david/flash-attention

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

نویسنده	SHA1 پیام	تاریخ
jayhshah	a5a75274bc FA3 kvcache + split kv + gqa parallelization (#1236)	4 ماه پیش
Ying Zhang	dfe1a59e4b Add var-seq-len to FA3 fp16 / bf16 fwd (#1072)	7 ماه پیش
Tri Dao	7f67966cc7 FA3 initial code release	7 ماه پیش