david/flash-attention

réplica de https://github.com/Dao-AILab/flash-attention

Autor	SHA1 Mensaxe	Data
Tri Dao	0e8c46ae08 Run isort and black on test files	hai 1 ano
Tri Dao	a81900d4c1 [ViT] Minor fix so it runs	hai 1 ano
Tri Dao	88173a1aaf [FusedDense] Support relu, rename FusedDenseGeluDense -> FusedMLP	%!s(int64=2) %!d(string=hai) anos
Tri Dao	780e8eeabb [ViT] Support timm checkpoint, add tests	%!s(int64=2) %!d(string=hai) anos