squall/flash-attention
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README for FA3

Browse Source
This commit is contained in:
Tri Dao 2024-11-12 20:01:07 -08:00
parent 241c682c9f
commit 7435839e3d
1 changed files with 3 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@ -40,15 +40,12 @@ This is a beta release for testing / benchmarking before we integrate that with
the rest of the repo.
Currently released:
- FP16 forward and backward
Coming soon in the next couple of days / next week:
- BF16
- Variable length (FP16, BF16)
- FP8 forward.
- FP16 / BF16 forward and backward, FP8 forward
Requirements: H100 / H800 GPU, CUDA >= 12.3.
For now, we highly recommend CUDA 12.3 for best performance.
To install:
```sh
cd hopper