Tri Dao d95ee1a95d Speed up compilation by splitting into separate .cu files		2022-11-25 16:30:18 -08:00
..
flash_attn	Speed up compilation by splitting into separate .cu files	2022-11-25 16:30:18 -08:00
fused_dense_lib	Mention that some CUDA extensions have only been tested on A100s	2022-11-15 07:10:25 -08:00
fused_softmax	Add Megatron attention implementation for benchmarking	2022-10-23 23:04:16 -07:00
layer_norm	[LayerNorm] Compile for both sm70 and sm80	2022-11-17 11:45:11 -08:00
rotary	Implement rotary embedding in CUDA	2022-11-04 22:42:01 -07:00
xentropy	Mention that some CUDA extensions have only been tested on A100s	2022-11-15 07:10:25 -08:00