Skip to content
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

[Feature Request] Grouped GEMM kernel #679

Open
LiyuanLucasLiu opened this issue Feb 24, 2024 · 1 comment
Open

[Feature Request] Grouped GEMM kernel #679

LiyuanLucasLiu opened this issue Feb 24, 2024 · 1 comment
Labels
enhancement New feature or request

Comments

@LiyuanLucasLiu
Copy link

LiyuanLucasLiu commented Feb 24, 2024 •
edited
Loading

Thanks for the awesome library! I'm wondering whether there are plans to provide ops support for grouped_gemm as in https://github.com/tgale96/grouped_gemm/tree/main

As of more information, it seems that fp8 is supported in cutlass grouped_gemm.

https://github.com/NVIDIA/cutlass/blob/main/examples/57_hopper_grouped_gemm/57_hopper_grouped_gemm.cu#L94
@ptrendx ptrendx added the enhancement New feature or request label May 16, 2024
@yaox12
Copy link
Collaborator

yaox12 commented Sep 5, 2024

A GroupedLinear layer has been added in TE v1.9, and it has FP8 support.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@yaox12 @ptrendx @LiyuanLucasLiu