david/flash-attention

-ын хуулбар https://github.com/Dao-AILab/flash-attention

Эзэн	SHA1 Мессеж	Огноо
Jay Shah	0a1a0c22b6 refactor for split kv	3 сар өмнө
Ying Zhang	dff976a84a fixes	3 сар өмнө
jayhshah	5018ac6ac5 Fp8 kernel with "in-kernel" transpose of V in producer (#1100)	4 сар өмнө
Tri Dao	74b0761ff7 [FA3] BF16 forward	5 сар өмнө
Tri Dao	7f67966cc7 FA3 initial code release	5 сар өмнө