, 31, 45, 46, 107, 125, 126, 128, 133, 135, 145, 150, 153, 169, 170, 174, 177, 178, 179, 180, 181, 182, 183, 185, 186, 187, 189, 191, 195, 234, 262, 269, 278, 280, 283, 286, 317, 318, 380, 398, 413, 422, 428, 429, 431, 432, 433, 439, 441, 458, 465, 466, 469, 470, 471, 474, 475, 477, 478, 479, 480, 481, 493, 494, 495, 519, 523, 528, 529, 530, 534, 536, 540, 542, 543, 544, 545, 550, 552], "weight_algorithm": 303, "weight_bit": 494, "weight_clip": [303, 413], "weight_config": [31, 420, 432], "weight_correct": [148, 195, 544], "weight_decai": 536, "weight_dict": 135, "weight_dtyp": [299, 303, 451, 478], "weight_empir": [128, 380], "weight_granular": [299, 303, 478], "weight_max_lb": 413, "weight_max_valu": [292, 293, 294, 297, 298], "weight_min_valu": [292, 293, 294, 297, 298], "weight_name_map": [125, 283], "weight_onli": [4, 195, 394, 439, 464, 472, 520, 539, 545, 547], "weight_shap": 31, "weight_slim": [172, 184], "weight_sym": [299, 303, 478, 480, 481], "weight_tensor": 465, "weight_typ": 458, "weightcorrect": 150, "weightdetail": 465, "weightonli": 31, "weightonlylinear": [429, 476, 547], "weightonlyqu": 476, "weightonlyquantsampl": 277, "weightpruningconfig": [195, 536, 541, 542], "weights_detail": 459, "weights_onli": [140, 396], "weightsdetail": 466, "weightsstatist": 466, "welcom": [468, 488, 489, 492, 554], "well": [198, 199, 235, 262, 448, 472, 487, 492, 520, 539, 542, 544, 548, 550], "wenhua": [476, 487], "were": [140, 234, 396, 542], "wget": 527, "what": [145, 180, 207, 234, 262, 417, 448, 480, 488, 543], "when": [30, 39, 49, 55, 133, 138, 140, 153, 174, 180, 185, 192, 195, 209, 210, 218, 225, 228, 262, 301, 305, 311, 321, 327, 385, 396, 397, 406, 431, 448, 471, 475, 476, 480, 481, 482, 483, 487, 488, 494, 520, 521, 536, 542, 544, 547, 550, 551, 552], "where": [30, 140, 195, 230, 234, 280, 396, 408, 465, 487, 495, 519, 550], "whether": [1, 30, 31, 90, 101, 133, 140, 145, 175, 195, 207, 209, 221, 225, 228, 230, 234, 305, 385, 391, 396, 409, 412, 413, 420, 425, 426, 431, 433, 442, 445, 454, 461, 464, 465, 476, 482, 493, 535, 544, 547, 550, 551], "which": [1, 29, 41, 68, 95, 135, 140, 152, 169, 173, 174, 176, 180, 181, 182, 184, 187, 188, 190, 192, 195, 209, 210, 211, 221, 227, 232, 234, 239, 245, 262, 266, 313, 340, 360, 391, 396, 413, 420, 425, 426, 431, 447, 465, 469, 471, 473, 475, 476, 477, 478, 480, 481, 487, 488, 490, 493, 494, 495, 519, 521, 524, 527, 528, 531, 535, 536, 537, 538, 541, 542, 544, 545, 546, 547, 548, 550, 551, 552], "while": [174, 185, 192, 266, 473, 475, 476, 480, 487, 492, 493, 494, 525, 531, 537, 542, 544, 547, 550], "white_list": [152, 299, 303, 439], "white_module_list": 447, "white_nod": 2, "whitespac": [224, 232], "whitespace_token": 224, "whl": [492, 532], "who": [267, 488], "whole": [470, 487, 495, 544, 553], "whose": [149, 175, 243, 390, 413, 530, 550, 552], "why": [487, 550], "wide": [473, 476, 487, 492, 525, 537, 542, 544], "wideresnet40": 553, "width": [179, 221, 225, 487, 519, 524, 542, 544, 551], "wiki": 488, "wikitext": 553, "window": [151, 154, 482, 483, 518, 532], "winogrand": 553, "winter": [487, 550], "wip": 534, "wise": [128, 137, 139, 141, 150, 195, 266, 267, 271, 380, 395, 398, 404, 469, 494, 531, 542, 547, 550, 552], "wish": 533, "with_arg": 495, "within": [89, 152, 153, 181, 182, 187, 194, 230, 243, 257, 261, 390, 473, 476, 488, 490, 495, 519, 537, 542, 543, 547, 550, 552], "without": [34, 75, 133, 185, 225, 280, 385, 445, 471, 472, 487, 488, 524, 536, 539, 542, 543, 544, 552], "without_scal": 471, "wnli": [209, 535], "won": [195, 544, 547], "woq": [431, 439, 441, 472, 492, 534, 539], "woqmodelload": 431, "word": [227, 476, 487, 520, 535, 542, 547, 553], "word_perplex": 553, "wordpiec": [224, 225, 551], "wordpiecetoken": 224, "work": [195, 301, 305, 477, 480, 482, 483, 487, 491, 494, 520, 521, 546, 547, 548, 550], "worker": [536, 544], "workflow": [469, 472, 492, 494, 495, 526, 529, 532, 537, 539], "workload": [465, 473, 543], "workload_loc": 465, "workshop": 543, "workspac": [161, 195, 464, 465, 538], "workspace_path": 195, "worth": [520, 542], "would": [475, 487, 489, 536, 542, 544, 550], "wrap": [1, 90, 101, 163, 230, 305, 389, 490, 524], "wrapmxnetmetr": 234, "wraponnxrtmetr": 234, "wrapped_lay": 101, "wrapper": [60, 87, 88, 89, 90, 107, 125, 134, 142, 153, 163, 170, 208, 225, 230, 234, 239, 243, 283, 332, 389, 390, 401, 429, 433, 480, 546], "wrapperlay": 413, "wrappytorchmetr": 234, "write": [133, 218, 385, 465, 524, 530, 536], "write_graph": [133, 385], "written": 536, "wt_compare_dict": 135, "www": [211, 553], "x": [1, 40, 59, 174, 195, 208, 225, 266, 281, 312, 331, 413, 481, 487, 492, 519, 520, 524, 529, 532, 537, 538, 544, 545, 550, 551], "x1": [487, 550, 552], "x2": [487, 550, 552], "x86": [473, 537], "x86_64": 518, "x86_inductor_quant": 409, "x86inductorquant": [409, 470], "x_max": 266, "x_q": [487, 550], "x_scale": [487, 550], "x_tmp": [487, 550], "xdoctest": [140, 396], "xeon": [473, 482, 487, 492, 532, 533, 534, 537, 543, 544, 546, 553], "xgb": 195, "xgboost": 542, "xiao": [476, 487, 547, 550], "xiui": [476, 487, 547, 550], "xlm": [209, 553], "xlnet": 209, "xpu": [195, 417, 443, 477, 480, 544], "xpu_acceler": 443, "xx": [145, 433], "xx_func": 520, "xxx": [154, 211, 536], "xxy": 211, "xxz": 211, "y": [94, 195, 225, 266, 359, 487, 520, 527, 550, 551], "y_dq": [487, 550], "y_max": 266, "y_q": [487, 550], "yaml": [192, 195, 198, 199, 209, 211, 288, 464, 465, 493, 495, 530, 535, 536, 540, 551], "yaml_fil": [465, 524], "yaml_file_path": 524, "yao": 135, "year": 533, "yet": 544, "yield": [153, 198, 199, 207, 235, 262, 266, 281, 387, 448, 487, 521, 544, 552], "yolo": 553, "yolov3": 553, "yolov5": 542, "you": [29, 140, 195, 207, 209, 234, 262, 396, 413, 469, 471, 489, 490, 494, 520, 521, 524, 527, 532, 533, 535, 537, 542, 544, 547, 548, 549, 550], "your": [207, 209, 469, 475, 489, 492, 520, 521, 524, 533, 536, 542, 543, 549, 552], "your_node1_nam": 524, "your_node2_nam": 524, "your_script": 548, "yourmodel": 476, "yourself": 542, "youtub": 543, "yum": [527, 532], "yvinec": [487, 550], "z": [30, 482, 487, 519, 520, 550], "za": 482, "zafrir": 542, "zero": [3, 30, 31, 180, 192, 225, 292, 293, 294, 298, 413, 422, 425, 426, 433, 465, 472, 475, 476, 487, 539, 542, 544, 547, 550, 551, 552], "zero_grad": [524, 536, 542], "zero_point": [30, 31, 451], "zero_point_nam": 30, "zeropoint": [480, 487, 544], "zfnet": 553, "zhen": 135, "zhewei": 135, "zip": [413, 490], "zo_valu": 30, "zone": 543, "zoo": [208, 225, 492, 525, 553], "zp": [31, 429, 433, 487, 550], "\u03b1": 519, "\u03b2": 519, "\u2776": 494, "\u2777": 494, "\u2778": 494, "\u2779": 494, "\u277a": 494, "\u277b": 494, "\u277c": 494, "\u817e\u8baf\u4e91taco": 543, "\u96c6\u6210\u82f1\u7279\u5c14": 