Fix stale version note in Qwen3.8-27B recipe - #891
Merged
Merged
Conversation
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request updates the vLLM configuration and documentation for Qwen models. Specifically, it updates models/Qwen/Qwen3.8-27B.yaml to reference the official vLLM release >=0.28.0 instead of a custom build, and updates models/Qwen/Qwen3.8-Flash-Next.yaml to replace deprecated compilation flags (-cc.mode and -cc.cudagraph_mode) with the unified --compilation-config argument. There are no review comments, and I have no additional feedback to provide.
namgyu-youn
changed the title
DFlash2's dependency (vllm-project/vllm#52816, merged 2026-08-21) was described as not yet in a stable release. It shipped in v0.28.0 (2026-08-26); update the feature description and guide accordingly. Signed-off-by: namgyu-youn <namgyu.dev@gmail.com>
namgyu-youn
force-pushed
the
fix/qwen38-recipe-issues
branch
from
August 30, 2026 17:43
c2906b6 to
bda7996
Compare
Member
|
Thanks! |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Qwen3.8-27B.yaml: the DFlash2 speculative-decoding mode said its dependency (vllm-project/vllm#52816) was "not in a stable release yet." It's recently released on v0.28.0 (2026-08-26), so update to say "vLLM >=0.28.0" instead.Test plan
git show v0.28.0:tests/v1/spec_decode/test_dflash2.pyconfirms DFlash2 (PR #52816) is present in the v0.28.0 tag.