david/flash-attention

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

نویسنده	SHA1 پیام	تاریخ
Tri Dao	42fc4962f0 Uncomment tanh softcapping	2 هفته پیش
Tri Dao	82dc825759 Don't use the unsafe convert_type function	2 هفته پیش
Tri Dao	9553b2728f More env vars to disable features	2 هفته پیش
Tri Dao	3248babb9e QOL: Use env var to selectively disable features	2 هفته پیش
Tri Dao	fc2fd95a18 Renable FP8 kernels	3 هفته پیش
Tri Dao	6e8b25e426 Refactor	2 ماه پیش
Ying Zhang	dfe1a59e4b Add var-seq-len to FA3 fp16 / bf16 fwd (#1072)	4 ماه پیش
Tri Dao	7f67966cc7 FA3 initial code release	5 ماه پیش