david/flash-attention

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

Auteur	SHA1 Message	Date
Tri Dao	71befc19e1 [Loss] Use flash_attn.losses.cross_entropy.CrossEntropyLoss	il y a 1 an
Tri Dao	dff68c2b22 Add smoothing for CrossEntropyParallel, rename to CrossEntropyLoss	il y a 2 ans
Tri Dao	0bf5e50038 Release training code	il y a 2 ans