543}, "titles": ["neural_compressor.adaptor.mxnet_utils", "neural_compressor.adaptor.mxnet_utils.util", "neural_compressor.adaptor.ox_utils.calibration", "neural_compressor.adaptor.ox_utils.calibrator", "neural_compressor.adaptor.ox_utils", "neural_compressor.adaptor.ox_utils.operators.activation", "neural_compressor.adaptor.ox_utils.operators.argmax", "neural_compressor.adaptor.ox_utils.operators.attention", "neural_compressor.adaptor.ox_utils.operators.binary_op", "neural_compressor.adaptor.ox_utils.operators.concat", "neural_compressor.adaptor.ox_utils.operators.conv", "neural_compressor.adaptor.ox_utils.operators.direct_q8", "neural_compressor.adaptor.ox_utils.operators.embed_layernorm", "neural_compressor.adaptor.ox_utils.operators.gather", "neural_compressor.adaptor.ox_utils.operators.gavgpool", "neural_compressor.adaptor.ox_utils.operators.gemm", "neural_compressor.adaptor.ox_utils.operators", "neural_compressor.adaptor.ox_utils.operators.lstm", "neural_compressor.adaptor.ox_utils.operators.matmul", "neural_compressor.adaptor.ox_utils.operators.maxpool", "neural_compressor.adaptor.ox_utils.operators.norm", "neural_compressor.adaptor.ox_utils.operators.ops", "neural_compressor.adaptor.ox_utils.operators.pad", "neural_compressor.adaptor.ox_utils.operators.pooling", "neural_compressor.adaptor.ox_utils.operators.reduce", "neural_compressor.adaptor.ox_utils.operators.resize", "neural_compressor.adaptor.ox_utils.operators.split", "neural_compressor.adaptor.ox_utils.operators.unary_op", "neural_compressor.adaptor.ox_utils.quantizer", "neural_compressor.adaptor.ox_utils.smooth_quant", "neural_compressor.adaptor.ox_utils.util", "neural_compressor.adaptor.ox_utils.weight_only", "neural_compressor.adaptor.tensorflow", "neural_compressor.adaptor.tf_utils.graph_converter", "neural_compressor.adaptor.tf_utils.graph_converter_without_calib", "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.bf16_convert", "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer", "neural_compressor.adaptor.tf_utils.graph_rewriter.bf16", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_add_to_biasadd", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_layout", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_leakyrelu", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_nan_to_random", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.convert_placeholder_to_const", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dilated_contraction", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.dummy_biasadd", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.expanddims_optimizer", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fetch_weight_from_reshape", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_batch_norm", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fold_constant", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_biasadd_add", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_column_wise_mul", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_conv_with_math", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_bn", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_decomposed_in", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_gelu", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_conv", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_pad_with_fp32_conv", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_reshape_transpose", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.graph_cse_optimizer", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.grappler_pass", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.insert_print_node", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.move_squeeze_after_relu", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.pre_optimize", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.remove_training_nodes", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.rename_batch_norm", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.split_shared_input", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_equivalent_nodes", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.strip_unused_nodes", "neural_compressor.adaptor.tf_utils.graph_rewriter.generic.switch_optimizer", "neural_compressor.adaptor.tf_utils.graph_rewriter.graph_base", "neural_compressor.adaptor.tf_utils.graph_rewriter", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_fake_quant", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.freeze_value_without_calib", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_redundant_dequantize", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_conv_requantize", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.fuse_matmul_requantize", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.meta_op_optimizer", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_hostconst_converter", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.post_quantized_op_cse", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.rnn_convert", "neural_compressor.adaptor.tf_utils.graph_rewriter.int8.scale_propagation", "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx", "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_graph", "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_node", "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.onnx_schema", "neural_compressor.adaptor.tf_utils.graph_rewriter.onnx.tf2onnx_utils", "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq", "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.insert_qdq_pattern", "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.merge_duplicated_qdq", "neural_compressor.adaptor.tf_utils.graph_rewriter.qdq.share_qdq_y_pattern", "neural_compressor.adaptor.tf_utils.graph_util", "neural_compressor.adaptor.tf_utils", "neural_compressor.adaptor.tf_utils.quantize_graph", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.fake_quantize", "neural_compressor.adaptor.tf_utils.quantize_graph.qat", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_config", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_helper", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.optimize_layer", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_add", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_base", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_layers.quantize_layer_bn", "neural_compressor.adaptor.tf_utils.quantize_graph.qat.quantize_wrapper", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_bn", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_concatv2", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_conv", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_deconv", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_in", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_matmul", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.fuse_qdq_pooling", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq", "neural_compressor.adaptor.tf_utils.quantize_graph.qdq.optimize_qdq", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_base", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_bn", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_concatv2", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_conv", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_for_intel_cpu", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_matmul", "neural_compressor.adaptor.tf_utils.quantize_graph.quantize_graph_pooling", "neural_compressor.adaptor.tf_utils.quantize_graph_common", "neural_compressor.adaptor.tf_utils.smooth_quant_calibration", "neural_compressor.adaptor.tf_utils.smooth_quant_scaler", "neural_compressor.adaptor.tf_utils.tf2onnx_converter", "neural_compressor.adaptor.tf_utils.transform_graph.bias_correction", "neural_compressor.adaptor.tf_utils.transform_graph.graph_transform_base", "neural_compressor.adaptor.tf_utils.transform_graph", "neural_compressor.adaptor.tf_utils.transform_graph.insert_logging", "neural_compressor.adaptor.tf_utils.transform_graph.rerange_quantized_concat", "neural_compressor.adaptor.tf_utils.util", "neural_compressor.adaptor.torch_utils.bf16_convert", "neural_compressor.adaptor.torch_utils.hawq_metric", "neural_compressor.adaptor.torch_utils", "neural_compressor.adaptor.torch_utils.layer_wise_quant", "neural_compressor.adaptor.torch_utils.layer_wise_quant.modified_pickle", "neural_compressor.adaptor.torch_utils.layer_wise_quant.quantize", "neural_compressor.adaptor.torch_utils.layer_wise_quant.torch_load", "neural_compressor.adaptor.torch_utils.layer_wise_quant.utils", "neural_compressor.adaptor.torch_utils.model_wrapper", "neural_compressor.adaptor.torch_utils.pattern_detector", "neural_compressor.adaptor.torch_utils.symbolic_trace", "neural_compressor.adaptor.torch_utils.util", "neural_compressor.algorithm.algorithm", "neural_compressor.algorithm.fast_bias_correction", "neural_compressor.algorithm", "neural_compressor.algorithm.smooth_quant", "neural_compressor.algorithm.weight_correction", "neural_compressor.benchmark", "neural_compressor.common.base_config", "neural_compressor.common.base_tuning", "neural_compressor.common.benchmark", "neural_compressor.common", "neural_compressor.common.tuning_param", "neural_compressor.common.utils.constants", "neural_compressor.common.utils", "neural_compressor.common.utils.logger", "neural_compressor.common.utils.save_load", "neural_compressor.common.utils.utility", "neural_compressor.compression.callbacks", "neural_compressor.compression.distillation.criterions", "neural_compressor.compression.distillation", "neural_compressor.compression.distillation.optimizers", "neural_compressor.compression.distillation.utility", "neural_compressor.compression.hpo", "neural_compressor.compression.hpo.sa_optimizer", "neural_compressor.compression.pruner.criteria", "neural_compressor.compression.pruner", "neural_compressor.compression.pruner.model_slim.auto_slim", "neural_compressor.compression.pruner.model_slim", "neural_compressor.compression.pruner.model_slim.pattern_analyzer", "neural_compressor.compression.pruner.model_slim.weight_slim", "neural_compressor.compression.pruner.patterns.base", "neural_compressor.compression.pruner.patterns", "neural_compressor.compression.pruner.patterns.mha", "neural_compressor.compression.pruner.patterns.ninm", "neural_compressor.compression.pruner.patterns.nxm", "neural_compressor.compression.pruner.pruners.base", "neural_compressor.compression.pruner.pruners.basic", "neural_compressor.compression.pruner.pruners.block_mask", "neural_compressor.compression.pruner.pruners", "neural_compressor.compression.pruner.pruners.mha", "neural_compressor.compression.pruner.pruners.pattern_lock", "neural_compressor.compression.pruner.pruners.progressive", "neural_compressor.compression.pruner.pruners.retrain_free", "neural_compressor.compression.pruner.pruning", "neural_compressor.compression.pruner.regs", "neural_compressor.compression.pruner.schedulers", "neural_compressor.compression.pruner.tf_criteria", "neural_compressor.compression.pruner.utils", "neural_compressor.compression.pruner.wanda", "neural_compressor.compression.pruner.wanda.utils", "neural_compressor.config", "neural_compressor.contrib", "neural_compressor.contrib.strategy", "neural_compressor.contrib.strategy.sigopt", "neural_compressor.contrib.strategy.tpe", "neural_compressor.data.dataloaders.base_dataloader", "neural_compressor.data.dataloaders.dataloader", "neural_compressor.data.dataloaders.default_dataloader", "neural_compressor.data.dataloaders.fetcher", "neural_compressor.data.dataloaders.mxnet_dataloader", "neural_compressor.data.dataloaders.onnxrt_dataloader", "neural_compressor.data.dataloaders.pytorch_dataloader", "neural_compressor.data.dataloaders.sampler", "neural_compressor.data.dataloaders.tensorflow_dataloader", "neural_compressor.data.datasets.bert_dataset", "neural_compressor.data.datasets.coco_dataset", "neural_compressor.data.datasets.dataset", "neural_compressor.data.datasets.dummy_dataset", "neural_compressor.data.datasets.dummy_dataset_v2", "neural_compressor.data.datasets.imagenet_dataset", "neural_compressor.data.datasets", "neural_compressor.data.datasets.style_transfer_dataset", "neural_compressor.data.filters.coco_filter", "neural_compressor.data.filters.filter", "neural_compressor.data.filters", "neural_compressor.data", "neural_compressor.data.transforms.imagenet_transform", "neural_compressor.data.transforms", "neural_compressor.data.transforms.postprocess", "neural_compressor.data.transforms.tokenization", "neural_compressor.data.transforms.transform", "neural_compressor", "neural_compressor.metric.bleu", "neural_compressor.metric.bleu_util", "neural_compressor.metric.coco_label_map", "neural_compressor.metric.coco_tools", "neural_compressor.metric.evaluate_squad", "neural_compressor.metric.f1", "neural_compressor.metric", "neural_compressor.metric.metric", "neural_compressor.mix_precision", "neural_compressor.model.base_model", "neural_compressor.model", "neural_compressor.model.keras_model", "neural_compressor.model.model", "neural_compressor.model.mxnet_model", "neural_compressor.model.nets_factory", "neural_compressor.model.onnx_model", "neural_compressor.model.tensorflow_model", "neural_compressor.model.torch_model", "neural_compressor.objective", "neural_compressor.profiling", "neural_compressor.profiling.parser.factory", "neural_compressor.profiling.parser.onnx_parser.factory", "neural_compressor.profiling.parser.onnx_parser.parser", "neural_compressor.profiling.parser.parser", "neural_compressor.profiling.parser.result", "neural_compressor.profiling.parser.tensorflow_parser.factory", "neural_compressor.profiling.parser.tensorflow_parser.parser", "neural_compressor.profiling.profiler.factory", "neural_compressor.profiling.profiler.onnxrt_profiler.factory", "neural_compressor.profiling.profiler.onnxrt_profiler.profiler", "neural_compressor.profiling.profiler.onnxrt_profiler.utils", "neural_compressor.profiling.profiler.profiler", "neural_compressor.profiling.profiler.tensorflow_profiler.factory", "neural_compressor.profiling.profiler.tensorflow_profiler.profiler", "neural_compressor.profiling.profiler.tensorflow_profiler.utils", "neural_compressor.quantization", "neural_compressor.strategy.auto", "neural_compressor.strategy.auto_mixed_precision", "neural_compressor.strategy.basic", "neural_compressor.strategy.bayesian", "neural_compressor.strategy.conservative", "neural_compressor.strategy.exhaustive", "neural_compressor.strategy.hawq_v2", "neural_compressor.strategy", "neural_compressor.strategy.mse", "neural_compressor.strategy.mse_v2", "neural_compressor.strategy.random", "neural_compressor.strategy.strategy", "neural_compressor.strategy.utils.constant", "neural_compressor.strategy.utils", "neural_compressor.strategy.utils.tuning_sampler", "neural_compressor.strategy.utils.tuning_space", "neural_compressor.strategy.utils.tuning_structs", "neural_compressor.strategy.utils.utility", "neural_compressor.template.api_doc_example", "neural_compressor.tensorflow.algorithms", "neural_compressor.tensorflow.algorithms.smoother.calibration", "neural_compressor.tensorflow.algorithms.smoother.core", "neural_compressor.tensorflow.algorithms.smoother", "neural_compressor.tensorflow.algorithms.smoother.scaler", "neural_compressor.tensorflow.algorithms.static_quant", "neural_compressor.tensorflow.algorithms.static_quant.keras", "neural_compressor.tensorflow.algorithms.static_quant.tensorflow", "neural_compressor.tensorflow", "neural_compressor.tensorflow.keras", "neural_compressor.tensorflow.keras.layers.conv2d", "neural_compressor.tensorflow.keras.layers.dense", "neural_compressor.tensorflow.keras.layers.depthwise_conv2d", "neural_compressor.tensorflow.keras.layers", "neural_compressor.tensorflow.keras.layers.layer_initializer", "neural_compressor.tensorflow.keras.layers.pool2d", "neural_compressor.tensorflow.keras.layers.separable_conv2d", "neural_compressor.tensorflow.keras.quantization.config", "neural_compressor.tensorflow.keras.quantization", "neural_compressor.tensorflow.quantization.algorithm_entry", "neural_compressor.tensorflow.quantization.autotune", "neural_compressor.tensorflow.quantization.config", "neural_compressor.tensorflow.quantization", "neural_compressor.tensorflow.quantization.quantize", "neural_compressor.tensorflow.quantization.utils.graph_converter", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.bf16_convert", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16.dequantize_cast_optimizer", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.bf16", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_add_to_biasadd", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_layout", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_leakyrelu", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_nan_to_random", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.convert_placeholder_to_const", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dilated_contraction", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.dummy_biasadd", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.expanddims_optimizer", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fetch_weight_from_reshape", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_batch_norm", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fold_constant", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_biasadd_add", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_column_wise_mul", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_conv_with_math", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_bn", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_decomposed_in", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_gelu", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_layer_norm", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_conv", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_pad_with_fp32_conv", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.fuse_reshape_transpose", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.graph_cse_optimizer", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.grappler_pass", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.insert_print_node", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.move_squeeze_after_relu", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.pre_optimize", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.remove_training_nodes", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.rename_batch_norm", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.split_shared_input", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_equivalent_nodes", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.strip_unused_nodes", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.generic.switch_optimizer", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.graph_base", "neural_compressor.tensorflow.quantization.utils.graph_rewriter", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_fake_quant", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.freeze_value", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_redundant_dequantize", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_conv_requantize", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_redundant_dequantize", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.fuse_matmul_requantize", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.meta_op_optimizer", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_hostconst_converter", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.post_quantized_op_cse", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.int8.scale_propagation", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.insert_qdq_pattern", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.merge_duplicated_qdq", "neural_compressor.tensorflow.quantization.utils.graph_rewriter.qdq.share_qdq_y_pattern", "neural_compressor.tensorflow.quantization.utils.graph_util", "neural_compressor.tensorflow.quantization.utils", "neural_compressor.tensorflow.quantization.utils.quantize_graph", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_bn", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_concatv2", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_conv", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_deconv", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_in", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_matmul", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.fuse_qdq_pooling", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq", "neural_compressor.tensorflow.quantization.utils.quantize_graph.qdq.optimize_qdq", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_base", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_bn", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_concatv2", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_conv", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_for_intel_cpu", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul", "neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_pooling", "neural_compressor.tensorflow.quantization.utils.quantize_graph_common", "neural_compressor.tensorflow.quantization.utils.transform_graph.bias_correction", "neural_compressor.tensorflow.quantization.utils.transform_graph.graph_transform_base", "neural_compressor.tensorflow.quantization.utils.transform_graph", "neural_compressor.tensorflow.quantization.utils.transform_graph.insert_logging", "neural_compressor.tensorflow.quantization.utils.transform_graph.rerange_quantized_concat", "neural_compressor.tensorflow.quantization.utils.utility", "neural_compressor.tensorflow.utils.constants", "neural_compressor.tensorflow.utils.data", "neural_compressor.tensorflow.utils", "neural_compressor.tensorflow.utils.model", "neural_compressor.tensorflow.utils.model_wrappers", "neural_compressor.tensorflow.utils.utility", "neural_compressor.torch.algorithms.base_algorithm", "neural_compressor.torch.algorithms.fp8_quant.utils.logger", "neural_compressor.torch.algorithms", "neural_compressor.torch.algorithms.layer_wise", "neural_compressor.torch.algorithms.layer_wise.load", "neural_compressor.torch.algorithms.layer_wise.modified_pickle", "neural_compressor.torch.algorithms.layer_wise.utils", "neural_compressor.torch.algorithms.mixed_precision.half_precision_convert", "neural_compressor.torch.algorithms.mixed_precision", "neural_compressor.torch.algorithms.mixed_precision.module_wrappers", "neural_compressor.torch.algorithms.mx_quant", "neural_compressor.torch.algorithms.mx_quant.mx", "neural_compressor.