Amazon SageMaker Inference: 2026 year-to-date launches in review

What moved

Amazon SageMaker AI shipped 13 inference launches in year-to-date across two deployment paths: fully managed endpoints and Amazon SageMaker HyperPod Inference. This post reviews each launch, from inference recommendations and capacity-aware instance pools to tiered KV caching and disaggregated prefill and decode. AWS issued this as an official post on 2026-09-18. The desk files the title and summary from the allow-listed official source, not a rewrite of claims the source did not make.

Why it matters

Amazon SageMaker AI shipped 13 inference launches in year-to-date across two deployment paths: fully managed endpoints and Amazon SageMaker HyperPod Inference. That is a public launch file from AWS, dated 2026-09-18. Tagged Enterprise.

On the record

• Filed from the AWS official RSS on 2026-09-18.
• Primary source host: aws.amazon.com.
• Amazon SageMaker AI shipped 13 inference launches in year-to-date across two deployment paths: fully managed endpoints and Amazon SageMaker HyperPod Inference.