david/flash-attention

mirrorاز https://github.com/Dao-AILab/flash-attention

نویسنده	SHA1 پیام	تاریخ
Tri Dao	0e8c46ae08 Run isort and black on test files	1 سال پیش
Tri Dao	88173a1aaf [FusedDense] Support relu, rename FusedDenseGeluDense -> FusedMLP	1 سال پیش
Tri Dao	93383bd55b [TP] Implement TensorParallel without sequence parallel	2 سال پیش
Tri Dao	226a1b721d Implement TensorParallel for FusedDense and FusedDenseGeluDense	2 سال پیش