OpenSource/ollama @ cuda-search

Jeffrey Morgan 34344d801c clean up cmake `build` directory when cross compiling macOS builds		1 年之前
..
ext_server	dbdd50b283 add `-DCMAKE_SYSTEM_NAME=Darwin` cmake flag (#1832)	1 年之前
generate	34344d801c clean up cmake `build` directory when cross compiling macOS builds	1 年之前
llama.cpp @ 328b83de23	fac9060da5 Init submodule with new path	1 年之前
dynamic_shim.c	d966b730ac Switch windows build to fully dynamic	1 年之前
dynamic_shim.h	9a70aecccb Refactor how we augment llama.cpp	1 年之前
ext_server_common.go	08f1e18965 Offload layers to GPU based on new model size estimates (#1850)	1 年之前
ext_server_default.go	08f1e18965 Offload layers to GPU based on new model size estimates (#1850)	1 年之前
ext_server_windows.go	18ddf6d57d fix windows build	1 年之前
ggml.go	08f1e18965 Offload layers to GPU based on new model size estimates (#1850)	1 年之前
gguf.go	08f1e18965 Offload layers to GPU based on new model size estimates (#1850)	1 年之前
llama.go	08f1e18965 Offload layers to GPU based on new model size estimates (#1850)	1 年之前
llm.go	f387e9631b use runner if cuda alloc won't fit	1 年之前
shim_darwin.go	08f1e18965 Offload layers to GPU based on new model size estimates (#1850)	1 年之前
shim_ext_server.go	08f1e18965 Offload layers to GPU based on new model size estimates (#1850)	1 年之前
shim_ext_server_linux.go	77d96da94b Code shuffle to clean up the llm dir	1 年之前
shim_ext_server_windows.go	77d96da94b Code shuffle to clean up the llm dir	1 年之前
utils.go	fccf8d179f partial decode ggml bin for more info	1 年之前