aws / aws-k8s-tester

AWS Kubernetes tester, kubetest2 deployer implementation
Apache License 2.0
163 stars 82 forks source link

Update aws-efa-nccl-tests docker file to the latest cuda and nccl version #446

Closed weicongw closed 4 months ago

weicongw commented 4 months ago

Issue #, if available:

Description of changes: Update aws-efa-nccl-tests docker file to the latest cuda and nccl version. Tested with EKS cluster.

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.

cartermckinnon commented 4 months ago

@weicongw can you add a block to the PR checks for this, so we can make sure it builds after this (and any future) changes?

example:

https://github.com/aws/aws-k8s-tester/blob/053bf51856c53e5dbeb09c3e8bd898731a3df637/.github/workflows/ci.yaml#L14-L18