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]: Is there a Flash-Decoding algorithm implemented based on Composable kernel? #45

Open

zhangxiao-stack opened this issue Feb 28, 2024 · 3 comments

Labels

zhangxiao-stack commented Feb 28, 2024

Suggestion Description

Is there a Flash-Decoding algorithm implemented based on Composable kernel?

Operating System

No response

GPU

No response

ROCm Component

composable kernel

fxmarty commented Feb 29, 2024

+1 cc @howiejayz @sabreshao, this would be useful for us in https://github.com/huggingface/text-generation-inference

Collaborator

sabreshao commented Mar 1, 2024

@fxmarty @zhangxiao-stack This effort is planned in March. Stay tuned.

sabreshao added the function label

jcao-ai commented Apr 22, 2024

@sabreshao Hi, is this feature ready ?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment