用 AWS CDK 编排 SageMaker AI 端点自动扩缩
原标题：Orchestrating SageMaker AI endpoint auto scaling with AWS CDK
AI 摘要
AWS 机器学习博客介绍了一种使用 AWS CDK 自定义资源编排 SageMaker AI 端点自动扩缩的方法。由于 SageMaker AI 要求在更新端点前先注销可扩缩目标，而 CloudFormation 无法跟踪注销后的 Application Auto Scaling 资源，直接部署会失败或静默丢失自动扩缩配置。该方案通过三个自定义资源按依赖顺序执行注销、端点更新、重新注册和附加扩缩策略，实现单次部署完成端点与扩缩参数更新。
正文节选
Orchestrating SageMaker AI endpoint auto scaling with AWS CDK Updating the Amazon Sagemaker AI real-time endpoint configuration (changing the instance type, instance count, or environment variables) causes deployments through AWS CloudFormation or the AWS Cloud Development Kit (AWS CDK) to fail. SageMaker AI requires you to deregister the scalable target before updating the endpoint, but when you deregister it, CloudFormation can’t track the AWS Application Auto Scaling resources. In this post,