baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
ollama/llm
History
Daniel Hiltgen 325d74985b Fix CPU performance on hyperthreaded systems 
The default thread count logic was broken and resulted in 2x the number
of threads as it should on a hyperthreading CPU
resulting in thrashing and poor performance.
2023-12-21 16:23:36 -08:00
..
llama.cpp Fix CPU performance on hyperthreaded systems 2023-12-21 16:23:36 -08:00
dynamic_shim.c Revamp the dynamic library shim 2023-12-20 14:45:57 -08:00
dynamic_shim.h Revamp the dynamic library shim 2023-12-20 14:45:57 -08:00
ext_server.go Fix CPU performance on hyperthreaded systems 2023-12-21 16:23:36 -08:00
ggml.go deprecate ggml 2023-12-19 09:05:46 -08:00
gguf.go remove per-model types 2023-12-11 09:40:21 -08:00
llama.go Revamp the dynamic library shim 2023-12-20 14:45:57 -08:00
llm.go Revamp the dynamic library shim 2023-12-20 14:45:57 -08:00
shim_darwin.go Revamp the dynamic library shim 2023-12-20 14:45:57 -08:00
shim_ext_server.go Revamp the dynamic library shim 2023-12-20 14:45:57 -08:00
utils.go partial decode ggml bin for more info 2023-08-10 09:23:10 -07:00