IntelLabs / IntelLabs/Xe-Forge

The optimized FlashAttention kernels

Open
#34 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
21
Forks
8
PR merge metrics
No merged PRs in 30d

Description

Hi, the README/paper report strong FlashAttention forward results on Intel Arc Pro B70, but I only found `examples/attention/1_FlashAttention_Fwd.py` and the YAML benchmark spec.

Are the optimized FlashAttention kernels used for the reported results checked into this repo? I’d like to use them for testing. Thanks!

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.