Skip to content

[TPU][V1] Remove ragged attention kernel parameter hard coding #16041

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 4, 2025
Merged

[TPU][V1] Remove ragged attention kernel parameter hard coding #16041

merged 1 commit into from
Apr 4, 2025

Conversation

yaochengji
Copy link
Collaborator

No description provided.

@github-actions GitHub Actions
Copy link

github-actions bot commented Apr 4, 2025

👋 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.

🚀

@mergify mergify bot added v1 tpu Related to Google TPUs labels Apr 4, 2025
@yaochengji yaochengji added the ready ONLY add when PR is ready to merge/full CI is needed label Apr 4, 2025
mgoin
mgoin approved these changes Apr 4, 2025
View reviewed changes
Copy link
Member

@mgoin mgoin left a comment

Choose a reason for hiding this comment

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

LGTM

@mgoin mgoin merged commit fadc59c into vllm-project:main Apr 4, 2025
58 checks passed
@mgoin
Copy link
Member

mgoin commented Apr 4, 2025

I was too hasty, it looks like the V1 test softfailed due to non-implemented function https://buildkite.com/vllm/ci/builds/16901/steps?jid=0195fe57-e92c-4847-ac45-c4c41dd05d23
Investigating since I think it isn't related to this PR

@vanbasten23
Copy link
Collaborator

I was too hasty, it looks like the V1 test softfailed due to non-implemented function https://buildkite.com/vllm/ci/builds/16901/steps?jid=0195fe57-e92c-4847-ac45-c4c41dd05d23 Investigating since I think it isn't related to this PR

Yeah, I don't think the ci failure is related to this PR. It's likely that tpu_worker hasn't account for SlidingWindowSpec hence the NotImplementedError which I'm taking a look now. cc @yaochengji

@vanbasten23 vanbasten23 mentioned this pull request Apr 4, 2025
Merged
@vanbasten23
Copy link
Collaborator

The fix is here #16070

@mgoin
Copy link
Member

mgoin commented Apr 4, 2025

I already posted a fix here #16059

Alex4210987 pushed a commit to LeiWang1999/vllm-bitblas that referenced this pull request Apr 5, 2025
@yaochengji @Alex4210987
[TPU][V1] Remove ragged attention kernel parameter hard coding (vllm-…
84df1af 
…project#16041)

Signed-off-by: Chengji Yao <[email protected]>
Signed-off-by: xinyuxiao <[email protected]>
lulmer pushed a commit to lulmer/vllm that referenced this pull request Apr 7, 2025
@yaochengji @lulmer
[TPU][V1] Remove ragged attention kernel parameter hard coding (vllm-…
80b338a 
…project#16041)

Signed-off-by: Chengji Yao <[email protected]>
Signed-off-by: Louis Ulmer <[email protected]>
@ckhordiasma ckhordiasma mentioned this pull request Apr 17, 2025
Closed
lk-chen pushed a commit to lk-chen/vllm that referenced this pull request Apr 29, 2025
@yaochengji @lk-chen
[TPU][V1] Remove ragged attention kernel parameter hard coding (vllm-…
d50795b 
…project#16041)

Signed-off-by: Chengji Yao <[email protected]>
shreyankg pushed a commit to shreyankg/vllm that referenced this pull request May 3, 2025
@yaochengji @shreyankg
[TPU][V1] Remove ragged attention kernel parameter hard coding (vllm-…
2d5c256 
…project#16041)

Signed-off-by: Chengji Yao <[email protected]>
RichardoMrMu pushed a commit to RichardoMrMu/vllm that referenced this pull request May 12, 2025
@yaochengji
[TPU][V1] Remove ragged attention kernel parameter hard coding (vllm-…
bb52ede 
…project#16041)

Signed-off-by: Chengji Yao <[email protected]>
Signed-off-by: Mu Huai <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@mgoin mgoin mgoin approved these changes

@vanbasten23 vanbasten23 Awaiting requested review from vanbasten23

@alexm-redhat alexm-redhat Awaiting requested review from alexm-redhat

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

Assignees

No one assigned

Labels

ready ONLY add when PR is ready to merge/full CI is needed tpu Related to Google TPUs v1

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@yaochengji @mgoin @vanbasten23