Skip to content

Add tuned triton fused_moe configs for Qwen3Moe #17328

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
Merged
merged 1 commit into from
Apr 28, 2025
Merged

Add tuned triton fused_moe configs for Qwen3Moe #17328

merged 1 commit into from
Apr 28, 2025

Conversation

mgoin
Copy link
Member

@mgoin mgoin commented Apr 28, 2025 •
edited by github-actions bot
Loading

Also adds support for creating new Qwen3Moe in benchmarks/kernels/benchmark_moe.py i.e. python benchmarks/kernels/benchmark_moe.py --model Qwen/Qwen3-30B-A3B -tp 1 --tune

Thanks to authors @JustinTong0323, @yhyang201, @whybeyoung, @GeLee-Q, and @yizhang2077 for originally producing these configs in SGL!
PRs: sgl-project/sglang#5833 sgl-project/sglang#5839 sgl-project/sglang#5846 sgl-project/sglang#5850 sgl-project/sglang#5849

@mgoin
Add tuned triton fused_moe configs for Qwen3Moe
02e04c3 
Signed-off-by: mgoin <mgoin64@gmail.com>
@github-actions GitHub Actions
Copy link

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

@simon-mo simon-mo merged commit 8fc88d6 into vllm-project:main Apr 28, 2025
9 of 12 checks passed
simon-mo pushed a commit that referenced this pull request Apr 28, 2025
@mgoin @simon-mo
[Model] Add tuned triton fused_moe configs for Qwen3Moe (#17328)
ba41cc9 
Signed-off-by: mgoin <mgoin64@gmail.com>
@zhaochenyang20
Copy link

Thanks for your acknowledgement

jikunshang pushed a commit to jikunshang/vllm that referenced this pull request Apr 29, 2025
@mgoin @dbyoung18
[Model] Add tuned triton fused_moe configs for Qwen3Moe (vllm-project…
43a6001 
…#17328)

Signed-off-by: mgoin <mgoin64@gmail.com>
@255doesnotexist 255doesnotexist mentioned this pull request Apr 29, 2025
Open
tjtanaavllm pushed a commit to ROCm/vllm that referenced this pull request Apr 29, 2025
@mgoin @tjtanaavllm
[Model] Add tuned triton fused_moe configs for Qwen3Moe (vllm-project…
24de861 
…#17328)

Signed-off-by: mgoin <mgoin64@gmail.com>
lk-chen pushed a commit to lk-chen/vllm that referenced this pull request Apr 29, 2025
@mgoin @lk-chen
[Model] Add tuned triton fused_moe configs for Qwen3Moe (vllm-project…
54f7bab 
…#17328)

Signed-off-by: mgoin <mgoin64@gmail.com>
RichardoMrMu pushed a commit to RichardoMrMu/vllm that referenced this pull request May 12, 2025
@mgoin
[Model] Add tuned triton fused_moe configs for Qwen3Moe (vllm-project…
1a7c02d 
…#17328)

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Mu Huai <tianbowen.tbw@antgroup.com>
dtrifiro pushed a commit to red-hat-data-services/vllm that referenced this pull request May 13, 2025
@andy-neuma
Sync midstream to upstream v0.8.5.post1 (opendatahub-io#218)
7db80a0 
Syncing midstream NM fork to Upstream tag of
[v0.8.5.post1](https://github.com/vllm-project/vllm/tree/v0.8.5.post1) +
cherry pick of
vllm-project@be633fb
needed for benchmarks +
[CP](neuralmagic/nm-vllm-ent@1fe447d)
for compressed tensor bump +
[CP](vllm-project#17677) for lora on AMD +
[CP](vllm-project#17315) for llama4 w/ pure
dense layers

```
commit 31c73ba (HEAD -> upstream-v0.8.5, nm-fork/upstream-v0.8.5)
Author: Chauncey <chaunceyjiang@gmail.com>
Date:   Wed Apr 30 15:11:04 2025 +0800

    [Bugfix] Fix AttributeError: 'State' object has no attribute 'engine_client' (vllm-project#17434)
    
    Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>

commit f8db0bd
Author: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Date:   Fri May 2 14:01:38 2025 -0400

    [BugFix][Attention] Fix sliding window attention in V1 giving incorrect results (vllm-project#17574)
    
    Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>

commit e335c34
Author: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Date:   Fri May 2 04:07:03 2025 -0400

    [BugFix] Fix Memory Leak (vllm-project#17567)
    
    Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>

commit cc463fe
Merge: 1e358ff ba41cc9
Author: Selbi Nuryyeva <selbi@redhat.com>
Date:   Tue Apr 29 12:34:57 2025 -0400

    Merge branch 'tag-upstream-v0.8.5' into upstream-v0.8.5

commit ba41cc9 (tag: v0.8.5, tag-upstream-v0.8.5)
Author: Michael Goin <mgoin64@gmail.com>
Date:   Mon Apr 28 16:20:24 2025 -0600

    [Model] Add tuned triton fused_moe configs for Qwen3Moe (vllm-project#17328)
    
    Signed-off-by: mgoin <mgoin64@gmail.com>

commit dcbac4c
Author: Simon Mo <simon.mo@hey.com>
Date:   Mon Apr 28 14:12:01 2025 -0700

    [Model] Qwen3 Dense FP8 Compat Fixes (vllm-project#17318)
    
    Signed-off-by: simon-mo <xmo@berkeley.edu>
[...]
```

Commands
```
git fetch upstream
git checkout -b upstream-v0.8.5
git merge upstream/v0.8.5
git cherry-pick be633fb
```

TEST PLAN
accept sync:
https://github.com/neuralmagic/nm-cicd/actions/runs/14841223552
related PR in cicd: neuralmagic/nm-cicd#99
release workflow:
https://github.com/neuralmagic/nm-cicd/actions/runs/14845693864
@ckhordiasma ckhordiasma mentioned this pull request May 14, 2025
Merged
zzzyq pushed a commit to zzzyq/vllm that referenced this pull request May 24, 2025
@mgoin
[Model] Add tuned triton fused_moe configs for Qwen3Moe (vllm-project…
36b401e 
…#17328)

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Yuqi Zhang <yuqizhang@google.com>
minpeter pushed a commit to minpeter/vllm that referenced this pull request Jun 24, 2025
@mgoin @minpeter
[Model] Add tuned triton fused_moe configs for Qwen3Moe (vllm-project…
e49db9e 
…#17328)

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: minpeter <kali2005611@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@simon-mo simon-mo simon-mo approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@mgoin @zhaochenyang20 @simon-mo