Skip to content

[NV] update glm5-fp4-b200 sglang image#1031

Merged
hshrivastava-droid merged 3 commits intomainfrom
nv/glm5-fp4-b200-sglang-v2
Apr 16, 2026
Merged

[NV] update glm5-fp4-b200 sglang image#1031
hshrivastava-droid merged 3 commits intomainfrom
nv/glm5-fp4-b200-sglang-v2

Conversation

@hshrivastava-droid
Copy link
Copy Markdown
Collaborator

@hshrivastava-droid hshrivastava-droid commented Apr 15, 2026

Summary

Update the SGLang image for glm5-fp4-b200-sglang (B200) from the nightly dev build to the stable release.

Image change:

  • Before: lmsysorg/sglang:nightly-dev-cu13-20260328-a27651d5
  • After: lmsysorg/sglang:v0.5.10.post1-cu130

Changes

  • .github/configs/nvidia-master.yaml — Update glm5-fp4-b200-sglang image tag to v0.5.10.post1-cu130
  • perf-changelog.yaml — Add changelog entry for the image update

@github-actions
Copy link
Copy Markdown
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

Comment thread perf-changelog.yaml
- glm5-fp4-b200-sglang
description:
- "Update SGLang image from nightly-dev-cu13-20260328-a27651d5 to v0.5.10.post1-cu130"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1031
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

🟡 The new perf-changelog.yaml entry uses a placeholder pr-link of pull/XXX instead of the actual PR number 1031. Update line 1356 to pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1031 before merging.

Extended reasoning...

What the bug is: The new changelog entry for glm5-fp4-b200-sglang added at the bottom of perf-changelog.yaml uses the placeholder string pull/XXX in its pr-link field rather than the actual PR number.

The specific code path: Line 1356 of perf-changelog.yaml reads:

  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX

The PR being reviewed is clearly PR #1031 (visible in the PR metadata), so the correct value is https://github.com/SemiAnalysisAI/InferenceX/pull/1031.

Why existing practices don't prevent it: The file already contains several other entries with pull/XXX (e.g., glm5-fp8-mi355x-sglang, minimaxm2.5-fp8-h200-vllm, qwen3.5-bf16-mi325x-sglang, qwen3.5-fp8-mi325x-sglang), indicating this placeholder pattern has slipped through in prior merges. However, those past failures to update the link do not make it acceptable to repeat the mistake in a new entry, especially when the correct PR number is definitively known.

Addressing the refutation: The refutation argues this is an accepted practice because other XXX entries exist and the PR is marked [WIP]. Neither argument holds: the presence of prior mistakes doesn't make them correct, and [WIP] status means the author should update the PR number before requesting final merge, not that the placeholder is intentionally permanent. The refutation also conflates this with bug_002—but this is an independently reportable, actionable issue on a new entry introduced by this PR.

Impact: Purely documentation/metadata. The pr-link field is informational only; no CI or runtime behavior is affected. However, a broken/placeholder link makes the changelog less useful for traceability.

How to fix: Replace line 1356 with:

  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1031

Step-by-step proof:

  1. PR [NV] update glm5-fp4-b200 sglang image #1031 is titled "[NV] update sglang image" and modifies perf-changelog.yaml.
  2. The diff shows a new entry appended with pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX.
  3. The PR number is 1031 by definition (it is the PR under review).
  4. Therefore the correct link is pull/1031, not pull/XXX.

faradawn added a commit to faradawn/sgl-cookbook that referenced this pull request Apr 15, 2026
Audit against glm5_fp4_b200.sh benchmark script (SemiAnalysisAI/InferenceX#1031):
--ep 1 was used in benchmark but missing from recipe; --enable-dp-lm-head
was in recipe but absent from the validated benchmark configuration.

Signed-off-by: Faradawn Yang <73060648+faradawn@users.noreply.github.com>
@hshrivastava-droid hshrivastava-droid changed the title [WIP][NV] update sglang image [WIP][NV] update glm5-fp4-b200 sglang image Apr 15, 2026
Copy link
Copy Markdown
Contributor

@functionstackx functionstackx left a comment

Choose a reason for hiding this comment

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

lgtm

Copy link
Copy Markdown
Collaborator

@jgangani jgangani left a comment

Choose a reason for hiding this comment

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

Looks good.

@kedarpotdar-nv
Copy link
Copy Markdown
Collaborator

@claude add a pr description

@hshrivastava-droid hshrivastava-droid changed the title [WIP][NV] update glm5-fp4-b200 sglang image [NV] update glm5-fp4-b200 sglang image Apr 16, 2026
@Klaud-Cold
Copy link
Copy Markdown
Collaborator

Klaud-Cold commented Apr 16, 2026

Claude finished @kedarpotdar-nv's task in 27s —— View job


Adding PR Description

  • Analyze PR changes
  • Update PR description

Done — added a PR description summarizing the SGLang image update for glm5-fp4-b200-sglang from the nightly dev build to v0.5.10.post1-cu130.

@hshrivastava-droid hshrivastava-droid merged commit 4c6038c into main Apr 16, 2026
32 checks passed
@hshrivastava-droid hshrivastava-droid deleted the nv/glm5-fp4-b200-sglang-v2 branch April 16, 2026 21:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

Development

Successfully merging this pull request may close these issues.

5 participants