Tri Dao 78b7a1dc18 [OPT] Load fp16 weights on CPU before moving to GPU		2023-01-22 17:01:32 -08:00
..
losses	Tweak CrossEntropyLoss to take process_group in init	2022-12-27 10:47:43 -08:00
models	[OPT] Load fp16 weights on CPU before moving to GPU	2023-01-22 17:01:32 -08:00
modules	[FusedDense] Support relu, rename FusedDenseGeluDense -> FusedMLP	2023-01-17 18:12:27 -08:00
ops	[FusedDense] Support relu, rename FusedDenseGeluDense -> FusedMLP	2023-01-17 18:12:27 -08:00
test_flash_attn.py	Skip flash_attn_split test	2022-11-13 12:27:48 -08:00
test_rotary.py	Add MLP, MHA, Block, Embedding modules	2022-11-13 22:06:44 -08:00