Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Onnxrt 11 7 sync merge #22

Closed
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
258 commits
Select commit Hold shift + click to select a range
2be4dc6
ONNX 1.15 integration (#17125)
liqunfu Sep 26, 2023
bcc6205
🐛 Bugfix win del file err (#17697)
trajepl Sep 26, 2023
33295ed
Handle string initializers in constant folding (#17422)
skottmckay Sep 27, 2023
a99c965
Make transpose optimizer able to look past DQ node for const initiali…
skottmckay Sep 27, 2023
e6aa0fa
Add Gelu Related Ops to Triton Codegen (#17713)
centwang Sep 27, 2023
276e873
Update onnx python package and setuptools (#17709)
snnn Sep 27, 2023
13b0f8a
fix: supported typo (#17216)
0o001 Sep 27, 2023
522cc96
[java] Filling out the javadoc for the float8 types (#17694)
Craigacp Sep 27, 2023
870b0bc
Fix typo of cmake (#17715)
MistEO Sep 27, 2023
8621bdc
Remove unnecessary #incldue <stacktrace> (#17716)
MistEO Sep 27, 2023
1f4a352
Bugfix: Add initializer to model in AttentionMask directly (#17719)
jambayk Sep 27, 2023
9136748
Fix: Fail to skip disabledmodel in winml (#17728)
mszhanyi Sep 28, 2023
fc9a69d
Update VecAddMoveOnlyFunctor and VecAddWithIsSupportedMethod with Def…
jchen351 Sep 28, 2023
20f96fd
Fix Attention Runtime Error for CLIP model (#17729)
tianleiwu Sep 28, 2023
9cb60c5
Resize and EP specific transpose optimization updates (#17664)
skottmckay Sep 28, 2023
caf9812
Update linux-wasm-ci.yml: remove the ln command (#17735)
snnn Sep 29, 2023
b4fbc25
[JS/Web] Add ConvTranspose implementation using MatMul (#17573)
satyajandhyala Sep 29, 2023
561aca9
[js/webgpu] support IO binding (#17480)
fs-eire Sep 29, 2023
14d349e
Enable backtrace in unit tests (#17655)
snnn Sep 29, 2023
5a623dc
Python API to check whether collective ops are available or not (#17730)
shaahji Sep 29, 2023
e106b1e
Fix react native load from Uint8Array buffer bug (#17739)
YUNQIUGUO Sep 30, 2023
6a5f469
Add training interfaces to js/common (#17333)
carzh Sep 30, 2023
668c70e
Add support for specifying a custom logging function per session. (#1…
pranavsharma Sep 30, 2023
9aad787
Update debug_alloc.cc: filter out one more memory leak from absl (#17…
snnn Sep 30, 2023
a941dd5
[js/web] FP16 Conv, ConvTranspose and MatMul (#17514)
dakenf Sep 30, 2023
0d60604
[JS/WebGPU] support Range operator (#17233)
xhcao Sep 30, 2023
63acaf4
Fix onnx quantizer activation and weight type attribute (#17651)
echarlaix Oct 1, 2023
ac4e726
Add bytes model loading test to react native e2e (#17749)
skottmckay Oct 2, 2023
f158f39
[WebNN EP] Support Softmax since version 13 (#17714)
Oct 2, 2023
451c025
[js/webgpu] allow specify preferredLayout (#17756)
fs-eire Oct 3, 2023
d11e053
Add option to specify the EP to use, enabling DML EP and others (#17490)
kazssym Oct 3, 2023
d0519a7
[js/web] BiasSplitGelu and BiasAdd kernels (#17161)
dakenf Oct 3, 2023
f8a8452
[js/webgpu] fix pad operator (#17775)
guschmue Oct 3, 2023
992f3e4
[js/webgpu] Support where (#17544)
axinging Oct 3, 2023
8e6019a
[QNN EP] Enable QNN Saver for debugging issues (#17747)
adrianlizarraga Oct 3, 2023
a05580e
StableDiffusion XL with TensorRT EP (#17748)
tianleiwu Oct 4, 2023
1bc1157
Unify handling of public headers in onnxruntime.cmake. (#17779)
edgchen1 Oct 4, 2023
db3901a
[js/webgpu] Enable the NCHW ConvMatMul path (#17717)
qjia7 Oct 5, 2023
d6dad96
Add CUDA EP in StableDiffusion demo (#17788)
tianleiwu Oct 5, 2023
e1a089c
[QNN EP] Skip Op validation for Q & DQ node with 5D data (#17792)
HectorSVC Oct 5, 2023
0e98823
