QuestionQ68

VerifiedDeployment and Orchestration of ML Workflows

A company must deploy a custom-trained classification ML model on AWS. The model needs to produce near-real-time, low-latency predictions and handle changing request volumes.

Which solution meets these requirements?

Explanation

Amazon SageMaker AI real-time endpoints are designed for interactive, low-latency inference. Endpoint auto scaling dynamically adds or removes model-serving instances in response to workload changes, allowing the deployment to accommodate variable request volumes. AWS: Real-time inference AWS: Automatic scaling of Amazon SageMaker AI models

Learn more

Community Discussion

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