使用 Amazon CloudFormation 创建自动扩缩策略 - Amazon SageMaker
Amazon Web Services 文档中描述的 Amazon Web Services 服务或功能可能因区域而异。要查看适用于中国区域的差异,请参阅 中国的 Amazon Web Services 服务入门 (PDF)

使用 Amazon CloudFormation 创建自动扩缩策略

以下示例演示如何使用 Amazon CloudFormation 在端点上激活 Application Auto Scaling。

Endpoint: Type: "AWS::SageMaker::Endpoint" Properties: EndpointName: yourEndpointName EndpointConfigName: yourEndpointConfigName ScalingTarget: Type: "AWS::ApplicationAutoScaling::ScalableTarget" Properties: MaxCapacity: 10 MinCapacity: 2 ResourceId: endpoint/MyEndPoint/variant/MyVariant RoleARN: arn ScalableDimension: sagemaker:variant:DesiredInstanceCount ServiceNamespace: sagemaker ScalingPolicy: Type: "AWS::ApplicationAutoScaling::ScalingPolicy" Properties: PolicyName: myscalablepolicy PolicyType: TargetTrackingScaling ScalingTargetId: Ref: ScalingTarget TargetTrackingScalingPolicyConfiguration: TargetValue: 75.0 ScaleInCooldown: 600 ScaleOutCooldown: 30 PredefinedMetricSpecification: PredefinedMetricType: SageMakerVariantInvocationsPerInstance

有关更多详细信息,请参阅 Amazon CloudFormation AutoScalingPlans API 参考