AWS CDK builds reusable constructs to resolve the blocking issue during SageMaker endpoint scaling updates.
When a SageMaker real-time AI endpoint has Application Auto Scaling enabled, attempting to update its configuration—such as instance type or count—directly via AWS CDK or CloudFormation will fail. This paper proposes a CDK construct based on custom resources that leverages strict dependency orchestration to achieve atomic updates of both the endpoint’s configuration and its scaling policies, eliminating the need for manual intervention.