Domovská stránka Prehľadávať Pomoc
Registrovať Prihlásiť sa
OpenSource
/
ollama
2
0
Fork 0
Súbory Issues 0 Pull requesty 0 Wiki
Branch: mattw/quantcontext
Branche Tagy
ollama
/
llm
Daniel Hiltgen e9ce91e9a6 Load dynamic cpu lib on windows 1 rok pred
..
llama.cpp e9ce91e9a6 Load dynamic cpu lib on windows 1 rok pred
dynamic_shim.c d966b730ac Switch windows build to fully dynamic 1 rok pred
dynamic_shim.h 9a70aecccb Refactor how we augment llama.cpp 1 rok pred
ext_server_common.go 0b3118e0af fix: relay request opts to loaded llm prediction (#1761) 1 rok pred
ext_server_default.go 0b3118e0af fix: relay request opts to loaded llm prediction (#1761) 1 rok pred
ext_server_windows.go e9ce91e9a6 Load dynamic cpu lib on windows 1 rok pred
ggml.go 811b1f03c8 deprecate ggml 1 rok pred
gguf.go 56ffc3023a remove per-model types 1 rok pred
llama.go 0b3118e0af fix: relay request opts to loaded llm prediction (#1761) 1 rok pred
llm.go e9ce91e9a6 Load dynamic cpu lib on windows 1 rok pred
shim_darwin.go d966b730ac Switch windows build to fully dynamic 1 rok pred
shim_ext_server.go ddbfa6fe31 Fix CPU only builds 1 rok pred
shim_ext_server_linux.go d966b730ac Switch windows build to fully dynamic 1 rok pred
shim_ext_server_windows.go e9ce91e9a6 Load dynamic cpu lib on windows 1 rok pred
utils.go fccf8d179f partial decode ggml bin for more info 1 rok pred