OpenSource/ollama @ jmorganca/initcmake

jmorganca 858a9bac59 windows: init `cmakeTargets` in `init_vars`		пре 1 година
..
ext_server	7c9792a6e0 Support unicode characters in model path (#3681)	пре 1 година
generate	858a9bac59 windows: init `cmakeTargets` in `init_vars`	пре 1 година
llama.cpp @ 46e12c4692	2ed0d65948 Bump llama.cpp to b2737	пре 1 година
patches	85801317d1 Fix clip log import	пре 1 година
ggla.go	8b2c10061c refactor tensor query	пре 1 година
ggml.go	435cc866a3 fix: mixtral graph	пре 1 година
gguf.go	14476d48cc fixes for gguf (#3863)	пре 1 година
llm.go	9502e5661f cgo quantize	пре 1 година
llm_darwin_amd64.go	58d95cc9bd Switch back to subprocessing for llama.cpp	пре 1 година
llm_darwin_arm64.go	58d95cc9bd Switch back to subprocessing for llama.cpp	пре 1 година
llm_linux.go	58d95cc9bd Switch back to subprocessing for llama.cpp	пре 1 година
llm_windows.go	058f6cd2cc Move nested payloads to installer and zip file on windows	пре 1 година
memory.go	7bb7cb8a60 only count output tensors	пре 1 година
payload.go	058f6cd2cc Move nested payloads to installer and zip file on windows	пре 1 година
server.go	bb31def011 return code `499` when user cancels request while a model is loading (#3955)	пре 1 година
status.go	58d95cc9bd Switch back to subprocessing for llama.cpp	пре 1 година