chenht2022 c1cc7d2cd2 1) Linear and MLP operators support qlen>1; 2) All operators now share a single memory buffer; 3) Refactor CPUInfer submit/sync logic.		2024-08-08 09:04:36 +00:00
..
__init__.py	Initial commit	2024-07-27 16:06:58 +08:00
attention.py	Initial commit	2024-07-27 16:06:58 +08:00
base_operator.py	Initial commit	2024-07-27 16:06:58 +08:00
experts.py	1) Linear and MLP operators support qlen>1; 2) All operators now share a single memory buffer; 3) Refactor CPUInfer submit/sync logic.	2024-08-08 09:04:36 +00:00
layer_wise_prefill.py	Initial commit	2024-07-27 16:06:58 +08:00
linear.py	Initial commit	2024-07-27 16:06:58 +08:00
RoPE.py	Initial commit	2024-07-27 16:06:58 +08:00