Steve Luo 7806842f2d add paged-attetionv2: support seq length split across thread block (#5707)

2024-05-14 12:46:54 +08:00

..

__init__.py

[Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613)

2024-04-24 14:17:54 +08:00

inference_ops_cuda.py

[Inference/Feat] Add convert_fp8 op for fp8 test in the future (#5706)

2024-05-10 18:39:54 +08:00

inference.cpp

add paged-attetionv2: support seq length split across thread block (#5707)

2024-05-14 12:46:54 +08:00