Skip to content

Conversation

@xuzhao9
Copy link
Contributor

@xuzhao9 xuzhao9 commented Nov 18, 2025

Summary:
Add triton tags to meta internal kernels meta-cuda-kernels.yaml.

  • Handle wrapper torch._library.capture_triton() with best effort
  • Correctly handle "self.*" function calls
  • Correctly handle module searching when the callee is not found in the module. (grouped_gemm)

Differential Revision: D86682742

@meta-codesync
Copy link

meta-codesync bot commented Nov 18, 2025

@xuzhao9 has exported this pull request. If you are a Meta employee, you can view the originating Diff in D86682742.

Summary:

Add triton tags to meta internal kernels `meta-cuda-kernels.yaml`.


* Handle wrapper `torch._library.capture_triton()` with best effort
* Correctly handle "self.*" function calls
* Correctly handle module searching when the callee is not found in the module. (grouped_gemm)

Differential Revision: D86682742
facebook-github-bot pushed a commit that referenced this pull request Nov 19, 2025
Summary:

Add triton tags to meta internal kernels `meta-cuda-kernels.yaml`.


* Handle wrapper `torch._library.capture_triton()` with best effort
* Correctly handle "self.*" function calls
* Correctly handle module searching when the callee is not found in the module. (grouped_gemm)

Differential Revision: D86682742
@xuzhao9 xuzhao9 requested a review from adamomainz November 19, 2025 00:48
@meta-codesync meta-codesync bot merged commit f28882e into main Nov 19, 2025
7 of 10 checks passed
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