bump vllm version#2427
Merged
Jackmin801 merged 5 commits intomainfrom May 6, 2026
Merged
Conversation
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 2 potential issues.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 553b7f4. Configure here.
Signed-off-by: Jackmin801 <56836461+Jackmin801@users.noreply.github.com>
vLLM 0.20.1 ships fixes for the LoRA+MoE+DP>1 corruption (#40338) and the OffloadingConnector CPU block-count miscalculation (#39617), so remove the local monkey patches and the corresponding call site in transformers_v5_compat. Refresh stale "vLLM 0.16/0.19" comments. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
hallerite
approved these changes
May 6, 2026
samsja
added a commit
that referenced
this pull request
May 8, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Note
Medium Risk
Upgrades the core inference stack (
vllm/PyTorch and related CUDA libs) and removes/changes vLLM monkeypatches, which can subtly affect runtime behavior and performance despite limited app-code changes.Overview
Updates the inference dependency stack, bumping
vllmto>=0.20.1, addingtorchvision/torchaudiofrom the PyTorch CUDA 12.8 index, and updating theflash-attnprebuilt wheel to a Torch 2.11 build.Cleans up vLLM compatibility patches by dropping now-unneeded monkeypatches (including the CPU offloading block-count fix and a large LoRA+MoE+DP fused-kernel workaround) and updating comments to reflect the new vLLM version;
uv.lockis regenerated accordingly with the new transitive packages/versions.Reviewed by Cursor Bugbot for commit 3b5375d. Bugbot is set up for automated code reviews on this repo. Configure here.