fix: prevent vllm_omni from breaking Qwen3 vLLM inference#79
Merged
Conversation
kaiitunnz
requested changes
Jun 19, 2026
Signed-off-by: Zhengyuan Su <su.zhengyuan@u.nus.edu>
Signed-off-by: Zhengyuan Su <su.zhengyuan@u.nus.edu>
timzsu
force-pushed
the
zsu/fix-inference-bug
branch
from
f7e9694 to
c321535
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Purpose
When vLLM Omni 0.22.0 is installed, vLLM 0.22.0 fails to initialize an engine for models using Model Runner V2 (e.g., Qwen3-8B). This PR implements a workaround. Note that I have also fixed the root cause upstream (vllm-project/vllm-omni#4568), so we can revert the patch after we bump the versions next time.
Changes
src/worker/executors/__init__.py: Import vLLM Omni lazily so the plugin is not registered when we are not using the Omni executor.src/worker/executors/vllm_executor.py: Removes the Omni plugin from vLLM if we are usingVLLMExecutor.examples/templates/inference_vllm_qwen3.yaml: A sample workflow to surface the problem.Test Plan
End-to-end execution of
examples/templates/inference_vllm_qwen3.yaml.Test Result
The workflow completes successfully.
Pre-submission Checklist
pre-commit run --all-filesand fixed any issues.uv run pytest tests/passes locally.uv sync --all-packages --group ci --frozen).[BREAKING]and described migration steps above.