You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
ColossalAI/extensions/pybind/inference
Steve Luo 7806842f2d
add paged-attetionv2: support seq length split across thread block (#5707)
7 months ago
..
__init__.py
inference.cpp add paged-attetionv2: support seq length split across thread block (#5707) 7 months ago
inference_ops_cuda.py [Inference/Feat] Add convert_fp8 op for fp8 test in the future (#5706) 7 months ago