AWS adds managed extensions on HyperPod Slurm clusters

AWS said on Nov. 20 that SageMaker HyperPod can install and update managed software on running Slurm nodes through an API or the console, in every region where HyperPod is offered. sagemaker-observability sends node, GPU, Elastic Fabric Adapter, Slurm job, and Slurm cluster metrics to CloudWatch or Managed Service for Prometheus, and sagemaker-user-management sets matching users and groups, SSH and sudo rules, Slurm accounting, and optional Active Directory. AWS says there is no additional charge for the extensions, while CloudWatch, Managed Prometheus, and Secrets Manager are billed separately, and a cluster needs the Nov. 2, 2026 HyperPod AMI or later with continuous provisioning. The developer guide also lists optional NCCL metrics and describes the observability collection as network metrics.

/ Sources

/ About this story

Compiled by Venture Atlas from the sources above, using automated AI-assisted research. This is a summary of reporting published elsewhere, not original reporting - follow the source links for the full account. See our editorial standards.

Something wrong here? Email apostructura@gmail.com and we will fix it.

/ Related