Skip to content

Conversation

henrylhtsang
Copy link
Contributor

@henrylhtsang henrylhtsang commented Apr 15, 2025

@pytorch-bot
Copy link

pytorch-bot bot commented Apr 15, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/151279

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit 04ef69e with merge base 101c4f4 (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

henrylhtsang added a commit that referenced this pull request Apr 15, 2025
reserved

Differential Revision: [D73005770](https://our.internmc.facebook.com/intern/diff/D73005770/)

ghstack-source-id: 278088325
Pull Request resolved: #151279
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D73005770

@henrylhtsang henrylhtsang added the topic: not user facing topic category label Apr 15, 2025
@henrylhtsang henrylhtsang changed the title [cutlass backend] Ban FP32 output dtype from using CUTLASS GEMM backend [cutlass backend][ez] Ban FP32 output dtype from using CUTLASS GEMM backend Apr 15, 2025
@pytorch-bot pytorch-bot bot added the ciflow/trunk Trigger trunk jobs on your pull request label Apr 15, 2025
Copy link
Contributor

@ColinPeppler ColinPeppler left a comment

Choose a reason for hiding this comment

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

I'm not sure banning FP32 is the right move here.

FP32 is supported by CUTLASS. My guess is the TF32 compilation issue is the result of some improper static typing.

@henrylhtsang
Copy link
Contributor Author

I'm not sure banning FP32 is the right move here.

FP32 is supported by CUTLASS. My guess is the TF32 compilation issue is the result of some improper static typing.

I think its okay to ban for now. It is not a feature that has a lot of attention imo.

Copy link
Contributor

@ColinPeppler ColinPeppler left a comment

Choose a reason for hiding this comment

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

ok stamp to unblock, maybe add a test expecting fp32 to not be picked up by cutlass.

@ColinPeppler
Copy link
Contributor

or some logging, debug msg

…LASS GEMM backend"


FP32 not supported: #145952

Differential Revision: [D73005770](https://our.internmc.facebook.com/intern/diff/D73005770/)

cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx ipiszy chenyang78 kadeng muchulee8 amjames chauhang aakhundov

[ghstack-poisoned]
henrylhtsang added a commit that referenced this pull request Apr 15, 2025
Pull Request resolved: #151279

reserved
ghstack-source-id: 278287822
@exported-using-ghexport

Differential Revision: [D73005770](https://our.internmc.facebook.com/intern/diff/D73005770/)
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D73005770

@henrylhtsang
Copy link
Contributor Author

@pytorchbot merge

@pytorchmergebot
Copy link
Collaborator

Merge failed

Reason: This PR has internal changes and must be landed via Phabricator! Please try reimporting/rexporting the PR!

Details for Dev Infra team Raised by workflow job

@henrylhtsang
Copy link
Contributor Author

@pytorchbot merge -i

@pytorchmergebot
Copy link
Collaborator

Merge started

Your change will be merged while ignoring the following 1 checks: Meta Internal-Only Changes Check

Learn more about merging in the wiki.

Questions? Feedback? Please reach out to the PyTorch DevX Team

Advanced Debugging
Check the merge workflow status
here

timocafe pushed a commit to timocafe/pytorch that referenced this pull request Apr 16, 2025
amathewc pushed a commit to amathewc/pytorch that referenced this pull request Apr 17, 2025
@github-actions github-actions bot deleted the gh/henrylhtsang/54/head branch May 25, 2025 02:21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants