david/flash-attention

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

Auteur	SHA1 Message	Date
Tri Dao	2c996ca25f Use SeqlenInfo for bwd and epilogue	il y a 1 semaine
Tri Dao	82dc825759 Don't use the unsafe convert_type function	il y a 2 semaines
Tri Dao	e7b93e3902 Clean up mha_combine kernel	il y a 3 semaines
Tri Dao	3d0d147940 Early stop on actual num_splits in mha_combine kernel	il y a 3 semaines
Tri Dao	9fd6b977bb Precompute the pointers in mha_combine kernel	il y a 3 semaines
Tri Dao	01de45b8f8 Add combine kernel	il y a 1 mois