OpenSource/ollama @ c895a7d13f74c66aee4c68aed75aaeddb7fbcf18

Michael Yang c895a7d13f some gocritic		1 anno fa
..
ext_server	829ff87bd1 revert tokenize ffi (#4761)	11 mesi fa
generate	7ca9605f54 speed up tests by only building static lib (#4740)	11 mesi fa
llama.cpp @ 5921b8f089	22f5c12ced Update llama.cpp submodule to `5921b8f0` (#4731)	11 mesi fa
patches	22f5c12ced Update llama.cpp submodule to `5921b8f0` (#4731)	11 mesi fa
filetype.go	d6f692ad1a Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322)	11 mesi fa
ggla.go	171eb040fc simplify safetensors reading	1 anno fa
ggml.go	d51f15257c Update llm/ggml.go	11 mesi fa
gguf.go	171eb040fc simplify safetensors reading	1 anno fa
llm.go	829ff87bd1 revert tokenize ffi (#4761)	11 mesi fa
llm_darwin_amd64.go	58d95cc9bd Switch back to subprocessing for llama.cpp	1 anno fa
llm_darwin_arm64.go	58d95cc9bd Switch back to subprocessing for llama.cpp	1 anno fa
llm_linux.go	58d95cc9bd Switch back to subprocessing for llama.cpp	1 anno fa
llm_windows.go	058f6cd2cc Move nested payloads to installer and zip file on windows	1 anno fa
memory.go	4cc3be3035 Move envconfig and consolidate env vars (#4608)	11 mesi fa
payload.go	04f3c12bb7 replace x/exp/slices with slices	11 mesi fa
server.go	c895a7d13f some gocritic	11 mesi fa
status.go	58d95cc9bd Switch back to subprocessing for llama.cpp	1 anno fa