david/flash-attention

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

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