examples/bls/async_model.py - main - rnekrasov/python_backend

examples/bls/async_model.py
160 строк7 KB
dyastremsky
Add GitHub action to format and lint code (#265)
27 июн 2023, 06:57
27 июн 2023, 06:57902df12
# Copyright 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
# are met:
#  * Redistributions of source code must retain the above copyright
#    notice, this list of conditions and the following disclaimer.
#  * Redistributions in binary form must reproduce the above copyright
#    notice, this list of conditions and the following disclaimer in the
#    documentation and/or other materials provided with the distribution.
#  * Neither the name of NVIDIA CORPORATION nor the names of its
#    contributors may be used to endorse or promote products derived
#    from this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

import asyncio
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 = json.loads(args["model_config"])

    # You must add the Python 'async' keyword to the beginning of `execute`
    # function if you want to use `async_exec` function.
    async 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`
        """

        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")

            # List of awaitables containing inflight inference responses.
            inference_response_awaits = []
            for model_name in ["pytorch", "add_sub"]:
                # Create inference request object
                infer_request = pb_utils.InferenceRequest(
                    model_name=model_name,
                    requested_output_names=["OUTPUT0", "OUTPUT1"],
                    inputs=[in_0, in_1],
                )

                # Store the awaitable inside the array. We don't need
                # the inference response immediately so we do not `await`
                # here.
                inference_response_awaits.append(infer_request.async_exec())

            # Wait for all the inference requests to finish. The execution
            # of the Python script will be blocked until all the awaitables
            # are resolved.
            inference_responses = await asyncio.gather(*inference_response_awaits)

            for infer_response in inference_responses:
                # Make sure that the inference response doesn't have an error.
                # If it has an error and you can't proceed with your model
                # execution you can raise an exception.
                if infer_response.has_error():
                    raise pb_utils.TritonModelException(
                        infer_response.error().message()
                    )

            # Get the OUTPUT0 from the "pytorch" model inference response
            pytorch_output0_tensor = pb_utils.get_output_tensor_by_name(
                inference_responses[0], "OUTPUT0"
            )

            # Get the OUTPUT1 from the "addsub" model inference response
            addsub_output1_tensor = pb_utils.get_output_tensor_by_name(
                inference_responses[1], "OUTPUT1"
            )

            # 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"))
            #
            # Because the infer_response of the models contains the final
            # outputs with correct output names, we can just pass the list
            # of outputs to the InferenceResponse object.
            inference_response = pb_utils.InferenceResponse(
                output_tensors=[pytorch_output0_tensor, addsub_output1_tensor]
            )
            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...")