LuGY 6a3f9fda83 [cuda] modify the fused adam, support hybrid of fp16 and fp32 (#497)

2022-03-25 14:15:53 +08:00

..

cuda_native

[cuda] modify the fused adam, support hybrid of fp16 and fp32 (#497)

2022-03-25 14:15:53 +08:00

jit

adapted for sequence parallel (#163)

2022-01-20 13:44:51 +08:00

__init__.py

refactor kernel (#142)

2022-01-13 16:47:17 +08:00