Skip to content

[Main2Main] Upgrade vllm commit to 0112 #5691

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Closed
zhangxinyuehfad wants to merge 1 commit into from
Closed

[Main2Main] Upgrade vllm commit to 0112 #5691

zhangxinyuehfad wants to merge 1 commit into from

Conversation

@zhangxinyuehfad
Copy link
Contributor

@zhangxinyuehfad zhangxinyuehfad commented Jan 7, 2026 •
edited
Loading

What this PR does / why we need it?

Upgrade vllm commit to 0112 (d7b2e57097dae8a620c28eddf663adad2a8329c5)

  1. remove init_cached_hf_modules due to [Chore] Try remove init_cached_hf_modules vllm#31786
  2. skip spec_decode e2e test due to [Perf] Async Scheduling + Speculative Decoding + Structured Outputs vllm#29821 break

Does this PR introduce any user-facing change?

How was this patch tested?

gemini-code-assist[bot]
gemini-code-assist bot reviewed Jan 7, 2026
View reviewed changes
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request updates the vLLM commit dependency and adapts the codebase for the removal of init_cached_hf_modules in newer vLLM versions. The changes introduce a version check to maintain backward compatibility.

My review focuses on making this compatibility check more robust. I've suggested replacing the version-specific check with a feature detection approach (hasattr), which is a more resilient and maintainable pattern for handling optional functionalities across different library versions. I've also pointed out that the corresponding unit test should be made hermetic by mocking the version check, to ensure it's independent of the installed vLLM version.

@github-actions github-actions bot added documentation Improvements or additions to documentation ci/build module:tests labels Jan 7, 2026
@github-actions
Copy link

github-actions bot commented Jan 7, 2026

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

  • A PR should do only one thing, smaller PRs enable faster reviews.
  • Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
  • Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

@vllm-ascend-ci vllm-ascend-ci added ready read for review ready-for-test start test by label for PR labels Jan 7, 2026
@zhangxinyuehfad zhangxinyuehfad force-pushed the main0107 branch 2 times, most recently from 5224123 to c046d9e Compare January 7, 2026 15:42
@wjunLu
Copy link
Collaborator

wjunLu commented Jan 8, 2026

Another 4-cards break is due to: vllm-project/vllm#31773

@github-actions
Copy link

github-actions bot commented Jan 9, 2026

This pull request has conflicts, please resolve those before we can evaluate the pull request.

@zhangxinyuehfad zhangxinyuehfad force-pushed the main0107 branch 2 times, most recently from 754b76d to 5f05e08 Compare January 11, 2026 16:26
@zhangxinyuehfad zhangxinyuehfad changed the title [Main2Main] Upgrade vllm commit to 0107 [Main2Main] Upgrade vllm commit to 0111 Jan 12, 2026
wjunLu
wjunLu reviewed Jan 12, 2026
View reviewed changes
.github/workflows/_e2e_test.yaml Outdated
# TODO: add ignore after the issue is fixed
pytest -sv --durations=0 tests/e2e/singlecard/spec_decode/test_mtp_eagle_correctness.py
pytest -sv --durations=0 tests/e2e/singlecard/spec_decode/test_v1_spec_decode.py
pytest -sv --durations=0 tests/e2e/singlecard/spec_decode/test_v1_spec_decode.py \
Copy link
Collaborator

@wjunLu wjunLu Jan 12, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please delete all skip cases, the break points are gone now

wjunLu
wjunLu reviewed Jan 12, 2026
View reviewed changes
vllm_ascend/distributed/kvpool/ascend_store_connector.py
from vllm.attention.backends.abstract import \
AttentionMetadata # type: ignore
else:
from vllm.v1.attention.backend import AttentionMetadata # type: ignore
Copy link
Collaborator

@wjunLu wjunLu Jan 12, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please recheck all changes about this

@zhangxinyuehfad zhangxinyuehfad changed the title [Main2Main] Upgrade vllm commit to 0111 [Main2Main] Upgrade vllm commit to 0112 Jan 12, 2026
@zhangxinyuehfad
[Main2Main] Upgrade vllm commit to 0112
125d51b 
Signed-off-by: wjunLu <[email protected]>
Signed-off-by: hfadzxy <[email protected]>
@zhangxinyuehfad
Copy link
Contributor Author

zhangxinyuehfad commented Jan 15, 2026

main2main upgrade to 0113, The pr not need

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

2 more reviewers

@wjunLu wjunLu wjunLu left review comments

@gemini-code-assist gemini-code-assist[bot] gemini-code-assist[bot] left review comments

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

ci/build documentation Improvements or additions to documentation module:tests ready read for review ready-for-test start test by label for PR

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@zhangxinyuehfad @wjunLu @vllm-ascend-ci