Add L0 test to protect end-to-end ensemble model (#739)

* L0 test for Ensemble model

* Modify L0_ensemble_model

* Update test_config_generator.py

* Remove unnecessary flags

* Add copyright information

* Copyright

* Correct Copyright body

* Copyright

* Fix precommit errors

examples/quick-start/add/1/model.py

@@ -0,0 +1,121 @@
+#!/usr/bin/env python3
+
+# Copyright 2020-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import json
+
+# triton_python_backend_utils is available in every Triton Python model. You
+# need to use this module to create inference requests and responses. It also
+# contains some utility functions for extracting information from model_config
+# and converting Triton input/output types to numpy types.
+import triton_python_backend_utils as pb_utils
+
+
+class TritonPythonModel:
+    """Your Python model must use the same class name. Every Python model
+    that is created must have "TritonPythonModel" as the class name.
+    """
+
+    def initialize(self, args):
+        """`initialize` is called only once when the model is being loaded.
+        Implementing `initialize` function is optional. This function allows
+        the model to initialize any state associated with this model.
+
+        Parameters
+        ----------
+        args : dict
+          Both keys and values are strings. The dictionary keys and values are:
+          * model_config: A JSON string containing the model configuration
+          * model_instance_kind: A string containing model instance kind
+          * model_instance_device_id: A string containing model instance device ID
+          * model_repository: Model repository path
+          * model_version: Model version
+          * model_name: Model name
+        """
+
+        # You must parse model_config. JSON string is not parsed here
+        self.model_config = model_config = json.loads(args["model_config"])
+
+        # Get OUTPUT0 configuration
+        output0_config = pb_utils.get_output_config_by_name(model_config, "OUTPUT0")
+
+        # Convert Triton types to numpy types
+        self.output0_dtype = pb_utils.triton_string_to_numpy(
+            output0_config["data_type"]
+        )
+
+    def execute(self, requests):
+        """`execute` MUST be implemented in every Python model. `execute`
+        function receives a list of pb_utils.InferenceRequest as the only
+        argument. This function is called when an inference request is made
+        for this model. Depending on the batching configuration (e.g. Dynamic
+        Batching) used, `requests` may contain multiple requests. Every
+        Python model, must create one pb_utils.InferenceResponse for every
+        pb_utils.InferenceRequest in `requests`. If there is an error, you can
+        set the error argument when creating a pb_utils.InferenceResponse
+
+        Parameters
+        ----------
+        requests : list
+          A list of pb_utils.InferenceRequest
+
+        Returns
+        -------
+        list
+          A list of pb_utils.InferenceResponse. The length of this list must
+          be the same as `requests`
+        """
+
+        output0_dtype = self.output0_dtype
+
+        responses = []
+
+        # Every Python backend must iterate over everyone of the requests
+        # and create a pb_utils.InferenceResponse for each of them.
+        for request in requests:
+            # Get INPUT0
+            in_0 = pb_utils.get_input_tensor_by_name(request, "INPUT0")
+            # Get INPUT1
+            in_1 = pb_utils.get_input_tensor_by_name(request, "INPUT1")
+
+            out_0 = in_0.as_numpy() + in_1.as_numpy()
+
+            # Create output tensors. You need pb_utils.Tensor
+            # objects to create pb_utils.InferenceResponse.
+            out_tensor_0 = pb_utils.Tensor("OUTPUT0", out_0.astype(output0_dtype))
+
+            # Create InferenceResponse. You can set an error here in case
+            # there was a problem with handling this inference request.
+            # Below is an example of how you can set errors in inference
+            # response:
+            #
+            # pb_utils.InferenceResponse(
+            #    output_tensors=..., TritonError("An error occurred"))
+            inference_response = pb_utils.InferenceResponse(
+                output_tensors=[out_tensor_0]
+            )
+            responses.append(inference_response)
+
+        # You should return a list of pb_utils.InferenceResponse. Length
+        # of this list must match the length of `requests` list.
+        return responses
+
+    def finalize(self):
+        """`finalize` is called only once when the model is being unloaded.
+        Implementing `finalize` function is OPTIONAL. This function allows
+        the model to perform any necessary clean ups before exit.
+        """
+        print("Cleaning up...")

