SageMaker AI Inference Endpoint Support

[JPfeifer21]

Is your feature request related to a problem? Please describe.

Our team is facing challenges with managing costs associated with AWS SageMaker AI Inference Endpoints. It is particularly frustrating when developers forget to manually scale down endpoints before leaving for the day, resulting in unnecessary operational costs during non-working hours in our test environments.

Describe the feature you'd like

We would like the AWS Instance Scheduler to support automatic scaling down and scaling up of SageMaker AI Inference Endpoints. This would allow endpoints to be managed based on a predefined schedule, similar to how EC2 and RDS instances are managed.

[CrypticCabub]

Thanks for submitting this feature request! We'll add it to our backlog. If anybody else would also like to see this feature, please thumbs-up the original post to help with priorititization.