tensorflow/inference/docker/build_artifacts/sagemaker/serve.py [70:117]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self._tfs_inter_op_parallelism = os.environ.get("SAGEMAKER_TFS_INTER_OP_PARALLELISM", 0)
        self._tfs_intra_op_parallelism = os.environ.get("SAGEMAKER_TFS_INTRA_OP_PARALLELISM", 0)
        self._gunicorn_worker_class = os.environ.get("SAGEMAKER_GUNICORN_WORKER_CLASS", "gevent")
        self._gunicorn_timeout_seconds = int(
            os.environ.get("SAGEMAKER_GUNICORN_TIMEOUT_SECONDS", 30)
        )
        self._nginx_proxy_read_timeout_seconds = int(
            os.environ.get("SAGEMAKER_NGINX_PROXY_READ_TIMEOUT_SECONDS", 60)
        )

        # Nginx proxy read timeout should not be less than the GUnicorn timeout. If it is, this
        # can result in upstream time out errors.
        if self._gunicorn_timeout_seconds > self._nginx_proxy_read_timeout_seconds:
            log.info(
                "GUnicorn timeout was higher than Nginx proxy read timeout."
                " Setting Nginx proxy read timeout from {} seconds to {} seconds"
                " to match GUnicorn timeout.".format(
                    self._nginx_proxy_read_timeout_seconds, self._gunicorn_timeout_seconds
                )
            )
            self._nginx_proxy_read_timeout_seconds = self._gunicorn_timeout_seconds

        if os.environ.get("OMP_NUM_THREADS") is None:
            os.environ["OMP_NUM_THREADS"] = "1"

        if _enable_multi_model_endpoint not in ["true", "false"]:
            raise ValueError("SAGEMAKER_MULTI_MODEL must be 'true' or 'false'")
        self._tfs_enable_multi_model_endpoint = _enable_multi_model_endpoint == "true"

        self._need_python_service()
        log.info("PYTHON SERVICE: {}".format(str(self._enable_python_service)))

        if _enable_batching not in ["true", "false"]:
            raise ValueError("SAGEMAKER_TFS_ENABLE_BATCHING must be 'true' or 'false'")
        self._tfs_enable_batching = _enable_batching == "true"

        if _enable_multi_model_endpoint not in ["true", "false"]:
            raise ValueError("SAGEMAKER_MULTI_MODEL must be 'true' or 'false'")
        self._tfs_enable_multi_model_endpoint = _enable_multi_model_endpoint == "true"

        self._use_gunicorn = self._enable_python_service or self._tfs_enable_multi_model_endpoint

        if self._sagemaker_port_range is not None:
            parts = self._sagemaker_port_range.split("-")
            low = int(parts[0])
            hi = int(parts[1])
            self._tfs_grpc_ports = []
            self._tfs_rest_ports = []
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tensorflow/inference/docker/build_artifacts/sagemaker_neuron/serve.py [74:121]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self._tfs_inter_op_parallelism = os.environ.get("SAGEMAKER_TFS_INTER_OP_PARALLELISM", 0)
        self._tfs_intra_op_parallelism = os.environ.get("SAGEMAKER_TFS_INTRA_OP_PARALLELISM", 0)
        self._gunicorn_worker_class = os.environ.get("SAGEMAKER_GUNICORN_WORKER_CLASS", "gevent")
        self._gunicorn_timeout_seconds = int(
            os.environ.get("SAGEMAKER_GUNICORN_TIMEOUT_SECONDS", 30)
        )
        self._nginx_proxy_read_timeout_seconds = int(
            os.environ.get("SAGEMAKER_NGINX_PROXY_READ_TIMEOUT_SECONDS", 60)
        )

        # Nginx proxy read timeout should not be less than the GUnicorn timeout. If it is, this
        # can result in upstream time out errors.
        if self._gunicorn_timeout_seconds > self._nginx_proxy_read_timeout_seconds:
            log.info(
                "GUnicorn timeout was higher than Nginx proxy read timeout."
                " Setting Nginx proxy read timeout from {} seconds to {} seconds"
                " to match GUnicorn timeout.".format(
                    self._nginx_proxy_read_timeout_seconds, self._gunicorn_timeout_seconds
                )
            )
            self._nginx_proxy_read_timeout_seconds = self._gunicorn_timeout_seconds

        if os.environ.get("OMP_NUM_THREADS") is None:
            os.environ["OMP_NUM_THREADS"] = "1"

        if _enable_multi_model_endpoint not in ["true", "false"]:
            raise ValueError("SAGEMAKER_MULTI_MODEL must be 'true' or 'false'")
        self._tfs_enable_multi_model_endpoint = _enable_multi_model_endpoint == "true"

        self._need_python_service()
        log.info("PYTHON SERVICE: {}".format(str(self._enable_python_service)))

        if _enable_batching not in ["true", "false"]:
            raise ValueError("SAGEMAKER_TFS_ENABLE_BATCHING must be 'true' or 'false'")
        self._tfs_enable_batching = _enable_batching == "true"

        if _enable_multi_model_endpoint not in ["true", "false"]:
            raise ValueError("SAGEMAKER_MULTI_MODEL must be 'true' or 'false'")
        self._tfs_enable_multi_model_endpoint = _enable_multi_model_endpoint == "true"

        self._use_gunicorn = self._enable_python_service or self._tfs_enable_multi_model_endpoint

        if self._sagemaker_port_range is not None:
            parts = self._sagemaker_port_range.split("-")
            low = int(parts[0])
            hi = int(parts[1])
            self._tfs_grpc_ports = []
            self._tfs_rest_ports = []
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -