Update glm5-fp4-b300-sglang and -mtp SGLang image to v0.5.12-cu130#1420
Update glm5-fp4-b300-sglang and -mtp SGLang image to v0.5.12-cu130#1420Klaud-Cold wants to merge 2 commits into
Conversation
… to v0.5.12-cu130 Ref #1154 Co-authored-by: Klaud Cold <Klaud-Cold@users.noreply.github.com>
|
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 single node 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 PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. If re-running failed jobs is attempted, PR authors are responsible for ensuring it passes. See GitHub's docs on re-running failed jobs: https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow As a rule of thumb, generally, PR authors should request a review & get a PR approval from the respective companies' CODEOWNERS before requesting a review from core maintainers. If additional help is needed, PR authors can reach out to core maintainers over Slack. |
There was a problem hiding this comment.
The image version bump itself looks correct, but the new perf-changelog.yaml entry has pr-link: XXX as a placeholder — this should be replaced with the actual PR URL before merging (cf. the prior entry which uses a real /pull/1402 link).
Extended reasoning...
Overview
The PR updates the SGLang container image from v0.5.11-cu130 to v0.5.12-cu130 for two configs (glm5-fp4-b300-sglang and glm5-fp4-b300-sglang-mtp) in .github/configs/nvidia-master.yaml, and adds a corresponding entry to perf-changelog.yaml. The image version change itself is a mechanical, low-risk bump.
Security risks
None. This is a container image tag change for a recipe configuration; it does not modify auth, crypto, permissions, or any code paths.
Level of scrutiny
Low — this is a near-trivial config tweak following an established pattern across the recent commit history (e.g., #1402, #1409, #1408 are similar version bumps). Normally I would shadow-approve this without hesitation.
Other factors
The blocker is the literal pr-link: XXX placeholder in the changelog entry. Every other recent entry in perf-changelog.yaml uses a real https://github.com/SemiAnalysisAI/InferenceX/pull/NNNN URL, so this is clearly an unfilled template value rather than an intentional convention. It's a tiny fix but worth a human glance to ensure the changelog stays clean before merge.
# Conflicts: # perf-changelog.yaml
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=25980016281 |
Updates SGLang image for
glm5-fp4-b300-sglangandglm5-fp4-b300-sglang-mtpfrom v0.5.11-cu130 to v0.5.12-cu130.\nRef #1154
Generated with Claude Code