david/flash-attention

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

Autor	SHA1 Mensaje	Fecha
Tri Dao	7a802796e1 Big refactor and update	hace 1 mes
Son Nguyen	478ee666cc Make namespace comment consistent (#1305)	hace 3 meses
jayhshah	c92ca63268 FA3 FP8 qkv descales + restore max offset for h128 causal + added sync for producer WG (#1173)	hace 5 meses
Tri Dao	bafe253042 [FA3] Bwd	hace 6 meses
jayhshah	5018ac6ac5 Fp8 kernel with "in-kernel" transpose of V in producer (#1100)	hace 6 meses
Tri Dao	7f67966cc7 FA3 initial code release	hace 7 meses