Sagemaker Optimize

Find an optimized serving configuration for a model with Amazon SageMaker AI inference recommendations, then deploy it and compare against a baseline benchmark. Covers both config search (best instance + serving knobs) and deep optimization (speculative decoding / EAGLE 3, quantization, kernel tuning). Use when the user asks to optimize, speed up, tune, or get a recommendation for a deployed or to-be-deployed model.

aws-samples Updated 141 repo stars
From model to production: agentic AI model deployment on Amazon SageMaker

File contents

aws-samples/sample-sagemaker-agentic-model-deployment commit ccccaa6462

Frequently asked questions

npx get-skill add aws-samples/sagemaker-optimize