Document expert parallelism flag differences in Claude configs#864
Merged
functionstackx merged 1 commit intomainfrom Mar 5, 2026
Merged
Document expert parallelism flag differences in Claude configs#864functionstackx merged 1 commit intomainfrom
functionstackx merged 1 commit intomainfrom
Conversation
Document the differences between vLLM's --enable-expert-parallel (boolean flag) and SGLang's --expert-parallel-size N (explicit integer) in both claude.yml and claude-pr-review.yml. Scripts should conditionally enable --enable-expert-parallel based on the EP_SIZE env var rather than hardcoding it. Co-authored-by: functionstackx <functionstackx@users.noreply.github.com>
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
--enable-expert-parallel(boolean flag) and SGLang's--expert-parallel-size N(explicit integer) in bothclaude.ymlandclaude-pr-review.yml--enable-expert-parallelbased onEP_SIZEenv var, not hardcode it--enable-expert-parallelin PR reviewsContext
vLLM serve does not accept
--expert-parallel-sizedirectly — it uses the boolean--enable-expert-parallelflag and determines EP size automatically. Scripts should use the conditionalEP_SIZEcheck pattern rather than always enabling expert parallelism.Referenced from PR #757 review discussion.
Generated with Claude Code