Update glm-5 container to use SGLang latest#1561
Open
xinli-sw wants to merge 2 commits into
Open
Conversation
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Note
Medium Risk
Switches benchmark recipes to a nightly SGLang container build, which can change runtime behavior/performance and introduce compatibility regressions despite being config-only.
Overview
Updates the GLM-5 B200 SGLang benchmark configs (FP8/FP4, incl. MTP variants) to use
lmsysorg/sglang:nightly-dev-cu13-20260523-c112f762instead of the pinnedv0.5.12-cu130image.Adds perf changelog entries documenting the SGLang image bump for the
glm5-fp4-b200-sglangandglm5-fp4-b200-sglang-mtpconfigs.Reviewed by Cursor Bugbot for commit 8678a8d. Bugbot is set up for automated code reviews on this repo. Configure here.