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

[Docs] Clarify OpenFold speedup

Browse Source
This commit is contained in:
Tri Dao 2022-11-25 10:49:17 -08:00
parent d9021ae4ec
commit b784ed73cf
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
usage.md
View File

@ -89,7 +89,8 @@ yields the fastest BERT training on cloud instances in MLPerf training 2.0 (June
memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2. With
FlashAttention as one of its
[components](https://twitter.com/gahdritz/status/1595420944880779266), it is
up to 3x faster than AlphaFold2, and can predict 2x longer structures.
up to 3x faster than AlphaFold2 to run inference on short sequences, and can
predict 2x longer structures.
## Different implementations