QuestionQ46

VerifiedDeployment and Orchestration of ML Workflows

A recommendation model uses ML and invokes an Amazon SageMaker AI endpoint to obtain recommendations. An ML engineer must ensure that the model remains available during an anticipated rise in user traffic.

Which solution meets these requirements?

Explanation

Amazon SageMaker AI endpoint auto scaling dynamically adds instances for a hosted model when workload increases, maintaining capacity for increased inference traffic. It is configured for the endpoint’s production variant through SageMaker AI and Application Auto Scaling.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!