[BeamSearch]optimize key cache reordering (#17771)
wangyems Oct 5, 2023
b6bef0f
Add test for iOS dynamic framework (#17790)
edgchen1 Oct 5, 2023
742069a
Add option for max intermediate outputs for MinMaxCalibrater (#17029)
Atticus1806 Oct 5, 2023
faef9c3
ONNX-Native Tensor Parallel: Using Distributed MatMul as Example (#17…
wschin Oct 5, 2023
5be79e2
Remove swift files on ORT main repo (#17799)
YUNQIUGUO Oct 5, 2023
7417fd4
[QNN EP] Add better unit tests for rank 5 ReduceSum (#17802)
adrianlizarraga Oct 5, 2023
be7541e
[Linter] Bump ruff and remove pylint (#17797)
justinchuby Oct 6, 2023
b306b02
[QNN EP] fixed input for InstanceNormU8 unit test and update copy lib…
jywu-msft Oct 6, 2023
3878011
Remove MPI dependency (#17624)
wejoncy Oct 6, 2023
cb9408e
Enable cpp20 builds for DML EP and WinML API (#17800)
smk2007 Oct 6, 2023
735df7e
[webgpu]: add a simple GetCapability implementation (#17643)
snnn Oct 6, 2023
be1e51a
Add length checks to fusion_transpose.py (#17608)
kazssym Oct 6, 2023
6ea4935
[js/web] use esbuild to accelerate bundle build (#17745)
fs-eire Oct 6, 2023
569876f
[TensorRT EP] Refactor OrtTensorRTProviderOptions initialization and …
chilo-ms Oct 6, 2023
385fab5
[QNN EP] Qnn cache improvement (#17757)
HectorSVC Oct 6, 2023
891b50c
General INFO logging tracking occurance of GraphTransformer modificat…
BowenBao Oct 7, 2023
7201def
Fix convergence for dolly+stage3 training (#17685)
pengwa Oct 7, 2023
37f4f27
[ROCm] ONNX Runtime training rocm package for ADO (#17683)
PeixuanZuo Oct 7, 2023
b76994d
Improve CUDA EP's GetCapability (#17809)
snnn Oct 7, 2023
b5a103a
Upgrade transformers to fix CI (#17823)
wschin Oct 7, 2023
faf9a0f
Fix runtime installation error (#17828)
MistEO Oct 7, 2023
c2bd5b7
Fix enable_training and use_migraphx (#17827)
cloudhan Oct 8, 2023
2ef6ee6
[ROCm] Update ROCm and MIGraphX CI to ROCm5.7 (#17834)
PeixuanZuo Oct 9, 2023
60f19ab
Fix Pad's quantization (#17807)
wschin Oct 9, 2023
ba72bb6
Fix a typo in ABI_Dev_Notes.md (#17832)
kyoshisuki Oct 9, 2023
406cd32
[CUDA] GroupQueryAttention operator using FlashAttention (#17674)
aciddelgado Oct 9, 2023
9c716f4
Add noexcep_operators to onnxruntime internal libraries (#17850)
baijumeswani Oct 9, 2023
046939b
Include CoreML in mac os python packages (#17844)
skottmckay Oct 10, 2023
05ac9f6
Split onnxruntime_providers.cmake to multiple (#17853)
snnn Oct 10, 2023
53be802
Onnx_test_runner and onnxruntime_test_all use the same broken test li…
mszhanyi Oct 10, 2023
d9b9c5a
[js/webgpu] support using uniform buffer (#17803)
fs-eire Oct 10, 2023
9a1c884
[QNN EP] Add script to generate Onnx model from native QNN generated …
HectorSVC Oct 10, 2023
d637111
[CUDA/ROCm] Update BiasSplitGelu for SD XL Refiner model (#17849)
tianleiwu Oct 10, 2023
c6f1a1c
update build_jsep.bat to add release build flags (#17471)
fs-eire Oct 11, 2023
5228332
[js] upgrade JS shared dev dependencies (#17831)
fs-eire Oct 11, 2023
948c836
[CUDA/ROCm] Remove limitation of BiasAdd (#17848)
tianleiwu Oct 11, 2023
54b7503
create patch for allgather fn for deepspeed stage 3 (#17855)
ajindal1 Oct 11, 2023
0e27824
Support inplace update for PythonOp/Grad (#17687)
pengwa Oct 11, 2023
a441a71
[js/web] support different export format for ort-web (#17878)
fs-eire Oct 11, 2023
b8f373b
Add API for NPU Device Selection in the DML EP (#17612)
nums11 Oct 11, 2023
d532645
[js/webgpu] revise uniform support (#17871)
fs-eire Oct 11, 2023
63dc5dc
Add document for PythonOp (#17888)
pengwa Oct 12, 2023
565bead
[QNN EP] Support Softmax/LogSoftmax with any axis attribute (#17877)
