Runyu Lu cefaeb5fdd [feat] cuda graph support and refactor non-functional api

2024-03-08 14:19:35 +08:00

..

layers

[Inference]Fused the gate and up proj in mlp，and optimized the autograd process. (#5365)

2024-02-06 19:38:25 +08:00

models

[feat] cuda graph support and refactor non-functional api

2024-03-08 14:19:35 +08:00

policy

Optimized the execution interval time between cuda kernels caused by view and memcopy (#5390)

2024-02-21 13:23:57 +08:00

__init__.py

[doc] updated inference readme (#5343)

2024-02-02 14:31:10 +08:00