[WIP][NV] update glm5 fp8 b200 sglang container#1030
Open
hshrivastava-droid wants to merge 4 commits intomainfrom
Open
[WIP][NV] update glm5 fp8 b200 sglang container#1030hshrivastava-droid wants to merge 4 commits intomainfrom
hshrivastava-droid wants to merge 4 commits intomainfrom
Conversation
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 |
Contributor
There was a problem hiding this comment.
This PR is marked [WIP] and the changelog pr-link still has a placeholder — please update those before this is ready to merge.
Extended reasoning...
Overview\nThis PR updates the SGLang container image for the glm5-fp8-b200-sglang config from a nightly build (nightly-dev-cu13-20260317-1eea7448) to the stable release v0.5.10.post1, and adds a matching entry to perf-changelog.yaml.\n\n### Security risks\nNo security concerns — this is a Docker image tag bump with no logic changes.\n\n### Level of scrutiny\nThe change itself is trivial and mechanical, following the same image-update pattern seen throughout the repo. The main reason for deferring is the explicit [WIP] label in the PR title, which signals the author considers it incomplete. The pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX placeholder in the changelog also needs to be updated to the actual PR number before merging.\n\n### Other factors\nNo bugs were found by the automated system. Once the [WIP] label is removed and the changelog pr-link is updated, this could be auto-approved.
Collaborator
Author
|
@claude - generate PR description |
Collaborator
|
Claude finished @hshrivastava-droid's task in 37s —— View job Generating PR Description
PR description has been updated with:
|
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
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.
Summary
glm5-fp8-b200-sglangfrom nightly build (nightly-dev-cu13-20260317-1eea7448) to stable releasev0.5.10.post1-cu130perf-changelog.yamlDetails
Config:
glm5-fp8-b200-sglangModel:
zai-org/GLM-5-FP8on B200 (TP=8, single-node)Image change:
lmsysorg/sglang:nightly-dev-cu13-20260317-1eea7448→lmsysorg/sglang:v0.5.10.post1-cu130Moving from a nightly dev build to the stable v0.5.10.post1 release for improved reliability and reproducibility.
Test plan
glm5-fp8-b200-sglangto validate performance on the new image