adrianlizarraga Oct 12, 2023
b3cab55
[WebNN EP] Add a duplicate entry to support new "dataType" (#17841)
Honry Oct 12, 2023
20798a9
Enable onnx_test_runner to run the whole models dir in CI machine (#1…
mszhanyi Oct 12, 2023
138ccec
Change how "NPM packaging pipeline" downloads packages from another p…
snnn Oct 12, 2023
25bbd8d
[js/web] allow gpu IO binding tests to fail temporarily (#17892)
fs-eire Oct 12, 2023
e2cd674
Fix GroupNorm fusion: skip if num of channels not supported (#17869)
tianleiwu Oct 12, 2023
74a8acf
Set default value for NVCC threads (#17866)
gedoensmax Oct 12, 2023
9d07ca3
Move compliance check before publishing pipeline artifact (#17857)
mszhanyi Oct 12, 2023
fa0a79a
Fix Triton Compile Error for Codegened Dropout Code (#17899)
centwang Oct 12, 2023
2efab54
Fix missing registration for new dml device selection API (#17898)
smk2007 Oct 12, 2023
809c890
Update TestCase.cc: exclude a test for DML (#17909)
snnn Oct 12, 2023
c373a80
Add "glue" between training WASM artifacts and training web (#17474)
carzh Oct 12, 2023
163218d
[WebNN EP] Update Op Softmax for readability (#17826)
Oct 12, 2023
3f3ece4
Update NDK to 26.0.10792818 (#17852)
snnn Oct 12, 2023
ca8cab2
distributed slice (#17761)
souptc Oct 12, 2023
ba7f20a
Fix illegal opcode error from mlas (#17885)
skottmckay Oct 12, 2023
0731731
CUDA EP vs ROCM EP hipify audit (#17776)
jeffdaily Oct 13, 2023
0c5b159
[ROCm] Add ROCm Debug wheels to private ADO Feeds (#17887)
PeixuanZuo Oct 13, 2023
dad70ad
[QNN EP] Handle rank 3 InstanceNormalization with N != 1 (#17897)
adrianlizarraga Oct 13, 2023
4e2a03d
[QNN EP] Fix topological node unit traversal during validation (#17913)
adrianlizarraga Oct 13, 2023
67d7eb3
[CUDA] Fix SkipLayerNorm strict mode when skip has broadcast (#17896)
tianleiwu Oct 13, 2023
635d3fa
Remove half of the compiled shaders for gridsample with unused types …
smk2007 Oct 13, 2023
28c1944
[TensorRT EP] Add back creation cudnn and cublas using external cuda …
chilo-ms Oct 13, 2023
7551dd0
Fix build break with cuda 12.2 (#17922)
yufenglee Oct 13, 2023
c695de9
Update eval_squad to use API of latest optimum (#17918)
tianleiwu Oct 13, 2023
762703e
Support output cross qk, dtw and more for whisper model (#17500)
zhanghuanrong Oct 13, 2023
c6c3555
Custom op shape inference API (#17737)
RandySheriffH Oct 13, 2023
9c65d55
[WebNN EP] Fixed wasm heap overflow for big model (#17902)
Honry Oct 13, 2023
3b69d9b
[QNN EP] Fix index-out-of-bounds bug in Slice builder when initialize…
adrianlizarraga Oct 13, 2023
11af344
Add MatMul 4bits support on GPU (#17890)
yufenglee Oct 13, 2023
a55b268
Add save_attribute option to quantize_static (#17945)
zhipenghan Oct 14, 2023
ae21199
Attempt to make the usage of the Android emulator in CIs more robust …
skottmckay Oct 14, 2023
209b6db
add onnxruntime_float16.h into header validation list. (#17935)
mszhanyi Oct 16, 2023
f7341e8
enable training for win-wasm-ci.yml (#17954)
fs-eire Oct 16, 2023
ad817d0
[js/web] optimize tsc for web: split out "npm prepare" (#17955)
fs-eire Oct 16, 2023
8abaa7b
[TensorRT EP] Fix cmake install (#17923)
chilo-ms Oct 16, 2023
7c17e33
Make CUDA a NHWC EP (#17200)
gedoensmax Oct 16, 2023
cf974f0
Bump @babel/traverse from 7.18.2 to 7.23.2 in /js/react_native (#17962)
dependabot[bot] Oct 16, 2023
83547d3
[CUDA] Fix SkipLayerNorm vectorized kernel out-of-bounds read (#17943)
tianleiwu Oct 16, 2023
6832b68
Fix missing attribute on C# DOrtGetResizedStringTensorElementBuffer d…
skottmckay Oct 17, 2023