torch.algorithms.mx_quant.utils", "neural_compressor.torch.algorithms.pt2e_quant.core", "neural_compressor.torch.algorithms.pt2e_quant.half_precision_rewriter", "neural_compressor.torch.algorithms.pt2e_quant", "neural_compressor.torch.algorithms.pt2e_quant.save_load", "neural_compressor.torch.algorithms.pt2e_quant.utility", "neural_compressor.torch.algorithms.smooth_quant", "neural_compressor.torch.algorithms.smooth_quant.save_load", "neural_compressor.torch.algorithms.smooth_quant.smooth_quant", "neural_compressor.torch.algorithms.smooth_quant.utility", "neural_compressor.torch.algorithms.static_quant", "neural_compressor.torch.algorithms.static_quant.save_load", "neural_compressor.torch.algorithms.static_quant.static_quant", "neural_compressor.torch.algorithms.static_quant.utility", "neural_compressor.torch.algorithms.weight_only.autoround", "neural_compressor.torch.algorithms.weight_only.awq", "neural_compressor.torch.algorithms.weight_only.gptq", "neural_compressor.torch.algorithms.weight_only.hqq.bitpack", "neural_compressor.torch.algorithms.weight_only.hqq.config", "neural_compressor.torch.algorithms.weight_only.hqq.core", "neural_compressor.torch.algorithms.weight_only.hqq", "neural_compressor.torch.algorithms.weight_only.hqq.optimizer", "neural_compressor.torch.algorithms.weight_only.hqq.qtensor", "neural_compressor.torch.algorithms.weight_only.hqq.quantizer", "neural_compressor.torch.algorithms.weight_only", "neural_compressor.torch.algorithms.weight_only.modules", "neural_compressor.torch.algorithms.weight_only.rtn", "neural_compressor.torch.algorithms.weight_only.save_load", "neural_compressor.torch.algorithms.weight_only.teq", "neural_compressor.torch.algorithms.weight_only.utility", "neural_compressor.torch.export", "neural_compressor.torch.export.pt2e_export", "neural_compressor.torch", "neural_compressor.torch.quantization.algorithm_entry", "neural_compressor.torch.quantization.autotune", "neural_compressor.torch.quantization.config", "neural_compressor.torch.quantization", "neural_compressor.torch.quantization.load_entry", "neural_compressor.torch.quantization.quantize", "neural_compressor.torch.utils.auto_accelerator", "neural_compressor.torch.utils.constants", "neural_compressor.torch.utils.environ", "neural_compressor.torch.utils", "neural_compressor.torch.utils.utility", "neural_compressor.training", "neural_compressor.transformers.quantization.utils", "neural_compressor.transformers.utils", "neural_compressor.transformers.utils.quantization_config", "neural_compressor.utils.collect_layer_histogram", "neural_compressor.utils.constant", "neural_compressor.utils.create_obj_from_config", "neural_compressor.utils.export", "neural_compressor.utils.export.qlinear2qdq", "neural_compressor.utils.export.tf2onnx", "neural_compressor.utils.export.torch2onnx", "neural_compressor.utils", "neural_compressor.utils.kl_divergence", "neural_compressor.utils.load_huggingface", "neural_compressor.utils.logger", "neural_compressor.utils.options", "neural_compressor.utils.pytorch", "neural_compressor.utils.utility", "neural_compressor.utils.weights_details", "neural_compressor.version", "Intel\u00ae Neural Compressor Documentation", "2.X API User Guide", "Dynamic Quantization", "FP8 Quantization", "Microscaling Quantization", "PyTorch Mixed Precision", "PyTorch Smooth Quantization", "PyTorch Static Quantization", "PyTorch Weight Only Quantization", "Torch", "TensorFlow Quantization", "Smooth Quant", "TensorFlow", "AutoTune", "Benchmark", "Quantization on Client", "Design", "Version mapping between Intel Neural Compressor to Gaudi Software Stack", "<no title>", "Quantization", "Contributor Covenant Code of Conduct", "Contribution Guidelines", "FX", "Security Policy", "Intel\u00ae Neural Compressor", "Adaptor", "How to Add An Adaptor", "How to Support New Data Type, Like Int4, with a Few Line Changes", "Adaptor", "ONNX Runtime", "Torch Utils", "2.0 API", "3.0 API", "API Document Example", "APIs", "Benchmark", "Compression", "Config", "Mix Precision", "Model", "Objective", "Quantization", "Strategy", "Tensorflow Quantization AutoTune", "Tensorflow Quantization Base API", "Tensorflow Quantization Config", "Pytorch Quantization AutoTune", "Pytorch Quantization Base API", "Pytorch Quantization Config", "Training", "Benchmarking", "Calibration Algorithms in Quantization", "INC Coding Conventions", "DataLoader", "Design", "Distillation for Quantization", "Distributed Training and Inference (Evaluation)", "Examples", "Export", "Frequently Asked Questions", "Framework YAML Configuration Files", "Getting Started", "Incompatible changes between v1.2 and v1.1", "Infrastructure of Intel\u00ae Neural Compressor", "Installation", "Legal Information", "LLMs Quantization Recipes", "Metrics", "Code Migration from Intel Neural Compressor 1.X to Intel Neural Compressor 2.X", "Mixed Precision", "Model", "Microscaling Quantization", "Objective", "Optimization Orchestration", "Pruning", "Full Publications/Events (84)", "Quantization", "Layer Wise Quantization (LWQ)", "Turn OFF Auto Mixed Precision during Quantization", "Weight Only Quantization (WOQ)", "Release", "SigOpt Strategy", "Smooth Quant", "Transform", "Tuning Strategies", "Validated Models", "Intel\u00ae Neural Compressor Documentation"], "titleterms": {"": [492, 532], "0": [499, 500, 553], "1": [524, 527, 530, 536, 553], "15": [543, 553], "17": 553, "2": [469, 499, 524, 527, 530, 536, 553], "2018": 543, "2020": 543, "2021": 543, "2022": 543, "2023": 543, "2024": 543, "25": 543, "3": [500, 527], "35": 543, "4": [527, 543], "5": [527, 543], "64": 532, "84": 543, "One": 541, "With": 478, "abil": 495, "accept": 489, "accord": [494, 495], "accuraci": [473, 478, 487, 534, 537, 544, 552], "activ": 5, "ad": 493, "adaptor": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 493, 494, 496], "add": 494, "addit": 492, "advanc": 469, "ai": 532, "algorithm": [146, 147, 148, 149, 150, 282, 283, 284, 285, 286, 287, 288, 289, 392, 393, 394, 395, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413, 414, 415, 416, 417, 418, 419, 420, 421, 422, 423, 424, 425, 426, 427, 428, 429, 430, 431, 432, 433, 519, 547, 550, 552], "algorithm_entri": [301, 437], "alpha": [474, 479, 550], "an": 494, "annot": 520, "api": [469, 472, 473, 477, 480, 493, 494, 499, 500, 501, 502, 512, 515, 518, 521, 523, 524, 530, 535, 537, 539, 540, 541, 542], "api_doc_exampl": 281, "appendix": 526, "approach": [480, 544], "architectur": [484, 522, 531, 532], "argmax": 6, "argument": 476, "ask": 527, "asymmetr": 487, "attent": 7, "attribut": [211, 281, 488], "auto": [263, 479, 546, 550, 552], "auto_acceler": 443, "auto_mixed_precis": 264, "auto_slim": 171, "autoround": [418, 476], "autotun": [302, 438, 473, 477, 481, 511, 514], "awar": [478, 487, 490, 536, 542, 544], "awq": [419, 476], "backend": [475, 480, 493, 544], "background": [493, 520], "base": [175, 180, 469, 512, 515, 532], "base_algorithm": 392, "base_config": 152, "base_dataload": 200, "base_model": 236, "base_tun": 153, "basic": [181, 265, 552], "bayesian": [266, 552], "benchmark": [151, 154, 482, 503, 518, 536], "benefit": 549, "bert_dataset": 209, "between": [485, 530], "bf16": [35, 36, 37, 307, 308, 309, 473, 537], "bf16_convert": [35, 134, 307], "bias_correct": [128, 380], "binari": 532, "binary_op": 8, "bitpack": 421, "bleu": 227, "bleu_util": 228, "block": 