pytorch-labs / tritonbench

Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
BSD 3-Clause "New" or "Revised" License
21 stars 3 forks source link

Add ufmt linter for pyproject #47

Closed xuzhao9 closed 2 weeks ago

xuzhao9 commented 2 weeks ago

Add linter to make sure PR is consistent with internal arc lint.

To format the code, run the following in the repo directory:

ufmt format .

We also test 25 operators in our H100 CI. Note that many of the flash_attention backends do not work right now and we need to fix them.

facebook-github-bot commented 2 weeks ago

@xuzhao9 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

facebook-github-bot commented 2 weeks ago

@xuzhao9 merged this pull request in pytorch-labs/tritonbench@359dfb46bd092b2f8d7854ce45c62ce595a229f2.

FindHao commented 5 days ago
pip install ufmt ruff-api

to install depednecies.