9356986
Fix AMD builds and enable testing NHWC CUDA ops in one GPU CI (#17972)
hariharans29 Oct 17, 2023
57c8736
Move a nodejs test to a different machine pool (#17970)
snnn Oct 17, 2023
3456831
[java] Make the backing byte buffer in an OrtValue accessible (#16578)
Craigacp Oct 17, 2023
2ef7abf
support for fp16 in GetClipMinMax() (#17967)
guschmue Oct 17, 2023
6557538
[DML EP] Enable more MHA masks (#17882)
PatriceVignola Oct 18, 2023
61f1a16
Fix MHA shape inference (#18009)
PatriceVignola Oct 18, 2023
59ae3fd
[CUDA] StableDiffusion XL demo with CUDA EP (#17997)
tianleiwu Oct 18, 2023
f9694c5
Bump @babel/traverse from 7.18.5 to 7.23.2 in /js/react_native/e2e (#…
dependabot[bot] Oct 18, 2023
2294710
[js/web] FP16 LayerNorm, InstanceNorm, SkipLayerNorm (#17630)
dakenf Oct 18, 2023
a2c6283
Fix Packed MultiHead Attention (#17996)
aciddelgado Oct 18, 2023
cbb0e0f
Create a new Dockerfile for cuda 12 and trt 8.6.1.6-1.cuda12.0 (#18000)
jchen351 Oct 18, 2023
35ecce4
[QNN EP] Reduce overhead of QNN context binary loading (#17965)
HectorSVC Oct 18, 2023
99b8dca
Disable dml stage in windows GPU pipeline temporarily. (#18034)
mszhanyi Oct 20, 2023
cc7e8cc
Update dockerfiles/Dockerfile.source to avoid installing onnx (#17975)
snnn Oct 20, 2023
a43c57f
ResizeGrad CUDA/ROCM kernel implementation (#17772)
baijumeswani Oct 20, 2023
020824e
Update ONNX to 1.15.0rc1 (#17914)
liqunfu Oct 20, 2023
2f57625
[TensorRT EP] Add stream sync after enqueue (#18026)
chilo-ms Oct 20, 2023
009cd4e
Allow cuda custom ops allocate deferred cpu mem (#17893)
RandySheriffH Oct 20, 2023
444a0ed
Avoid one time clone to save memory peak (#17934)
pengwa Oct 21, 2023
b7ae293
Support large model export using multi-gpu (#17990)
wejoncy Oct 22, 2023
f0d5ea5
[QNN EP] Disable flaky test QnnCPUBackendTests.MatMulOp_Broadcast (#1…
HectorSVC Oct 23, 2023
8a12b2c
[js/webgpu] Fix the transpose error when dims > 4D (#18027)
qjia7 Oct 23, 2023
2a17d5c
LLaMA Model Optimization (#18021)
kunal-vaishnavi Oct 23, 2023
780ee18
[aarch64] Implement QGEMM kernels with UMMLA/SMMLA instructions (#17160)
snadampal Oct 23, 2023
f3cfe08
[JS/Web] Enabled 1d spacial input to GlobalAveragePool (#17973)
satyajandhyala Oct 23, 2023
2c50b75
Functions Ahead Of Time inlininng (#17764)
yuslepukhin Oct 24, 2023
4ffd022
[TensorRT EP] Refactor of TRT plugins support (#17946)
chilo-ms Oct 24, 2023
555b2af
[TensorRT EP] Add unit test for user provided cuda stream (#17974)
chilo-ms Oct 24, 2023
688524a
[CUDA EP] Add warning logs when adding memcpy nodes (#18032)
tianleiwu Oct 24, 2023
eb47008
[js/webgpu] FP16 Cast, Resize (#18035)
qjia7 Oct 24, 2023
e63ccd3
Install CUDA 12.2 on Windows (#18044)
jchen351 Oct 24, 2023
abb3291
Update win-wasm-ci.yml: increase the timeout value (#18023)
snnn Oct 24, 2023
efa0cc2
implement isinf20 and isnan20 (#17874)
liqunfu Oct 24, 2023
6ec45f2
Merge aiinfra-linux-ARM64-CPU-2019 and onnxruntime-linux-ARM64-CPU-20…
snnn Oct 24, 2023
76e275b
Merge Cuda docker files into a single one (#18020)
jchen351 Oct 24, 2023
ae85619
Introduce new optimizer MatMul + BatchNormalization (#17915)
sumitsays Oct 25, 2023
2c6b31c
FP16 optimizer automatically detect DeepSpeed compatibility (#18084)
pengwa Oct 25, 2023
706e13e
implement affinegrid cpu kernel (#17777)
liqunfu Oct 25, 2023
d88d52e
[aarch64] Remove mmla kernel support from apple (#18082)
snadampal Oct 25, 2023
d30d4d3
Add MatMul FP4 and NF4 Support (#18066)
jambayk Oct 25, 2023
538e97c
[DML EP] Add dynamic graph compilation (#17876)
PatriceVignola Oct 26, 2023
0f72739
Disable ccache for WinML build (#18104)
snnn Oct 26, 2023
64de71c
[js/web/training] Add CreateTrainingSession (#17891)
carzh Oct 26, 2023
b023de0
Redo #18044 Install CUDA 12.2 on Windows (#18093)
jchen351 Oct 26, 2023
455a9ce
[TensorRT EP] Use latest onnx-tensorrt parser (#18067)
chilo-ms Oct 26, 2023
a514a68
Support per-tensor device mesh at op level (#18025)
wschin Oct 26, 2023
f2e19a8
Updates to training pipelines to reduce CI time (#18116)
askhade Oct 26, 2023
7c18c60
Change cuda image for tensorRT to the one with cudnn8 (#18102)
jchen351 Oct 26, 2023
b7bee62
[CUDA] Remove shape warnings in NHWC <> NCHW unit tests (#17992)
gedoensmax Oct 26, 2023
52f4968
[js/webgpu] Change timestamp-query-in-passes to timestamp-query (#18108)
Oct 26, 2023
37873be
enable reduce ops on opset18 (#18053)
souptc Oct 26, 2023
b7408f7
[ORTModule] ATen Efficient Attention and Triton Flash Attention (#17959)
centwang Oct 27, 2023
0f3a067
[FIX] reorder initializer (#18097)
mindest Oct 27, 2023
b79ea74
Add updates to LLaMA scripts (#18076)
kunal-vaishnavi Oct 27, 2023
9c32310
Distributed Reshape Implementation (#18068)
wschin Oct 27, 2023
c10b83e
Update python cryptography version to 41.0.4 (#18056)
xadupre Oct 27, 2023
b5f242e
GemmFloat8 as a contrib ops (#16051)
xadupre Oct 27, 2023
58f1d15
Replace Transpose with Replace if they are equivalent (#18096)
guyang3532 Oct 27, 2023
2eeafc3
Enable global TRT timing cache (#17865)
gedoensmax Oct 27, 2023
28ad3ff
Fix stale bot issue (#18064)
sophies927 Oct 27, 2023
d9695de
[WebNN EP] Remove Conv initializer constraint for GPU (#18129)
Oct 27, 2023
8daabf3
Tune min version supporint custom op ComputeV2 (#18134)
RandySheriffH Oct 27, 2023
24f9c1a
Distributed Expand (#18126)
wschin Oct 28, 2023
0e34100
create memory descriptors based on the tensor dimensions (#15848)
snadampal Oct 29, 2023
8ebdd3b
Fix regression in perf test runner (#18139)
hariharans29 Oct 30, 2023
436056d
Revert "Disable dml stage in windows GPU pipeline temporarily. (#1803…
mszhanyi Oct 30, 2023
9bba990
[js/web] fix a few package consuming problems (#18109)
fs-eire Oct 30, 2023
be2f72a
[QNN EP] Disable early termination in GetCapability (#18140)
HectorSVC Oct 30, 2023
4819fbf
Augment blockwise quantization (#18101)
chenfucn Oct 30, 2023
348a963
[DML EP] Handle non-raw data in dynamic graph compilation (#18160)
PatriceVignola Oct 30, 2023
90d1f53
optimize SLN with large dimension (#18138)
yufenglee Oct 30, 2023
785e2b1
[js/webgpu] Optimize softmax by vector (#18153)
qjia7 Oct 30, 2023
efef640
[ROCm] update rocm package exclude libs (#18130)
PeixuanZuo Oct 31, 2023
8ed9bd6
Add one more MHA mask pattern (#18164)
PatriceVignola Oct 31, 2023
8a574b8
Update setup_env_cuda.bat (#18176)
jchen351 Oct 31, 2023
08dce54
Improve tunable verbose log (#17328)
cloudhan Oct 31, 2023
1c25fe5
Fix PoliCheck (#18180)
centwang Oct 31, 2023
29e4098
Update batch file to set PATH for Cuda with TRT (#18182)
jchen351 Oct 31, 2023
95f053c
[CUDA] Update GroupNorm and Add SkipGroupNorm (#18091)
tianleiwu Oct 31, 2023
20f2dd8
use onnx rel-1.15.0, update cgman, cmake/external and requirement has…
liqunfu Oct 31, 2023
ed41a28
Fix cast removal bug (#17953)
adityagoel4512 Oct 31, 2023
62c7894
Add mobile CIs to list run by script for external PRs. (#18094)
skottmckay Oct 31, 2023
2b95e74
Versioning for custom op (#18088)
RandySheriffH Oct 31, 2023
d1b85f5
Reduce LLaMA memory usage (#18181)
kunal-vaishnavi Nov 1, 2023
c181159
[WebNN EP] Restore to use deviceType enum (#18154)
Honry Nov 1, 2023
819b5a3
