Reduce inference cold starts on Amazon SageMaker HyperPod with model caching

Amazon SageMaker HyperPod now supports model caching to cut inference cold starts. The feature pre‑loads model weights and container images onto cluster nodes, letting pods read from local NVMe storage instead of downloading over the network. This reduces cold starts from tens of minutes to seconds, speeding up deployment and lowering latency for developers.

Opening Kapyn…