Update qwen3.5-bf16-mi300x-sglang SGLang image to v0.5.11-rocm720-mi30x#1352
Update qwen3.5-bf16-mi300x-sglang SGLang image to v0.5.11-rocm720-mi30x#1352Klaud-Cold wants to merge 1 commit into
Conversation
…30x\n\nRef #1154\n\nCo-authored-by: Klaud Cold <Klaud-Cold@users.noreply.github.com>
Klaud-Cold
requested review from
billishyahao,
chunfangamd,
seungrokj and
yctseng0211
as code owners
|
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. |
1 similar comment
|
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}
| - qwen3.5-bf16-mi300x-sglang | ||
| description: | ||
| - "Update SGLang image from v0.5.10-rocm720-mi30x to v0.5.11-rocm720-mi30x" | ||
| pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX |
There was a problem hiding this comment.
🟡 The new perf-changelog entry for qwen3.5-bf16-mi300x-sglang uses the placeholder pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX instead of this PR's number. Please change XXX to 1352 so the link resolves and matches the convention used by every other entry in perf-changelog.yaml.
Extended reasoning...
What's wrong
The diff adds a new entry at the bottom of perf-changelog.yaml:
- config-keys:
- qwen3.5-bf16-mi300x-sglang
description:
- "Update SGLang image from v0.5.10-rocm720-mi30x to v0.5.11-rocm720-mi30x"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXXThe pr-link value still contains the literal XXX placeholder rather than the actual PR number. Per the PR metadata, this is PR #1352, so the link should be https://github.com/SemiAnalysisAI/InferenceX/pull/1352.
Why this is a bug, not stylistic
AGENTS.md (lines 300 / 323) documents pull/XXX as the template placeholder that authors must fill in when adding a changelog entry. Every other entry in the file uses a concrete PR number — the four entries immediately preceding this one reference /pull/1304, /1305, /1308, and /1310 (around lines 2325, 2332, 2338, 2345). The invariant the file maintains is: each changelog entry's pr-link points at the PR that introduced the corresponding config change, so the changelog is traceable back to its source review.
Step-by-step proof
- Open the PR in GitHub: this PR is numbered 1352 (see PR metadata title "Update qwen3.5-bf16-mi300x-sglang SGLang image to v0.5.11-rocm720-mi30x", PR Update qwen3.5-bf16-mi300x-sglang SGLang image to v0.5.11-rocm720-mi30x #1352).
- Open
perf-changelog.yamlat line 2351 — the new entry'spr-linkreadshttps://github.com/SemiAnalysisAI/InferenceX/pull/XXX. - Visit that URL in a browser — GitHub returns a 404, since
/pull/XXXis not a valid PR identifier. - Compare with the immediately preceding entries: e.g. line 2345 reads
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1310, which resolves to the actual PR that introduced that entry. The XXX entry breaks this invariant.
Impact
Purely a metadata/docs issue — no runtime, benchmark, or config behavior is affected. The only consequence is that the changelog entry for this image bump is not traceable to its originating PR (404 link).
Fix
Replace XXX with 1352 on line 2351:
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1352
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=25763481215 |
1 similar comment
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=25763481215 |
1 participant
Summary
qwen3.5-bf16-mi300x-sglangimage fromlmsysorg/sglang:v0.5.10-rocm720-mi30xtolmsysorg/sglang:v0.5.11-rocm720-mi30xRef #1154
Generated with Claude Code