Split KV on MHA and Attention ops (#18007)
aciddelgado Nov 1, 2023
69f0297
[QNN EP] Fix Batch Normalization Op Builder (#17981)
weischan-quic Nov 1, 2023
d87216b
Openvino ep ort 23.1 (#17911)
preetha-intel Nov 1, 2023
9e8ad39
Distributed Reduction (#18206)
wschin Nov 1, 2023
a2e9ba7
[JS/Web]Added FusedConv. (#17766)
satyajandhyala Nov 1, 2023
178f7ca
GQA Memory Efficient Kernel (#17920)
aciddelgado Nov 2, 2023
dabd395
llama 70b model fusion and shardding (#18175)
frank-dong-ms Nov 2, 2023
f9d5705
[EP Perf] Fix sort (#18174)
yf711 Nov 2, 2023
e3b043b
[js/web/training] runTrainStep implementation (#18006)
carzh Nov 2, 2023
c8e1038
Optimize 4bit Qlora training (#18131)
pengwa Nov 2, 2023
8978bdc
add bfloat16 support for where operator (#18118)
prathikr Nov 2, 2023
8d48d3e
[js/web] optimize reduce related operators (#17957)
xhcao Nov 2, 2023
d8d7952
Disable ccache for DML (#18230)
snnn Nov 2, 2023
9f5a685
Rerun the flaky ort-web tests automatically (#18187)
mszhanyi Nov 3, 2023
1439da3
Partially disable QGemm tests for float 8 types (#18196)
xadupre Nov 3, 2023
016b752
Pre-link when creating static library for apple framework (#18241)
skottmckay Nov 3, 2023
e36d003
Introduce new optimizer Pad + Conv/MaxPool (#18136)
sumitsays Nov 3, 2023
4f2096b
Update XNNPACK to latest version (#18038)
skottmckay Nov 3, 2023
c352e9b
Rework/cleanup the C# build infrastructure for nuget packages. (#18127)
skottmckay Nov 3, 2023
90f205e
[QNN EP] Fix Pad UT (#17982)
winskuo-quic Nov 3, 2023
e207060
[JS/Web] Added Unifroms support to unary ops. (#18223)
satyajandhyala Nov 3, 2023
192caee
Fix Signed Mismatch (#18258)
nums11 Nov 3, 2023
4c4d79a
Change a bitwise logical xor to logical wise (#18246)
snnn Nov 3, 2023
2ec1f94
Make MlasTestFixture::mlas_tester an inline variable. (#18263)
edgchen1 Nov 3, 2023
26b3964
Block-wise 4b quantization matmul operator change (#18172)
chenfucn Nov 3, 2023
84bdf04
[TensorRT EP] Fix bug for shape tensor input (#18253)
chilo-ms Nov 3, 2023
08eaa1c
Remove internal enforce for IO binding inputs (#18266)
kunal-vaishnavi Nov 3, 2023
dfafcb5
[TensorRT EP] Properly set CUDA_INCLUDE_DIR for onnx-tensorrt (#18274)
chilo-ms Nov 4, 2023
d652b1f
[VitisAI] fix tensor has multi data type (#18188)
BoarQing Nov 6, 2023
b7b8b5b
Fix Eigen-3.4.0 URL and hash (#18290)
mszhanyi Nov 6, 2023
398ef67
Update protobuf python package's version (#18203)
snnn Nov 6, 2023
3b63d85
Fix unit test when TVM EP is enabled (#18189)
xadupre Nov 6, 2023
ad34c67
[QNN EP] Enable Expand op (#18234)
HectorSVC Nov 7, 2023
fb6737e
Distributed Squeeze and Distributed Unsqueeze (#18269)
wschin Nov 7, 2023
276918d
Allow SkipLayerNorm and LayerNorm in rotary attention fusion (#18288)
PatriceVignola Nov 7, 2023
00c2bf3
SkipGroupNorm fusion and SDXL Pipeline Update (#18273)
tianleiwu Nov 7, 2023
630c877
Zhijxu/improve ortmodule python perf a little bit (#13716)
zhijxu-MS Nov 7, 2023
4f15b42
Customize _get_tensor_rank for model export in stage3 (#18294)
pengwa Nov 7, 2023
9868a71
[Fix] Stages to Run couldn't be selected (#18310)
mszhanyi Nov 7, 2023
800ae77
[DML EP] Add RotaryEmbedding (#18158)
PatriceVignola Nov 7, 2023
a16d528
[JS/Web] Added Uniforms support to binary ops. (#18260)
satyajandhyala Nov 7, 2023
83c0275
add bfloat16 support for ConcatTraining and SplitTraining ops (#18280)
prathikr Nov 7, 2023
6127dd1
implement gridsample 20 (#17744)
liqunfu Nov 7, 2023
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
22 changes: 0 additions & 22 deletions .github/stale.yml

This file was deleted.

