Skip to content

Conversation

MengqingCao
Copy link
Collaborator

@MengqingCao MengqingCao commented Aug 14, 2025

What this PR does / why we need it?

  1. update CachedRequestState as NewRequestData changed in [Core] Use individual MM items in P0/P1 cache and model runner vllm#22570
  2. drop maintenance of vllm v0.10.0 in the branch main

Does this PR introduce any user-facing change?

N/A

How was this patch tested?

CI passed with existing test.

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 CachedRequestState to rename the mm_inputs attribute to mm_kwargs, aligning with changes in NewRequestData. The change is applied to the class definition and its instantiation. However, the review identified that not all usages of this attribute were updated in vllm_ascend/worker/model_runner_v1.py, which will lead to runtime errors. A critical comment has been added to address this incomplete refactoring.

Copy link

👋 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.

Signed-off-by: MengqingCao <[email protected]>
Copy link

codecov bot commented Aug 14, 2025

Codecov Report

❌ Patch coverage is 94.73684% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 76.18%. Comparing base (0f7492d) to head (971ca90).
⚠️ Report is 7 commits behind head on main.

Files with missing lines Patch % Lines
vllm_ascend/multistream/ms_split.py 0.00% 1 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             main    #2367      +/-   ##
==========================================
+ Coverage   75.74%   76.18%   +0.44%     
==========================================
  Files         118      120       +2     
  Lines       13525    13532       +7     
==========================================
+ Hits        10245    10310      +65     
+ Misses       3280     3222      -58     
Flag Coverage Δ
unittests 76.18% <94.73%> (+0.44%) ⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Signed-off-by: MengqingCao <[email protected]>
from vllm_ascend.utils import vllm_version_is

# Import specific patches for different versions
if vllm_version_is("0.10.0"):
Copy link
Collaborator

Choose a reason for hiding this comment

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

this can be left. while we can add it back later.

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

this can be left. while we can add it back later.

ok, will add it back in next pr then

@wangxiyuan wangxiyuan merged commit 61866b8 into vllm-project:main Aug 14, 2025
22 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants