Update glm5-fp4-b200-sglang SGLang image to v0.5.11-cu130#1327
Update glm5-fp4-b200-sglang SGLang image to v0.5.11-cu130#1327Klaud-Cold wants to merge 1 commit into
Conversation
…\n\nCo-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. |
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
| - glm5-fp4-b200-sglang | ||
| description: | ||
| - "Update SGLang image from v0.5.10.post1-cu130 to v0.5.11-cu130" | ||
| pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX |
There was a problem hiding this comment.
🔴 The pr-link on line 2351 contains pull/XXX placeholder instead of the actual PR number. This should be replaced with 1327 before merging, otherwise the changelog will publish a broken link (https://github.com/SemiAnalysisAI/InferenceX/pull/XXX returns 404).
Extended reasoning...
What the bug is
Line 2351 of perf-changelog.yaml reads:
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXXThe XXX is a placeholder that was never substituted with the actual PR number. The PR is #1327, so the link should be https://github.com/SemiAnalysisAI/InferenceX/pull/1327.
Why this is the convention
The workflow file .github/workflows/claude.yml documents the intent: XXX is used as a placeholder until the PR is created, after which it should be replaced. A scan of perf-changelog.yaml shows ~268 existing pr-link entries, all using real numeric PR IDs (e.g., 1304, 1305, 1308, 1310 in the directly adjacent entries on lines 2325, 2332, 2338, 2345). This one entry is the sole outlier.
Impact
If merged as-is, the changelog — which is a user-facing artifact — will contain a link that resolves to a 404 page on GitHub, breaking the traceability between the changelog entry and the PR that produced the change. This defeats the purpose of including pr-link at all for this entry.
How to fix
Replace XXX with 1327 on line 2351:
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1327Step-by-step proof
- PR metadata identifies this PR as Update glm5-fp4-b200-sglang SGLang image to v0.5.11-cu130 #1327.
- The diff adds a new entry to
perf-changelog.yamlat lines 2347-2351 forglm5-fp4-b200-sglang. - Line 2351 of that entry is
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX. - The string
XXXis not a valid PR number; GitHub will resolve this URL to a 404. - Every other entry in this file uses a numeric PR ID, confirming this is a missed substitution rather than an intentional placeholder convention.
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=25763417948 |
1 similar comment
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=25763417948 |
1 participant
Summary
glm5-fp4-b200-sglangimage fromlmsysorg/sglang:v0.5.10.post1-cu130tolmsysorg/sglang:v0.5.11-cu130Ref #1154
Generated with Claude Code