/**
* Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
* SPDX-License-Identifier: Apache-2.0.
*/
#pragma once
#include The metrics of recommendations.See Also:
AWS
* API Reference
Defines the cost per hour for the instance.
*/ inline double GetCostPerHour() const{ return m_costPerHour; } /** *Defines the cost per hour for the instance.
*/ inline bool CostPerHourHasBeenSet() const { return m_costPerHourHasBeenSet; } /** *Defines the cost per hour for the instance.
*/ inline void SetCostPerHour(double value) { m_costPerHourHasBeenSet = true; m_costPerHour = value; } /** *Defines the cost per hour for the instance.
*/ inline RecommendationMetrics& WithCostPerHour(double value) { SetCostPerHour(value); return *this;} /** *Defines the cost per inference for the instance .
*/ inline double GetCostPerInference() const{ return m_costPerInference; } /** *Defines the cost per inference for the instance .
*/ inline bool CostPerInferenceHasBeenSet() const { return m_costPerInferenceHasBeenSet; } /** *Defines the cost per inference for the instance .
*/ inline void SetCostPerInference(double value) { m_costPerInferenceHasBeenSet = true; m_costPerInference = value; } /** *Defines the cost per inference for the instance .
*/ inline RecommendationMetrics& WithCostPerInference(double value) { SetCostPerInference(value); return *this;} /** *The expected maximum number of requests per minute for the instance.
*/ inline int GetMaxInvocations() const{ return m_maxInvocations; } /** *The expected maximum number of requests per minute for the instance.
*/ inline bool MaxInvocationsHasBeenSet() const { return m_maxInvocationsHasBeenSet; } /** *The expected maximum number of requests per minute for the instance.
*/ inline void SetMaxInvocations(int value) { m_maxInvocationsHasBeenSet = true; m_maxInvocations = value; } /** *The expected maximum number of requests per minute for the instance.
*/ inline RecommendationMetrics& WithMaxInvocations(int value) { SetMaxInvocations(value); return *this;} /** *The expected model latency at maximum invocation per minute for the * instance.
*/ inline int GetModelLatency() const{ return m_modelLatency; } /** *The expected model latency at maximum invocation per minute for the * instance.
*/ inline bool ModelLatencyHasBeenSet() const { return m_modelLatencyHasBeenSet; } /** *The expected model latency at maximum invocation per minute for the * instance.
*/ inline void SetModelLatency(int value) { m_modelLatencyHasBeenSet = true; m_modelLatency = value; } /** *The expected model latency at maximum invocation per minute for the * instance.
*/ inline RecommendationMetrics& WithModelLatency(int value) { SetModelLatency(value); return *this;} /** *The expected CPU utilization at maximum invocations per minute for the * instance.
NaN
indicates that the value is not
* available.
The expected CPU utilization at maximum invocations per minute for the * instance.
NaN
indicates that the value is not
* available.
The expected CPU utilization at maximum invocations per minute for the * instance.
NaN
indicates that the value is not
* available.
The expected CPU utilization at maximum invocations per minute for the * instance.
NaN
indicates that the value is not
* available.
The expected memory utilization at maximum invocations per minute for the * instance.
NaN
indicates that the value is not
* available.
The expected memory utilization at maximum invocations per minute for the * instance.
NaN
indicates that the value is not
* available.
The expected memory utilization at maximum invocations per minute for the * instance.
NaN
indicates that the value is not
* available.
The expected memory utilization at maximum invocations per minute for the * instance.
NaN
indicates that the value is not
* available.
The time it takes to launch new compute resources for a serverless endpoint. * The time can vary depending on the model size, how long it takes to download the * model, and the start-up time of the container.
NaN
* indicates that the value is not available.
The time it takes to launch new compute resources for a serverless endpoint. * The time can vary depending on the model size, how long it takes to download the * model, and the start-up time of the container.
NaN
* indicates that the value is not available.
The time it takes to launch new compute resources for a serverless endpoint. * The time can vary depending on the model size, how long it takes to download the * model, and the start-up time of the container.
NaN
* indicates that the value is not available.
The time it takes to launch new compute resources for a serverless endpoint. * The time can vary depending on the model size, how long it takes to download the * model, and the start-up time of the container.
NaN
* indicates that the value is not available.