550, "block_mask": 182, "build": [521, 527, 535], "built": [530, 532, 535], "calcul": 494, "calibr": [2, 3, 283, 494, 519], "callback": 162, "capabl": [493, 547], "case": 482, "chang": [495, 530, 548], "channel": [487, 550], "check": 489, "checklist": 489, "citat": 533, "class": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 73, 74, 75, 76, 77, 78, 79, 81, 82, 83, 84, 85, 87, 88, 89, 90, 92, 93, 94, 95, 98, 100, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 131, 132, 134, 135, 139, 142, 143, 146, 147, 149, 150, 152, 153, 156, 157, 159, 161, 162, 163, 165, 169, 173, 174, 175, 177, 178, 179, 180, 181, 182, 184, 185, 186, 187, 188, 189, 190, 191, 195, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 216, 217, 218, 221, 223, 224, 225, 227, 230, 234, 236, 238, 239, 240, 241, 242, 243, 244, 245, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 258, 259, 260, 263, 264, 265, 266, 267, 268, 269, 271, 272, 273, 274, 277, 278, 279, 280, 281, 283, 284, 286, 288, 289, 292, 293, 294, 297, 298, 299, 303, 306, 307, 308, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 345, 346, 347, 348, 349, 350, 352, 353, 354, 355, 357, 358, 359, 360, 363, 364, 365, 366, 367, 368, 369, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 383, 384, 387, 389, 390, 391, 392, 398, 399, 401, 403, 404, 405, 406, 412, 413, 416, 417, 418, 419, 420, 421, 422, 423, 426, 427, 429, 430, 431, 432, 433, 439, 443, 444, 448, 451, 452, 460, 461, 462, 463, 465, 466, 493], "client": [476, 483], "coco_dataset": 210, "coco_filt": 217, "coco_label_map": 229, "coco_tool": 230, "code": [488, 489, 520, 536, 547], "collect_layer_histogram": 452, "comment": 520, "common": [152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 476, 477, 490, 527], "commun": 492, "comparison": 549, "compat": 532, "compress": [162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 504, 547], "compressor": [468, 485, 490, 492, 521, 531, 532, 535, 536, 549, 554], "comput": 532, "concat": 9, "conduct": [488, 489], "config": [195, 299, 303, 422, 439, 505, 513, 516, 540], "configur": [495, 524, 528, 549], "conserv": [267, 552], "constant": [157, 275, 386, 444, 453], "content": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 73, 74, 75, 76, 77, 78, 79, 81, 82, 83, 84, 85, 87, 88, 89, 90, 92, 93, 94, 95, 98, 100, 101, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 131, 132, 133, 134, 135, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 149, 150, 151, 152, 153, 154, 156, 157, 159, 160, 161, 162, 163, 165, 166, 169, 170, 171, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 194, 195, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 216, 217, 218, 221, 223, 224, 225, 227, 228, 230, 231, 232, 234, 235, 236, 238, 239, 240, 241, 242, 243, 244, 245, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 271, 272, 273, 274, 277, 278, 279, 280, 281, 283, 284, 286, 288, 289, 292, 293, 294, 297, 298, 299, 301, 302, 303, 305, 306, 307, 308, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 345, 346, 347, 348, 349, 350, 352, 353, 354, 355, 357, 358, 359, 360, 363, 364, 365, 366, 367, 368, 369, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 383, 384, 385, 387, 389, 390, 391, 392, 396, 397, 398, 399, 401, 403, 404, 405, 406, 408, 409, 411, 412, 413, 415, 416, 417, 418, 419, 420, 421, 422, 423, 425, 426, 427, 429, 430, 431, 432, 433, 435, 437, 438, 439, 441, 442, 443, 444, 445, 447, 448, 451, 452, 454, 456, 457, 458, 460, 461, 462, 463, 464, 465, 466, 492], "contrib": [196, 197, 198, 199], "contribut": 489, "contributor": [488, 489], "conv": 10, "conv2d": 292, "convent": 520, "convert_add_to_biasadd": [38, 310], "convert_layout": [39, 311], "convert_leakyrelu": [40, 312], "convert_nan_to_random": [41, 313], "convert_placeholder_to_const": [42, 314], "core": [284, 405, 423], "coven": [488, 489], "cpu": [492, 532, 553], "creat": 489, "create_obj_from_config": 454, "criteria": [169, 489, 542, 552], "criterion": 163, "custom": [521, 535, 552], "data": [200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 387, 494, 495, 525], "dataload": [200, 201, 202, 203, 204, 205, 206, 207, 208, 521], "dataset": [209, 210, 211, 212, 213, 214, 215, 216, 530], "decai": 542, "default_dataload": 202, "defin": [495, 524], "demo": [471, 482], "dens": 293, "deploy": 542, "depthwise_conv2d": 294, "dequantize_cast_optim": [36, 308], "design": [484, 494, 522, 552], "detail": 490, "determin": [479, 550], "devic": [480, 544], "differ": 549, "dilated_contract": [43, 315], "direct_q8": 11, "distil": [163, 164, 165, 166, 523, 536, 553], "distribut": [524, 552], "docker": [492, 532], "document": [468, 492, 501, 554], "driven": [473, 537], "dummy_biasadd": [44, 316], "dummy_dataset": 212, "dummy_dataset_v2": 213, "dump": 482, "dure": [537, 546], "dynam": [470, 487, 490, 544], "each": 550, "effici": 476, "embed_layernorm": 12, "enforc": 488, "engin": [532, 550], "enhanc": 550, "entir": 550, "environ": [445, 532], "evalu": 524, "evaluate_squad": 231, "event": [492, 543], "exampl": [470, 471, 472, 473, 475, 476, 478, 479, 487, 490, 493, 501, 518, 521, 523, 524, 525, 526, 535, 536, 537, 538, 539, 540, 541, 542, 544, 545, 547, 550, 553], "except": [138, 397], "execut": 524, "exhaust": [268, 552], "exit": 552, "expanddims_optim": [45, 317], "export": [434, 435, 455, 456, 457, 458, 526, 547], "f1": 232, "face": 530, "factori": [247, 248, 252, 254, 255, 259], "fake_quant": 98, "fast_bias_correct": 147, "featur": [524, 528, 529, 531, 544], "fetch_weight_from_reshap": [46, 318], "fetcher": 203, "few": 495, "file": 528, "filter": [217, 218, 219], "fix": [474, 479, 550], "flow": [493, 544], "fold_batch_norm": [47, 319], "fold_const": [48, 320], "folder": 520, "fp16": [473, 537], "fp32": [494, 526], "fp8": [471, 492], "fp8_quant": 393, "framework": [474, 492, 494, 521, 526, 528, 532, 538, 539, 545, 547, 550], "free": 542, "freeze_fake_qu": [73, 345], "freeze_valu": [74, 346], "freeze_value_without_calib": 75, "frequent": 527, "from": [492, 494, 532, 536], "full": 543, "function": [1, 3, 21, 29, 30, 31, 52, 53, 55, 89, 90, 101, 103, 133, 134, 135, 140, 141, 144, 145, 146, 151, 152, 153, 154, 160, 161, 163, 165, 166, 169, 170, 171, 173, 175, 176, 180, 183, 188, 189, 190, 191, 192, 194, 201, 202, 209, 211, 218, 224, 225, 227, 228, 230, 231, 232, 234, 235, 239, 243, 245, 257, 261, 262, 266, 274, 278, 280, 281, 292, 293, 294, 297, 298, 299, 301, 302, 303, 305, 324, 325, 327, 385, 387, 390, 391, 396, 398, 404, 406, 408, 409, 411, 412, 413, 415, 417, 418, 420, 425, 427, 431, 433, 435, 437, 438, 439, 441, 442, 443, 445, 447, 448, 454, 456, 457, 458, 461, 462, 464, 465, 524], "fundament": [487, 544, 550], "fuse_biasadd_add": [49, 321], "fuse_column_wise_mul": [50, 322], "fuse_conv_redundant_dequant": [76, 347], "fuse_conv_requant": [77, 348], "fuse_conv_with_math": [51, 323], "fuse_decomposed_bn": [52, 324], "fuse_decomposed_in": [53, 325], "fuse_gelu": [54, 326], "fuse_layer_norm": [55, 327], "fuse_matmul_redundant_dequant": [78, 349], "fuse_matmul_requant": [79, 350], "fuse_pad_with_conv": [56, 328], "fuse_pad_with_fp32_conv": [57, 329], "fuse_qdq_bn": [108, 363], "fuse_qdq_concatv2": [109, 364], "fuse_qdq_conv": [110, 365], "fuse_qdq_deconv": [111, 366], "fuse_qdq_in": [112, 367], "fuse_qdq_matmul": [113, 368], "fuse_qdq_pool": [114, 369], "fuse_reshape_transpos": [58, 330], "fx": 490, "gather": 