34 changes: 34 additions & 0 deletions .github/workflows/stale.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
name: Close stale issues
on:
# Allows you to dictate when you want this workflow to run using cron syntax (times in UTC)
schedule:
- cron: "0 15 * * *"
# Allows you to run this workflow manually from the Actions tab
# workflow_dispatch:

jobs:
close-stale-issues:
runs-on: ubuntu-latest
permissions:
issues: write
pull-requests: write
steps:
- uses: actions/[email protected]
with:
# Comma separated list of labels that can be assigned to issues to exclude them from being marked as stale
exempt-issue-labels: contributions welcome, feature request, regression
# Number of days without activity before the actions/stale action labels an issue
days-before-issue-stale: 30
# Number of days without activity before the actions/stale action closes an issue
days-before-issue-close: 7
# Label you want to apply to issues that have been inactive for the amount of time specified by days-before-issue-stale
stale-issue-label: "stale"
# Comment that you want to add to issues that are labeled by the actions/stale action
stale-issue-message: "This issue has been automatically marked as stale due to inactivity and will be closed in 7 days if no further activity occurs. If further support is needed, please provide an update and/or more details."
# Comment that you want to add to issues that are closed by the actions/stale action
close-issue-message: "This issue has been automatically closed due to inactivity. Please reactivate if further support is needed."
# If you never want this action to label PRs, set this value to -1
days-before-pr-stale: -1
# If you never want this action to close PRs, set this value to -1
days-before-pr-close: -1
repo-token: ${{ secrets.GITHUB_TOKEN }}
29 changes: 2 additions & 27 deletions .lintrunner.toml
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,7 @@ exclude_patterns = [
'cmake/external/**',
# ignore generated flatbuffers code
'onnxruntime/core/flatbuffers/ort_flatbuffers_py/**',
'orttraining/orttraining/python/training/optim/_ds_code_store.py',
]
command = [
'python',
Expand Down Expand Up @@ -76,6 +77,7 @@ exclude_patterns = [
'cmake/**',
'orttraining/*',
'onnxruntime/core/flatbuffers/**',
'orttraining/orttraining/python/training/optim/_ds_code_store.py',
]
command = [
'python',
Expand All @@ -97,33 +99,6 @@ init_command = [
]
is_formatter = true

[[linter]]
code = 'PYLINT'
include_patterns = [
# TODO: Opt in to pylint by adding paths here
]
exclude_patterns = [
]
command = [
'python',
'-m',
'lintrunner_adapters',
'run',
'pylint_linter',
'--rcfile=pyproject.toml',
'--',
'@{{PATHSFILE}}'
]
init_command = [
'python',
'-m',
'lintrunner_adapters',
'run',
'pip_init',
'--dry-run={{DRYRUN}}',
'--requirement=requirements-lintrunner.txt',
]

[[linter]]
code = 'RUSTFMT'
include_patterns = ['**/*.rs']
Expand Down
1 change: 1 addition & 0 deletions .vscode/settings.json
Original file line number Diff line number Diff line change
Expand Up @@ -40,3 +40,4 @@
"-build/include_subdir",
"-runtime/references"
]
}
109 changes: 0 additions & 109 deletions Package.swift

This file was deleted.