examples/quick-start/add/config.pbtxt

@@ -0,0 +1,41 @@
+# Copyright (c) 2020-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+name: "add"
+backend: "python"
+
+input [
+  {
+    name: "INPUT0"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  }
+]
+input [
+  {
+    name: "INPUT1"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  }
+]
+output [
+  {
+    name: "OUTPUT0"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  }
+]
+
+instance_group [{ kind: KIND_CPU }]

examples/quick-start/ensemble_add_sub/config.pbtxt

@@ -0,0 +1,80 @@
+# Copyright (c) 2020-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+name: "ensemble_add_sub"
+platform: "ensemble"
+
+input [
+  {
+    name: "INPUT0"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  },
+  {
+    name: "INPUT1"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  }
+]
+
+output [
+  {
+    name: "OUTPUT0"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  },
+  {
+    name: "OUTPUT1"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  }
+]
+
+ensemble_scheduling {
+  step [
+    {
+      model_name: "add"
+      model_version: 1
+      input_map {
+        key: "INPUT0"
+        value: "INPUT0"
+      }
+      input_map {
+        key: "INPUT1"
+        value: "INPUT1"
+      }
+      output_map {
+        key: "OUTPUT0"
+        value: "OUTPUT0"
+      }
+    },
+    {
+      model_name: "sub"
+      model_version: 1
+      input_map {
+        key: "INPUT0"
+        value: "INPUT0"
+      }
+      input_map {
+        key: "INPUT1"
+        value: "INPUT1"
+      }
+      output_map {
+        key: "OUTPUT1"
+        value: "OUTPUT1"
+      }
+    }
+  ]
+}

examples/quick-start/sub/1/model.py

@@ -0,0 +1,121 @@
+#!/usr/bin/env python3
+
+# Copyright 2020-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import json
+
+# triton_python_backend_utils is available in every Triton Python model. You
+# need to use this module to create inference requests and responses. It also
+# contains some utility functions for extracting information from model_config
+# and converting Triton input/output types to numpy types.
+import triton_python_backend_utils as pb_utils
+
+
+class TritonPythonModel:
+    """Your Python model must use the same class name. Every Python model
+    that is created must have "TritonPythonModel" as the class name.
+    """
+
+    def initialize(self, args):
+        """`initialize` is called only once when the model is being loaded.
+        Implementing `initialize` function is optional. This function allows
+        the model to initialize any state associated with this model.
+
+        Parameters
+        ----------
+        args : dict
+          Both keys and values are strings. The dictionary keys and values are:
+          * model_config: A JSON string containing the model configuration
+          * model_instance_kind: A string containing model instance kind
+          * model_instance_device_id: A string containing model instance device ID
+          * model_repository: Model repository path
+          * model_version: Model version
+          * model_name: Model name
+        """
+
+        # You must parse model_config. JSON string is not parsed here
+        self.model_config = model_config = json.loads(args["model_config"])
+
+        # Get OUTPUT1 configuration
+        output1_config = pb_utils.get_output_config_by_name(model_config, "OUTPUT1")
+
+        # Convert Triton types to numpy types
+        self.output1_dtype = pb_utils.triton_string_to_numpy(
+            output1_config["data_type"]
+        )
+
+    def execute(self, requests):
+        """`execute` MUST be implemented in every Python model. `execute`
+        function receives a list of pb_utils.InferenceRequest as the only
+        argument. This function is called when an inference request is made
+        for this model. Depending on the batching configuration (e.g. Dynamic
+        Batching) used, `requests` may contain multiple requests. Every
+        Python model, must create one pb_utils.InferenceResponse for every
+        pb_utils.InferenceRequest in `requests`. If there is an error, you can
+        set the error argument when creating a pb_utils.InferenceResponse
+
+        Parameters
+        ----------
+        requests : list
+          A list of pb_utils.InferenceRequest
+
+        Returns
+        -------
+        list
+          A list of pb_utils.InferenceResponse. The length of this list must
+          be the same as `requests`
+        """
+
+        output1_dtype = self.output1_dtype
+
+        responses = []
+
+        # Every Python backend must iterate over everyone of the requests
+        # and create a pb_utils.InferenceResponse for each of them.
+        for request in requests:
+            # Get INPUT0
+            in_0 = pb_utils.get_input_tensor_by_name(request, "INPUT0")
+            # Get INPUT1
+            in_1 = pb_utils.get_input_tensor_by_name(request, "INPUT1")
+
+            out_1 = in_0.as_numpy() - in_1.as_numpy()
+
+            # Create output tensors. You need pb_utils.Tensor
+            # objects to create pb_utils.InferenceResponse.
+            out_tensor_1 = pb_utils.Tensor("OUTPUT1", out_1.astype(output1_dtype))
+
+            # Create InferenceResponse. You can set an error here in case
+            # there was a problem with handling this inference request.
+            # Below is an example of how you can set errors in inference
+            # response:
+            #
+            # pb_utils.InferenceResponse(
+            #    output_tensors=..., TritonError("An error occurred"))
+            inference_response = pb_utils.InferenceResponse(
+                output_tensors=[out_tensor_1]
+            )
+            responses.append(inference_response)
+
+        # You should return a list of pb_utils.InferenceResponse. Length
+        # of this list must match the length of `requests` list.
+        return responses
+
+    def finalize(self):
+        """`finalize` is called only once when the model is being unloaded.
+        Implementing `finalize` function is OPTIONAL. This function allows
+        the model to perform any necessary clean ups before exit.
+        """
+        print("Cleaning up...")