13, "gaudi": 485, "gavgpool": 14, "gemm": 15, "gener": [38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 482, 494], "get": [470, 471, 472, 473, 475, 476, 478, 483, 490, 492, 493, 518, 521, 523, 524, 528, 529, 535, 537, 539, 540, 541, 542, 544], "gptq": [420, 476], "gpu": [492, 532], "graph": 494, "graph_bas": [71, 343], "graph_convert": [33, 306], "graph_converter_without_calib": 34, "graph_cse_optim": [59, 331], "graph_rewrit": [35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359], "graph_transform_bas": [129, 381], "graph_util": [95, 360], "grappler_pass": [60, 332], "guid": 469, "guidelin": 489, "half_precision_convert": 399, "half_precision_rewrit": 406, "hardwar": [473, 532, 537, 553], "hawq_metr": 135, "hawq_v2": [269, 552], "heterogen": 532, "horovodrun": 524, "how": [481, 494, 495], "hpo": [167, 168], "hpu": [492, 532], "hqq": [421, 422, 423, 424, 425, 426, 427, 476], "hyperparamet": 542, "imag": [492, 532], "imagenet_dataset": 214, "imagenet_transform": 221, "implement": [493, 494], "import": 520, "inc": 520, "incompat": [530, 548], "infer": 524, "inform": 533, "infrastructur": 531, "insert_log": [131, 383], "insert_print_nod": [62, 334], "insert_qdq_pattern": [92, 357], "instal": [492, 532], "int4": 495, "int8": [73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 526, 553], "intel": [468, 485, 492, 521, 531, 532, 535, 536, 554], "intel_extension_for_pytorch": [492, 532], "interfac": 520, "intern": 520, "introduct": [470, 471, 472, 473, 474, 475, 476, 477, 478, 479, 480, 482, 483, 487, 490, 493, 494, 495, 518, 519, 521, 523, 524, 526, 528, 531, 535, 537, 538, 539, 540, 541, 542, 544, 545, 547, 549, 550, 551, 552], "invok": 495, "ipex": [475, 487, 544], "issu": [527, 548], "iter": 494, "json": 520, "kera": [288, 291, 292, 293, 294, 295, 296, 297, 298, 299, 300], "keras_model": 238, "kernel": 495, "kit": 532, "kl_diverg": 460, "knowledg": 553, "known": 548, "languag": [492, 534, 542], "larg": [492, 534, 542], "latenc": 482, "layer": [292, 293, 294, 295, 296, 297, 298, 476, 545, 550], "layer_initi": 296, "layer_wis": [395, 396, 397, 398], "layer_wise_qu": [137, 138, 139, 140, 141], "legal": 533, "licens": 533, "like": [477, 495], "limit": [487, 550], "line": 495, "list": [494, 525, 551], "llm": [492, 534], "load": [396, 476, 477, 492], "load_entri": 441, "load_huggingfac": 461, "logger": [159, 393, 462, 520], "lstm": 17, "lwq": 545, "map": 485, "matmul": [18, 487, 550], "matrix": [473, 474, 476, 477, 480, 482, 490, 493, 518, 519, 521, 523, 524, 526, 528, 529, 531, 535, 537, 538, 539, 540, 541, 542, 544, 545, 547, 550], "maxpool": 19, "merge_duplicated_qdq": [93, 358], "meta_op_optim": [81, 352], "metric": [227, 228, 229, 230, 231, 232, 233, 234, 530, 535], "mha": [177, 184], "microsc": [472, 539], "migrat": 536, "mix": [473, 480, 506, 536, 537, 546], "mix_precis": 235, "mixed_precis": [399, 400, 401], "mme": 532, "mode": [490, 553], "model": [236, 237, 238, 239, 240, 241, 242, 243, 244, 389, 474, 475, 481, 492, 494, 507, 526, 532, 534, 536, 538, 539, 542, 545, 547, 550, 553], "model_slim": [171, 172, 173, 174], "model_wrapp": [142, 390], "modified_pickl": [138, 397], "modul": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 73, 74, 75, 76, 77, 78, 79, 81, 82, 83, 84, 85, 87, 88, 89, 90, 92, 93, 94, 95, 98, 100, 101, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 131, 132, 133, 134, 135, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 149, 150, 151, 152, 153, 154, 156, 157, 159, 160, 161, 162, 163, 165, 166, 169, 171, 173, 174, 175, 177, 178, 179, 180, 181, 182, 184, 185, 186, 187, 188, 189, 190, 191, 192, 194, 195, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 216, 217, 218, 221, 223, 224, 225, 227, 228, 230, 231, 232, 234, 235, 236, 238, 239, 240, 241, 242, 243, 244, 245, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 271, 272, 273, 274, 277, 278, 279, 280, 281, 283, 284, 286, 288, 289, 292, 293, 294, 297, 298, 299, 301, 302, 303, 305, 306, 307, 308, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 345, 346, 347, 348, 349, 350, 352, 353, 354, 355, 357, 358, 359, 360, 363, 364, 365, 366, 367, 368, 369, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 383, 384, 385, 387, 389, 390, 391, 392, 396, 397, 398, 399, 401, 403, 404, 405, 406, 408, 409, 411, 412, 413, 415, 416, 417, 418, 419, 420, 421, 422, 423, 425, 426, 427, 429, 430, 431, 432, 433, 435, 437, 438, 439, 441, 442, 443, 444, 445, 447, 448, 451, 452, 454, 456, 457, 458, 460, 461, 462, 463, 464, 465, 466], "module_wrapp": 401, "move_squeeze_after_relu": [63, 335], "mse": [271, 552], "mse_v2": [272, 552], "multipl": [532, 540, 553], "mx": 403, "mx_quant": [402, 403, 404], "mxnet": [535, 544, 551], "mxnet_dataload": 204, "mxnet_model": 240, "mxnet_util": [0, 1], "need": 494, "nets_factori": 241, "network": 542, "neural": [468, 485, 490, 492, 521, 531, 532, 535, 536, 542, 549, 554], "neural_compressor": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227, 228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 270, 271, 272, 273, 274, 275, 276, 277, 278, 279, 280, 281, 282, 283, 284, 285, 286, 287, 288, 289, 290, 291, 292, 293, 294, 295, 296, 297, 298, 299, 300, 301, 302, 303, 304, 305, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 360, 361, 362, 363, 364, 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 382, 383, 384, 385, 386, 387, 388, 389, 390, 391, 392, 393, 394, 395, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413, 414, 415, 416, 417, 418, 419, 420, 421, 422, 423, 424, 425, 426, 427, 428, 429, 430, 431, 432, 433, 434, 435, 436, 437, 438, 439, 440, 441, 442, 443, 444, 445, 446, 447, 448, 449, 450, 451, 452, 453, 454, 455, 456, 457, 458, 459, 460, 461, 462, 463, 464, 465, 466, 467], "new": [492, 493, 495, 552], "ninm": 178, "norm": 20, "note": [490, 548], "nxm": 179, "object": [245, 508, 540], "off": 546, "onli": [476, 487, 492, 547], "onnx": [86, 87, 88, 89, 90, 497, 532, 544, 545, 553], "onnx_graph": 87, "onnx_model": 242, "onnx_nod": 88, "onnx_pars": [248, 249], "onnx_schema": 89, "onnxrt": [535, 551], "onnxrt_dataload": 205, "onnxrt_profil": [255, 256, 257], "onnxrtadaptor": 493, "op": [21, 526], "oper": [5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 494, 495], "optim": [165, 425, 541, 542], "optimize_lay": 103, "optimize_qdq": [116, 371], "option": [463, 524], "orchestr": [536, 541], "other": [492, 532], "our": [488, 550], "overview": [469, 481, 489], "ox_util": [2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31], "packag": [170, 176, 183], "pad": 22, "paramet": 471, "parser": [247, 248, 249, 250, 251, 252, 253], "pattern": [175, 176, 177, 178, 179, 542], "pattern_analyz": 173, "pattern_detector": 143, "pattern_lock": 185, "per": [487, 550], "perform": 549, "platform": [492, 532, 549], "pledg": 488, "polici": [491, 552], "pool": 23, "pool2d": 297, "post": [480, 490, 536, 544], "post_hostconst_convert": [82, 353], "post_quantized_op_cs": [83, 354], "postprocess": 223, "pre_optim": [64, 336], "precis": [473, 480, 506, 536, 537, 546], "prepar": [494, 549], "prerequisit": 532, "problem": [477, 490], "process": 552, "processor": 532, "profil": [246, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261], "progress": 186, "prune": [188, 536, 542, 553], "pruner": [169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194], "pt2e": 475, "pt2e_export": 