david/flash-attention

spegling av https://github.com/Dao-AILab/flash-attention

Upphovsman	SHA1 Meddelande	Datum
Chirag Jain	50896ec574 Make nvcc threads configurable via environment variable (#885)	9 månader sedan
Tri Dao	dc08ea1c33 Support H100 for other CUDA extensions	1 år sedan
Tri Dao	ca81f32e04 Implement rotary embedding in CUDA	2 år sedan