Skip to content

Revert "[NVIDIA] Update NVIDIA GPT-OSS vLLM image from v0.15.1 to v0.16.0"#903

Merged
cquil11 merged 1 commit intomainfrom
revert-800-claude/issue-798-20260226-0534
Mar 10, 2026
Merged

Revert "[NVIDIA] Update NVIDIA GPT-OSS vLLM image from v0.15.1 to v0.16.0"#903
cquil11 merged 1 commit intomainfrom
revert-800-claude/issue-798-20260226-0534

Conversation

@cquil11
Copy link
Collaborator

@cquil11 cquil11 commented Mar 10, 2026

Reverts #800

@github-actions
Copy link
Contributor

Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook

If it is not, please create a PR first before we can merge your PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you

2 similar comments
@github-actions
Copy link
Contributor

Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook

If it is not, please create a PR first before we can merge your PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you

@github-actions
Copy link
Contributor

Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook

If it is not, please create a PR first before we can merge your PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you

@cquil11 cquil11 merged commit cad1169 into main Mar 10, 2026
6 checks passed
@cquil11 cquil11 deleted the revert-800-claude/issue-798-20260226-0534 branch March 10, 2026 16:48
cquil11 added a commit that referenced this pull request Mar 10, 2026
…1 to v0.16.0 (#800)" (#903) [skip-sweep]"

This reverts commit cad1169.
Copy link
Contributor

@claude claude bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM — straightforward revert of image version bump, config-only change.

Extended reasoning...

Overview

This PR reverts PR #800, which had updated the NVIDIA GPT-OSS vLLM image from v0.15.1 to v0.16.0-cu130. The changes are limited to two files: .github/configs/nvidia-master.yaml (3 image tag reverts across gptoss-fp4-b200-vllm, gptoss-fp4-h100-vllm, and gptoss-fp4-h200-vllm) and perf-changelog.yaml (removal of the corresponding changelog entry).

Security risks

None. This is a config-only change that reverts Docker image tags to a previously-used version. No code, authentication, permissions, or data handling is affected.

Level of scrutiny

Minimal scrutiny needed. This is a mechanical revert of a version bump in benchmark configuration files. The git history confirms this pattern — the revert commit d54901c is already on master, indicating this change has already been validated.

Other factors

No bugs were found by the automated bug hunting system. The PR timeline contains only automated bot comments with no outstanding reviewer feedback. The change is small, self-contained, and follows the established pattern of image version management in this repository.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

Development

Successfully merging this pull request may close these issues.

1 participant