435, "pt2e_quant": [405, 406, 407, 408, 409], "ptq": 553, "public": [492, 520, 543], "pull": 489, "pure": 524, "pypi": 492, "python": [469, 521, 535], "pytorch": [464, 473, 474, 475, 476, 481, 487, 514, 515, 516, 524, 526, 535, 544, 545, 546, 551, 553], "pytorch_dataload": 206, "qat": [98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 553], "qdq": [91, 92, 93, 94, 108, 109, 110, 111, 112, 113, 114, 115, 116, 356, 357, 358, 359, 363, 364, 365, 366, 367, 368, 369, 370, 371, 553], "qlinear2qdq": 456, "qtensor": 426, "quant": [479, 550], "quantiz": [28, 139, 262, 299, 300, 301, 302, 303, 304, 305, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 360, 361, 362, 363, 364, 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 382, 383, 384, 385, 427, 437, 438, 439, 440, 441, 442, 449, 470, 471, 472, 474, 475, 476, 477, 478, 480, 483, 487, 490, 492, 494, 495, 509, 511, 512, 513, 514, 515, 516, 519, 523, 526, 532, 534, 536, 537, 539, 544, 545, 546, 547, 550, 553], "quantization_config": 451, "quantize_config": 100, "quantize_graph": [97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 362, 363, 364, 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377, 378], "quantize_graph_bas": [117, 372], "quantize_graph_bn": [118, 373], "quantize_graph_common": [124, 379], "quantize_graph_concatv2": [119, 374], "quantize_graph_conv": [120, 375], "quantize_graph_for_intel_cpu": [121, 376], "quantize_graph_matmul": [122, 377], "quantize_graph_pool": [123, 378], "quantize_help": 101, "quantize_lay": [102, 103, 104, 105, 106], "quantize_layer_add": 104, "quantize_layer_bas": 105, "quantize_layer_bn": 106, "quantize_wrapp": 107, "queri": 493, "query_fw_cap": 494, "question": 527, "quick": 529, "random": [273, 552], "rang": 494, "recip": [534, 544], "recommend": 520, "reduc": 24, "refer": [472, 476, 487, 519, 520, 539, 542, 544, 547, 550], "reg": 189, "regular": 542, "releas": [525, 548], "remove_training_nod": [65, 337], "rename_batch_norm": [66, 338], "report": 491, "request": [473, 489, 537], "requir": 532, "rerange_quantized_concat": [132, 384], "resiz": 25, "respons": 488, "result": 251, "retrain": 542, "retrain_fre": 187, "rnn_convert": 84, "rtn": [430, 476], "rule": [474, 475, 476, 478, 520, 544], "run": 494, "runtim": [497, 532, 544, 545, 553], "sa_optim": 168, "sampl": [475, 494, 529], "sampler": 207, "save": 476, "save_load": [160, 408, 411, 415, 431], "scale_propag": [85, 355], "scaler": 286, "schedul": [190, 542], "scheme": [480, 487, 544], "scope": [488, 542], "section": [468, 554], "secur": [491, 524], "select": 492, "separable_conv2d": 298, "set": 520, "share_qdq_y_pattern": [94, 359], "shot": 541, "side": 476, "sigopt": [198, 549, 552], "singl": 540, "smooth": [474, 479, 480, 487, 550], "smooth_quant": [29, 149, 410, 411, 412, 413], "smooth_quant_calibr": 125, "smooth_quant_scal": 126, "smoother": [283, 284, 285, 286], "smoothquant": 550, "softwar": [473, 485, 532, 537], "sourc": 532, "space": 552, "spars": 542, "sparsiti": 542, "specif": 495, "specifi": [474, 475, 476, 478, 544], "split": 26, "split_shared_input": [67, 339], "stack": 485, "standard": 488, "start": [470, 471, 472, 473, 475, 476, 478, 483, 490, 492, 493, 518, 521, 523, 524, 528, 529, 535, 537, 539, 540, 541, 542, 544], "static": [475, 480, 487, 490, 544], "static_qu": [287, 288, 289, 414, 415, 416, 417], "statu": 489, "step": 489, "strategi": [197, 198, 199, 263, 264, 265, 266, 267, 268, 269, 270, 271, 272, 273, 274, 275, 276, 277, 278, 279, 280, 510, 549, 552], "string": 520, "strip_equivalent_nod": [68, 340], "strip_unused_nod": [69, 341], "structur": 520, "style_transfer_dataset": 216, "submodul": [0, 4, 16, 37, 61, 72, 80, 86, 91, 96, 97, 99, 102, 115, 130, 136, 137, 148, 155, 158, 164, 167, 170, 172, 176, 183, 193, 197, 215, 219, 222, 226, 233, 237, 270, 276, 285, 287, 295, 300, 304, 309, 333, 344, 351, 356, 361, 362, 370, 382, 388, 394, 395, 400, 402, 407, 410, 414, 424, 428, 434, 440, 446, 450, 455, 459], "subpackag": [4, 72, 96, 97, 99, 136, 155, 170, 196, 220, 226, 270, 282, 290, 291, 304, 344, 361, 362, 394, 428, 436, 459], "summari": [482, 495], "support": [471, 473, 474, 476, 477, 480, 482, 489, 490, 493, 495, 518, 519, 521, 523, 524, 526, 528, 531, 532, 535, 537, 538, 539, 540, 541, 542, 544, 545, 547, 550, 551], "switch_optim": [70, 342], "symbolic_trac": 144, "symmetr": 487, "system": 532, "templat": [281, 489], "tensor": [487, 550], "tensorflow": [32, 282, 283, 284, 285, 286, 287, 288, 289, 290, 291, 292, 293, 294, 295, 296, 297, 298, 299, 300, 301, 302, 303, 304, 305, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 360, 361, 362, 363, 364, 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 382, 383, 384, 385, 386, 387, 388, 389, 390, 391, 478, 480, 481, 487, 492, 511, 512, 513, 524, 526, 532, 535, 544, 546, 551, 553], "tensorflow_dataload": 208, "tensorflow_model": 243, "tensorflow_pars": [252, 253], "tensorflow_profil": [259, 260, 261], "teq": [432, 476], "tf2onnx": 457, "tf2onnx_convert": 127, "tf2onnx_util": 90, "tf_criteria": 191, "tf_util": [33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133], "through": [479, 532, 550, 553], "throughput": 482, "todo": 520, "token": 224, "topic": 469, "torch": [392, 393, 394, 395, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413, 414, 415, 416, 417, 418, 419, 420, 421, 422, 423, 424, 425, 426, 427, 428, 429, 430, 431, 432, 433, 434, 435, 436, 437, 438, 439, 440, 441, 442, 443, 444, 445, 446, 447, 477, 492, 498, 532, 553], "torch2onnx": 458, "torch_load": 140, "torch_model": 244, "torch_util": [134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145], "tpc": 532, "tpe": [199, 552], "trademark": 533, "train": [448, 480, 487, 490, 517, 524, 536, 542, 544], "transform": [221, 222, 223, 224, 225, 449, 450, 451, 530, 551], "transform_graph": [128, 129, 130, 131, 132, 380, 381, 382, 383, 384], "tune": [478, 479, 487, 495, 544, 547, 550, 552], "tune_cfg": 494, "tuning_param": 156, "tuning_sampl": 277, "tuning_spac": 278, "tuning_struct": 279, "turn": 546, "two": 532, "type": [495, 520, 542], "unary_op": 27, "us": [479, 482, 492, 495, 521, 532, 535, 550], "usag": [471, 474, 475, 476, 479, 482, 550, 552], "user": [469, 524, 530, 547], "util": [1, 30, 133, 141, 145, 157, 158, 159, 160, 161, 166, 192, 194, 257, 261, 275, 276, 277, 278, 279, 280, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 360, 361, 362, 363, 364, 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 382, 383, 384, 385, 386, 387, 388, 389, 390, 391, 393, 398, 404, 409, 413, 417, 433, 443, 444, 445, 446, 447, 449, 450, 451, 452, 453, 454, 455, 456, 457, 458, 459, 460, 461, 462, 463, 464, 465, 466, 498], "v": 520, "v1": 530, "valid": [474, 532, 550, 553], "vendor": 532, "version": [467, 485], "vulner": 491, "wanda": [193, 194], "weight": [476, 487, 492, 547], "weight_correct": 150, "weight_onli": [31, 418, 419, 420, 421, 422, 423, 424, 425, 426, 427, 428, 429, 430, 431, 432, 433], "weight_slim": 174, "weights_detail": 466, "what": 492, "wise": [476, 545], "without": 478, "woq": [547, 553], "work": [481, 493, 544], "workflow": [484, 522], "x": [469, 536], "xe": 532, "yaml": [494, 524, 528]}}) \ No newline at end of file

save(model[, output_dir])

save(model[, output_dir, format])

Save the quantized model and config to the output path.

load(model_name_or_path[, original_model, format, device])