david/flash-attention

zrkadlo https://github.com/Dao-AILab/flash-attention

Autor	SHA1 Správa	Dátum
Tri Dao	c2407dec96 Fix typo in config: train.gpu -> train.gpu_mem	2 rokov pred
Tri Dao	4a6eaa9f27 Update configs, add results	2 rokov pred
Tri Dao	0bf5e50038 Release training code	2 rokov pred