david/flash-attention

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

Autor	SHA1 Mensaje	Fecha
Tri Dao	76f14c61c9 Tune fwd tile sizes for Sm86 and Sm89	hace 3 semanas
Tri Dao	51484a7b56 Make backward epilogue work for Sm80	hace 3 semanas
Tri Dao	659a631f4c Rename bwd classes to include Sm90 suffix	hace 3 semanas
Tri Dao	a901c7eeda Make Sm80 forward pass work with persistent scheduler	hace 4 semanas
Tri Dao	5171269dab Implement forward pass for Sm80	hace 1 mes