david/flash-attention

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

Autor	SHA1 Mensaxe	Data
Ying Zhang	1c9717d699 address comments	hai 2 meses
Ying Zhang	be6c1b98c4 small fixes	hai 2 meses
Ying Zhang	dff976a84a fixes	hai 3 meses
Ying Zhang	7b4e68e04f hopper local attention	hai 3 meses
Tri Dao	3f6ff1c1c5 Remove struct : cute::aligned_struct to avoid error with gcc 12	hai 4 meses
Tri Dao	bafe253042 [FA3] Bwd	hai 4 meses
Tri Dao	7f67966cc7 FA3 initial code release	hai 5 meses