Skip to content

[BugFix/Build] Fix sparse kernels not getting built on hopper #14572

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 3 commits into from
Mar 11, 2025
Merged

[BugFix/Build] Fix sparse kernels not getting built on hopper #14572

merged 3 commits into from
Mar 11, 2025

Conversation

LucasWilkinson
Copy link
Collaborator

@LucasWilkinson LucasWilkinson commented Mar 10, 2025 •
edited by github-actions bot
Loading

#14354 caused the sparse kernels to not get built on hopper resulting in:

NotImplementedError: No compiled cutlass_sparse_compress for a compute capability less than CUDA device capability: 90

Tested using:

vllm serve nm-testing/TinyLlama-1.1B-Chat-v1.0-sparse2of4_fp8_dynamic-e2e

@LucasWilkinson
Build sparse kernels on hopper
a887eb6 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.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.

🚀

@mergify mergify bot added the ci/build label Mar 10, 2025
@LucasWilkinson
update comment
9f5f743 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
@LucasWilkinson
restrict to hopper
c1d88d9 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
dsikka
dsikka approved these changes Mar 11, 2025
View reviewed changes
Copy link
Contributor

@dsikka dsikka left a comment

Choose a reason for hiding this comment

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

Thanks!

tlrmchlsmth
tlrmchlsmth approved these changes Mar 11, 2025
View reviewed changes
Copy link
Collaborator

@tlrmchlsmth tlrmchlsmth left a comment

Choose a reason for hiding this comment

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

LGTM - let's take a look at cleaning some of this up after. I think the number of SCALED_MM_ARCH environment variables has gotten a little unwieldy

@tlrmchlsmth tlrmchlsmth added the ready ONLY add when PR is ready to merge/full CI is needed label Mar 11, 2025
@tlrmchlsmth tlrmchlsmth enabled auto-merge (squash) March 11, 2025 14:28
@LucasWilkinson
Copy link
Collaborator Author

LGTM - let's take a look at cleaning some of this up after. I think the number of SCALED_MM_ARCH environment variables has gotten a little unwieldy

Agreed, I'm hoping to make a cmake macro the combines CUDA version guards and gencode guards

@tlrmchlsmth tlrmchlsmth merged commit 07b4b7a into vllm-project:main Mar 11, 2025
70 checks passed
JC1DA pushed a commit to JC1DA/vllm that referenced this pull request Mar 11, 2025
@LucasWilkinson @JC1DA
[BugFix/Build] Fix sparse kernels not getting built on hopper (vllm-p…
f77a6cc 
…roject#14572)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
lulmer pushed a commit to lulmer/vllm that referenced this pull request Apr 7, 2025
@LucasWilkinson @lulmer
[BugFix/Build] Fix sparse kernels not getting built on hopper (vllm-p…
0f60848 
…roject#14572)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Louis Ulmer <ulmerlouis@gmail.com>
@ckhordiasma ckhordiasma mentioned this pull request Apr 17, 2025
Closed
shreyankg pushed a commit to shreyankg/vllm that referenced this pull request May 3, 2025
@LucasWilkinson @shreyankg
[BugFix/Build] Fix sparse kernels not getting built on hopper (vllm-p…
77597fc 
…roject#14572)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
RichardoMrMu pushed a commit to RichardoMrMu/vllm that referenced this pull request May 12, 2025
@LucasWilkinson
[BugFix/Build] Fix sparse kernels not getting built on hopper (vllm-p…
6582b5c 
…roject#14572)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Mu Huai <tianbowen.tbw@antgroup.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@tlrmchlsmth tlrmchlsmth tlrmchlsmth approved these changes

@dsikka dsikka dsikka approved these changes

Assignees
No one assigned
Labels
ci/build ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@LucasWilkinson @tlrmchlsmth @dsikka