Skip to content

[WIP] MLA decode attention - cuda graph support #12588

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
wants to merge 12 commits into from
Closed

[WIP] MLA decode attention - cuda graph support #12588

wants to merge 12 commits into from

Conversation

alexm-redhat
Copy link
Collaborator

Adds cuda graph support to Lucas' PR that implements triton MLA attention kernel: #12528

LucasWilkinson and others added 11 commits January 30, 2025 03:18
@LucasWilkinson @WoosukKwon @simon-mo
squashed commits
ec8c1cf 
Co-authored-by: Woosuk Kwon <[email protected]>
Co-authored-by: simon-mo <[email protected]>
Signed-off-by: Lucas Wilkinson <[email protected]>
@LucasWilkinson
fix VLLM_MLA_PERFORM_MATRIX_ABSORPTION=0
f23d126 
Signed-off-by: Lucas Wilkinson <[email protected]>
@LucasWilkinson
more cleanups
3895bba 
Signed-off-by: Lucas Wilkinson <[email protected]>
@LucasWilkinson @mgoin
Update utils.py
4880a43 
Co-authored-by: Michael Goin <[email protected]>
@LucasWilkinson @mgoin
Update vllm/attention/backends/mla/utils.py
aa19f29 
Co-authored-by: Michael Goin <[email protected]>
@LucasWilkinson
review comments
534cd00 
Signed-off-by: Lucas Wilkinson <[email protected]>
@LucasWilkinson
renaming for consistency
2326814 
Signed-off-by: Lucas Wilkinson <[email protected]>
@LucasWilkinson @zhuohan123
Update vllm/config.py
2b140de 
Co-authored-by: Zhuohan Li <[email protected]>
@LucasWilkinson
review comments
7241acb 
Signed-off-by: Lucas Wilkinson <[email protected]>
@LucasWilkinson
review comments
135c404 
Signed-off-by: Lucas Wilkinson <[email protected]>
@alexm-redhat
add cuda graph support to triton_mla attention
984ffdd
@github-actions GitHub Actions
Copy link

👋 Hi! Thank you for contributing to the vLLM project.
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 do one of these:

  • Add ready label to the PR
  • Enable auto-merge.

🚀

@alexm-redhat alexm-redhat marked this pull request as draft January 30, 2025 21:18
@mergify mergify bot added the tpu Related to Google TPUs label Mar 27, 2025
@mergify Mergify
Copy link

mergify bot commented Mar 27, 2025

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @alexm-redhat.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

@mergify mergify bot added the needs-rebase label Mar 27, 2025
@mergify mergify bot added the rocm Related to AMD ROCm label Jun 13, 2025
@mergify mergify bot added the deepseek Related to DeepSeek models label Jul 2, 2025
@hmellor
Copy link
Member

hmellor commented Oct 3, 2025

Closing as stale

@hmellor hmellor closed this Oct 3, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@tlrmchlsmth tlrmchlsmth Awaiting requested review from tlrmchlsmth tlrmchlsmth is a code owner

@WoosukKwon WoosukKwon Awaiting requested review from WoosukKwon WoosukKwon is a code owner

@zhuohan123 zhuohan123 Awaiting requested review from zhuohan123 zhuohan123 is a code owner

@youkaichao youkaichao Awaiting requested review from youkaichao youkaichao is a code owner

@comaniac comaniac Awaiting requested review from comaniac comaniac is a code owner

@njhill njhill Awaiting requested review from njhill njhill is a code owner

@robertgshaw2-redhat robertgshaw2-redhat Awaiting requested review from robertgshaw2-redhat

@NickLucche NickLucche Awaiting requested review from NickLucche NickLucche will be requested when the pull request is marked ready for review NickLucche is a code owner

@jikunshang jikunshang Awaiting requested review from jikunshang jikunshang will be requested when the pull request is marked ready for review jikunshang is a code owner

@bigPYJ1151 bigPYJ1151 Awaiting requested review from bigPYJ1151 bigPYJ1151 will be requested when the pull request is marked ready for review bigPYJ1151 is a code owner

@mgoin mgoin Awaiting requested review from mgoin mgoin will be requested when the pull request is marked ready for review mgoin is a code owner

@yewentao256 yewentao256 Awaiting requested review from yewentao256 yewentao256 will be requested when the pull request is marked ready for review yewentao256 is a code owner

@22quinn 22quinn Awaiting requested review from 22quinn 22quinn will be requested when the pull request is marked ready for review 22quinn is a code owner

@LucasWilkinson LucasWilkinson Awaiting requested review from LucasWilkinson LucasWilkinson will be requested when the pull request is marked ready for review LucasWilkinson is a code owner

Assignees

No one assigned

Labels

deepseek Related to DeepSeek models needs-rebase rocm Related to AMD ROCm tpu Related to Google TPUs

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@alexm-redhat @hmellor @LucasWilkinson