Skip to content

Conversation

@wangxiyuan
Copy link
Collaborator

@wangxiyuan wangxiyuan commented Aug 4, 2025

What's the PR does:

  1. Move AscendSparseMoeBlock to qwen3 model, since it's only used by qwen3 model.
  2. Disable AscendSparseMoeBlock if aclgraph is enabled, AscendSparseMoeBlock doesn't work with aclgraph currently.

@github-actions
Copy link

github-actions bot commented Aug 4, 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.

@Yikun Yikun added accuracy-test enable all accuracy test for PR ready-for-test start test by label for PR labels Aug 4, 2025
@wangxiyuan
Copy link
Collaborator Author

depends on #2181

@wangxiyuan wangxiyuan changed the title [Revert] Revert qwen3 moe model change [BugFix] Fix the bug that qwen3 moe doesn't work with EP Aug 4, 2025
@wangxiyuan wangxiyuan force-pushed the revert_qwen3 branch 3 times, most recently from f9935fc to 41a9872 Compare August 5, 2025 00:44
@wangxiyuan wangxiyuan changed the title [BugFix] Fix the bug that qwen3 moe doesn't work with EP [BugFix] Fix the bug that qwen3 moe doesn't work with aclgraph Aug 5, 2025
@codecov
Copy link

codecov bot commented Aug 5, 2025

Codecov Report

❌ Patch coverage is 30.30303% with 23 lines in your changes missing coverage. Please review.
✅ Project coverage is 76.34%. Comparing base (807f089) to head (03b4565).
⚠️ Report is 3 commits behind head on main.

Files with missing lines Patch % Lines
vllm_ascend/models/qwen3_moe.py 30.30% 23 Missing ⚠️
Additional details and impacted files
@@           Coverage Diff           @@
##             main    #2183   +/-   ##
=======================================
  Coverage   76.34%   76.34%           
=======================================
  Files         110      110           
  Lines       12473    12474    +1     
=======================================
+ Hits         9522     9523    +1     
  Misses       2951     2951           
Flag Coverage Δ
unittests 76.34% <30.30%> (+<0.01%) ⬆️

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.

@wangxiyuan wangxiyuan requested a review from weijinqian0 August 5, 2025 03:08
@Yikun Yikun added ready-for-test start test by label for PR and removed ready-for-test start test by label for PR labels Aug 5, 2025
@wangxiyuan wangxiyuan added ready-for-test start test by label for PR and removed ready-for-test start test by label for PR labels Aug 5, 2025
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
@wangxiyuan wangxiyuan merged commit 458ab2d into vllm-project:main Aug 5, 2025
25 checks passed
zzhx1 pushed a commit to lidenghui1110/vllm-ascend that referenced this pull request Aug 11, 2025
…project#2183)

What's the PR does:
1. Move AscendSparseMoeBlock to qwen3 model, since it's only used by
qwen3 model.
2. Disable AscendSparseMoeBlock if aclgraph is enabled,
AscendSparseMoeBlock doesn't work with aclgraph currently.

- vLLM version: v0.10.0
- vLLM main:
vllm-project/vllm@cdfd687

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
zzhx1 pushed a commit to lidenghui1110/vllm-ascend that referenced this pull request Aug 11, 2025
…project#2183)

What's the PR does:
1. Move AscendSparseMoeBlock to qwen3 model, since it's only used by
qwen3 model.
2. Disable AscendSparseMoeBlock if aclgraph is enabled,
AscendSparseMoeBlock doesn't work with aclgraph currently.

- vLLM version: v0.10.0
- vLLM main:
vllm-project/vllm@cdfd687

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
@wangxiyuan wangxiyuan deleted the revert_qwen3 branch September 4, 2025 06:52
chopper0126 pushed a commit to chopper0126/vllm-ascend that referenced this pull request Sep 26, 2025
…project#2183)

What's the PR does:
1. Move AscendSparseMoeBlock to qwen3 model, since it's only used by
qwen3 model.
2. Disable AscendSparseMoeBlock if aclgraph is enabled,
AscendSparseMoeBlock doesn't work with aclgraph currently.

- vLLM version: v0.10.0
- vLLM main:
vllm-project/vllm@cdfd687

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Angazenn pushed a commit to Angazenn/vllm-ascend that referenced this pull request Oct 21, 2025
…project#2183)

What's the PR does:
1. Move AscendSparseMoeBlock to qwen3 model, since it's only used by
qwen3 model.
2. Disable AscendSparseMoeBlock if aclgraph is enabled,
AscendSparseMoeBlock doesn't work with aclgraph currently.

- vLLM version: v0.10.0
- vLLM main:
vllm-project/vllm@cdfd687

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

accuracy-test enable all accuracy test for PR module:ops module:tests ready-for-test start test by label for PR

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants