Update dsr1-fp8-mi355x-sglang SGLang image to v0.5.12-rocm700-mi35x#1432
Update dsr1-fp8-mi355x-sglang SGLang image to v0.5.12-rocm700-mi35x#1432Klaud-Cold wants to merge 1 commit into
Conversation
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. |
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. |
| - dsr1-fp8-mi355x-sglang | ||
| description: | ||
| - "Update SGLang image from v0.5.9-rocm700-mi35x to v0.5.12-rocm700-mi35x" | ||
| pr-link: XXX |
There was a problem hiding this comment.
🔴 The new perf-changelog.yaml entry for dsr1-fp8-mi355x-sglang contains the literal placeholder pr-link: XXX instead of a real URL. Every other entry in the file uses a real GitHub PR URL — please replace it with https://github.com/SemiAnalysisAI/InferenceX/pull/1432 to match the convention and avoid a broken link in the published changelog.
Extended reasoning...
What the bug is
At perf-changelog.yaml:2556, the new entry added by this PR ends with:
- config-keys:
- dsr1-fp8-mi355x-sglang
description:
- "Update SGLang image from v0.5.9-rocm700-mi35x to v0.5.12-rocm700-mi35x"
pr-link: XXXThe string XXX is clearly an unfilled template placeholder — it is not a valid URL and does not resolve to anything.
Why it doesn't match convention
Every other recent entry in perf-changelog.yaml uses a fully-qualified GitHub PR URL of the form https://github.com/SemiAnalysisAI/InferenceX/pull/<num>. The immediately preceding entry (line 2550) is:
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1402and the entries above it (lines 2526, 2532, 2538, 2544) follow the same pattern. The XXX is the only deviation in the file.
Why it slipped through
The PR description references #1154 (the umbrella tracking issue for this kind of rolling image bump) rather than the PR's own number. When the changelog entry was generated, the template's pr-link placeholder was never substituted with this PR's own number (#1432). There is no schema validation in this file that would catch XXX as a malformed URL, so it merges silently.
Impact
Once merged, the changelog — which is user-facing — will contain a broken/non-resolving link for this entry. Anyone clicking through to find context on the SGLang image bump from v0.5.9 to v0.5.12 will hit a dead string. It doesn't affect the perf sweep itself, but it does affect changelog usability.
Step-by-step proof
- Open
perf-changelog.yamlafter this PR merges. - Scroll to line 2556 (the bottom-most entry, for
dsr1-fp8-mi355x-sglang). - Observe
pr-link: XXX. - Any consumer (web renderer, doc generator, or human reader) that follows
pr-linkwill try to resolveXXX— which is not a URL and does not point to PR Update dsr1-fp8-mi355x-sglang SGLang image to v0.5.12-rocm700-mi35x #1432 where the change actually originated.
Fix
Replace line 2556 with:
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1432Trivial one-line change, matches the convention used by every other entry in the file.
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=25980026855 |
Updates SGLang image for
dsr1-fp8-mi355x-sglangfrom v0.5.9-rocm700-mi35x to v0.5.12-rocm700-mi35x.\nRef #1154
Generated with Claude Code