49 changes: 0 additions & 49 deletions cgmanifests/generate_cgmanifest.py
Original file line number Diff line number Diff line change
Expand Up @@ -90,55 +90,6 @@ def add_github_dep(name, parsed_url):
git_deps[dep] = name


with open(
os.path.join(REPO_DIR, "tools", "ci_build", "github", "linux", "docker", "Dockerfile.manylinux2_28_cuda11"),
) as f:
for line in f:
if not line.strip():
package_name = None
package_filename = None
package_url = None
if package_filename is None:
m = re.match(r"RUN\s+export\s+(.+?)_ROOT=(\S+).*", line)
if m is not None:
package_name = m.group(1)
package_filename = m.group(2)
else:
m = re.match(r"RUN\s+export\s+(.+?)_VERSION=(\S+).*", line)
if m is not None:
package_name = m.group(1)
package_filename = m.group(2)
elif package_url is None:
m = re.match(r"(.+?)_DOWNLOAD_URL=(\S+)", line)
if m is not None:
package_url = m.group(2)
if package_name == "LIBXCRYPT":
package_url = m.group(2) + "/v" + package_filename + ".tar.gz"
elif package_name == "CMAKE":
package_url = m.group(2) + "/v" + package_filename + "/cmake-" + package_filename + ".tar.gz"
else:
package_url = m.group(2) + "/" + package_filename + ".tar.gz"
parsed_url = urlparse(package_url)
if parsed_url.hostname == "github.com":
add_github_dep("manylinux dependency " + package_name, parsed_url)
else:
registration = {
"Component": {
"Type": "other",
"other": {
"Name": package_name.lower(),
"Version": package_filename.split("-")[-1],
"DownloadUrl": package_url,
},
"comments": "manylinux dependency",
}
}
registrations.append(registration)
package_name = None
package_filename = None
package_url = None


def normalize_path_separators(path):
return path.replace(os.path.sep, "/")

Expand Down
80 changes: 2 additions & 78 deletions cgmanifests/generated/cgmanifest.json
Original file line number Diff line number Diff line change
Expand Up @@ -2,82 +2,6 @@
"$schema": "https://json.schemastore.org/component-detection-manifest.json",
"Version": 1,
"Registrations": [
{
"Component": {
"Type": "other",
"other": {
"Name": "autoconf",
"Version": "2.71",
"DownloadUrl": "http://ftp.gnu.org/gnu/autoconf/autoconf-2.71.tar.gz"
},
"comments": "manylinux dependency"
}
},
{
"Component": {
"Type": "other",
"other": {
"Name": "automake",
"Version": "1.16.5",
"DownloadUrl": "http://ftp.gnu.org/gnu/automake/automake-1.16.5.tar.gz"
},
"comments": "manylinux dependency"
}
},
{
"Component": {
"Type": "other",
"other": {
"Name": "libtool",
"Version": "2.4.7",
"DownloadUrl": "http://ftp.gnu.org/gnu/libtool/libtool-2.4.7.tar.gz"
},
"comments": "manylinux dependency"
}
},
{
"Component": {
"Type": "other",
"other": {
"Name": "git",
"Version": "2.36.2",
"DownloadUrl": "https://www.kernel.org/pub/software/scm/git/git-2.36.2.tar.gz"
},
"comments": "manylinux dependency"
}
},
{
"Component": {
"Type": "other",
"other": {
"Name": "sqlite_autoconf",
"Version": "3390200",
"DownloadUrl": "https://www.sqlite.org/2022/sqlite-autoconf-3390200.tar.gz"
},
"comments": "manylinux dependency"
}
},
{
"Component": {
"Type": "other",
"other": {
"Name": "openssl",
"Version": "1.1.1q",
"DownloadUrl": "https://www.openssl.org/source/openssl-1.1.1q.tar.gz"
},
"comments": "manylinux dependency"
}
},
{
"component": {
"type": "git",
"git": {
"commitHash": "50cf2b6dd4fdf04309445f2eec8de7051d953abf",
"repositoryUrl": "https://github.com/besser82/libxcrypt.git"
},
"comments": "manylinux dependency LIBXCRYPT"
}
},
{
"component": {
"type": "git",
Expand All @@ -102,7 +26,7 @@
"component": {
"type": "git",
"git": {
"commitHash": "e2525550194ce3d8a2c4a3af451c9d9b3ae6650e",
"commitHash": "b86cc54efce19530fb953e4b21f57e6b3888534c",
"repositoryUrl": "https://github.com/onnx/onnx.git"
},
"comments": "git submodule at cmake/external/onnx"
Expand Down Expand Up @@ -272,7 +196,7 @@
"component": {
"type": "git",
"git": {
"commitHash": "0462dc31ae78f48744b6141ae376df1f96d3f459",
"commitHash": "a43ce67187bab219520fd80f21af8bbd4354bc8c",
"repositoryUrl": "https://github.com/onnx/onnx-tensorrt.git"
},
"comments": "onnx_tensorrt"
Expand Down
Loading