Open
Conversation
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
shepardxia
requested review from
ClementeP,
benlebrun,
samuki and
vicky-xef
and removed request for
benlebrun
samuki
reviewed
Feb 10, 2026
ClementeP
reviewed
Feb 11, 2026
pyproject.toml
Outdated
| "vllm>=0.6.6,<=0.10.0; sys_platform == 'linux'", | ||
| "triton>=3.2.0; sys_platform == 'linux'", | ||
| ] | ||
| sgl = [ |
There was a problem hiding this comment.
is there no version requirement for SGL ?
Contributor
Author
There was a problem hiding this comment.
The latest versions are fine, but I didn't test for a lower bound. Could add version requirement later when SGLang has a breaking change.
Member
There was a problem hiding this comment.
This actually breaks with the latest version of SGLang, since the call signature of Scheduler now requires dp_rank and moe_dp_rank. I pinned the version to >=0.5.8,<0.5.9 for now.
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR adds the SGLang as one of the inference backend options.