OpenSource/ollama @ mattw/allmodelsonhuggingface

Daniel Hiltgen 9983fa5f4e Cleaup stale submodule		1 anno fa
..
ext_server	77d96da94b Code shuffle to clean up the llm dir	1 anno fa
generate	9983fa5f4e Cleaup stale submodule	1 anno fa
llama.cpp @ 328b83de23	fac9060da5 Init submodule with new path	1 anno fa
dynamic_shim.c	d966b730ac Switch windows build to fully dynamic	1 anno fa
dynamic_shim.h	9a70aecccb Refactor how we augment llama.cpp	1 anno fa
ext_server_common.go	77d96da94b Code shuffle to clean up the llm dir	1 anno fa
ext_server_default.go	0b3118e0af fix: relay request opts to loaded llm prediction (#1761)	1 anno fa
ext_server_windows.go	e9ce91e9a6 Load dynamic cpu lib on windows	1 anno fa
ggml.go	811b1f03c8 deprecate ggml	1 anno fa
gguf.go	56ffc3023a remove per-model types	1 anno fa
llama.go	0b3118e0af fix: relay request opts to loaded llm prediction (#1761)	1 anno fa
llm.go	e9ce91e9a6 Load dynamic cpu lib on windows	1 anno fa
shim_darwin.go	77d96da94b Code shuffle to clean up the llm dir	1 anno fa
shim_ext_server.go	77d96da94b Code shuffle to clean up the llm dir	1 anno fa
shim_ext_server_linux.go	77d96da94b Code shuffle to clean up the llm dir	1 anno fa
shim_ext_server_windows.go	77d96da94b Code shuffle to clean up the llm dir	1 anno fa
utils.go	fccf8d179f partial decode ggml bin for more info	1 anno fa