NVIDIA-NeMo / NVIDIA-NeMo/RL

Flash-attention-3

Open
#2,148 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
2k
Forks
561
Avg merge
4d 5h
Merged PRs (30d)
145

Description

There are now prebuilt wheels for FA3 that should work for torch >2.9

context
* https://download.pytorch.org/whl/cu130/flash-attn-3/
* https://download.pytorch.org/whl/cu126/flash-attn-3/
* https://github.com/Dao-AILab/flash-attention/pull/2282
* https://github.com/Dao-AILab/flash-attention/pull/2223

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.