Bump mlx-lm/mlx-vlm deps and add Qwen3.5-0.8B smoke test #174
Merged
LxYuan0420 merged 1 commit intovllm-project:mainfrom Mar 19, 2026
Merged
Bump mlx-lm/mlx-vlm deps and add Qwen3.5-0.8B smoke test #174LxYuan0420 merged 1 commit intovllm-project:mainfrom
LxYuan0420 merged 1 commit intovllm-project:mainfrom
Conversation
Collaborator
Signed-off-by: Chao-Ju Chen <ricky.chen@infinirc.com>
ricky-chaoju
force-pushed
the
deps/bump-mlx-deps
branch
from
f4dc461 to
fdef8d3
Compare
Contributor
Author
|
done! Thanks @LxYuan0420 |
LxYuan0420
approved these changes
Mar 18, 2026
Contributor
Author
|
@LxYuan0420 Please check #176 first before merging this one. Thanks! |
Collaborator
|
@ricky-chaoju Thanks! This PR will give us groundtruth labels and unblock the flash-linear-attn for the paged path! |
31 tasks
This was referenced Mar 19, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Follow-up to #169 (transformers>=5.0.0 upgrade).
mlx>=0.31.0,mlx-lm>=0.31.0,mlx-vlm>=0.4.0tests/test_qwen35_smoke.py: golden token comparison for Qwen/Qwen3.5-0.8B (greedy decoding, 5/5 passed)Qwen3.5 uses the
qwen3_5architecture which requires transformers>=5.0.0 and mlx-lm>=0.30.0. This proves the upgraded dependency stack works end-to-end on Metal.Test
test_qwen35_smoke
test_paged_deterministic