kvcache-ai-ktransformers/ktransformers
2024-08-08 09:04:36 +00:00
..
configs Initial commit 2024-07-27 16:06:58 +08:00
ktransformers_ext 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
models Initial commit 2024-07-27 16:06:58 +08:00
operators 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
optimize Initial commit 2024-07-27 16:06:58 +08:00
server Initial commit 2024-07-27 16:06:58 +08:00
tests Initial commit 2024-07-27 16:06:58 +08:00
util Initial commit 2024-07-27 16:06:58 +08:00
website Initial commit 2024-07-27 16:06:58 +08:00
__init__.py [feature] support python 310 and multi instruction 2024-07-31 13:58:17 +00:00
local_chat.py Initial commit 2024-07-27 16:06:58 +08:00