Skip to content

Conversation

realliujiaxu
Copy link
Contributor

@realliujiaxu realliujiaxu commented Aug 8, 2025

What this PR does / why we need it?

When the FusedMoEState is set to AllGatherEP, there are two bugs:

  1. DP>1 is not supported, communication for DP is missing.
  2. After switching to CANN version 8.2.RC1, the behavior of npu_moe_init_routing_v2 was modified, causing the returned value expanded_x_idx to become random. This may lead to out-of-bounds errors when executing sorted_topk_weight= torch.index_select(topk_weights.view(-1), 0, expanded_x_idx).

Does this PR introduce any user-facing change?

No

How was this patch tested?

Copy link

github-actions bot commented Aug 8, 2025

👋 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.

Copy link

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

Signed-off-by: realliujiaxu <[email protected]>
@realliujiaxu
Copy link
Contributor Author

@ApsarasX @zzzzwwjj please review

Copy link

codecov bot commented Aug 26, 2025

Codecov Report

❌ Patch coverage is 20.00000% with 4 lines in your changes missing coverage. Please review.
✅ Project coverage is 77.98%. Comparing base (1de16ea) to head (48b1b2e).
⚠️ Report is 36 commits behind head on main.

Files with missing lines Patch % Lines
vllm_ascend/quantization/w8a8_dynamic.py 0.00% 3 Missing ⚠️
vllm_ascend/ops/fused_moe.py 50.00% 1 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             main    #2288      +/-   ##
==========================================
+ Coverage   77.37%   77.98%   +0.60%     
==========================================
  Files         128      134       +6     
  Lines       16455    18500    +2045     
==========================================
+ Hits        12732    14427    +1695     
- Misses       3723     4073     +350     
Flag Coverage Δ
unittests 77.98% <20.00%> (+0.60%) ⬆️

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

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

Signed-off-by: realliujiaxu <[email protected]>
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