Orchestrating SageMaker AI endpoint auto scaling with AWS CDK
Updating a SageMaker AI endpoint that has Application Auto Scaling registered makes AWS CloudFormation and AWS CDK deployments fail. This post shows how to build a reusable AWS CDK construct with CloudFormation custom resources that deregisters and re-registers auto scaling automatically, so you can update the endpoint and its scaling in a single deployment.
AWS Machine Learning has published a post detailing the issue of updating Amazon SageMaker AI real-time endpoint configurations, which can lead to deployments failing when using AWS CloudFormation or the AWS Cloud Development Kit (AWS CDK). The problem arises because SageMaker AI requires deregistering scalable targets before updating endpoints, but CloudFormation cannot track AWS Application Auto Scaling resources when they are deregistered.
To solve this issue, AWS Machine Learning introduces a reusable CDK construct with AWS CloudFormation custom resources, allowing for automatic deregister and registration of auto scaling during endpoint updates. This eliminates the need for manual intervention and ensures that endpoint configurations and auto scaling parameters can be updated in a single deployment.
Brief written by urgent.news from AWS Machine Learning's own syndicated text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
