/**
* Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
* SPDX-License-Identifier: Apache-2.0.
*/
#pragma once
#include Configures the behavior of the client used by SageMaker to interact with the
* model container during asynchronous inference.See Also:
AWS
* API Reference
The maximum number of concurrent requests sent by the SageMaker client to the * model container. If no value is provided, SageMaker chooses an optimal * value.
*/ inline int GetMaxConcurrentInvocationsPerInstance() const{ return m_maxConcurrentInvocationsPerInstance; } /** *The maximum number of concurrent requests sent by the SageMaker client to the * model container. If no value is provided, SageMaker chooses an optimal * value.
*/ inline bool MaxConcurrentInvocationsPerInstanceHasBeenSet() const { return m_maxConcurrentInvocationsPerInstanceHasBeenSet; } /** *The maximum number of concurrent requests sent by the SageMaker client to the * model container. If no value is provided, SageMaker chooses an optimal * value.
*/ inline void SetMaxConcurrentInvocationsPerInstance(int value) { m_maxConcurrentInvocationsPerInstanceHasBeenSet = true; m_maxConcurrentInvocationsPerInstance = value; } /** *The maximum number of concurrent requests sent by the SageMaker client to the * model container. If no value is provided, SageMaker chooses an optimal * value.
*/ inline AsyncInferenceClientConfig& WithMaxConcurrentInvocationsPerInstance(int value) { SetMaxConcurrentInvocationsPerInstance(value); return *this;} private: int m_maxConcurrentInvocationsPerInstance; bool m_maxConcurrentInvocationsPerInstanceHasBeenSet = false; }; } // namespace Model } // namespace SageMaker } // namespace Aws