OpenSource/ollama @ mxyng/split-bin

Michael Yang 41ae232e10 split model layer into metadata and data layers		vor 1 Jahr
..
ext_server	fcf4d60eee llm: add back check for empty token cache	vor 1 Jahr
generate	8a65717f55 Do not build AVX runners on ARM64	vor 1 Jahr
llama.cpp @ 952d03dbea	e33d5c2dbc update llama.cpp commit to `952d03d`	vor 1 Jahr
patches	85801317d1 Fix clip log import	vor 1 Jahr
filetype.go	da0bb5d772 comments	vor 1 Jahr
ggla.go	41ae232e10 split model layer into metadata and data layers	vor 1 Jahr
ggml.go	41ae232e10 split model layer into metadata and data layers	vor 1 Jahr
gguf.go	41ae232e10 split model layer into metadata and data layers	vor 1 Jahr
llm.go	da0bb5d772 comments	vor 1 Jahr
llm_darwin_amd64.go	58d95cc9bd Switch back to subprocessing for llama.cpp	vor 1 Jahr
llm_darwin_arm64.go	58d95cc9bd Switch back to subprocessing for llama.cpp	vor 1 Jahr
llm_linux.go	58d95cc9bd Switch back to subprocessing for llama.cpp	vor 1 Jahr
llm_windows.go	058f6cd2cc Move nested payloads to installer and zip file on windows	vor 1 Jahr
memory.go	f0c454ab57 gpu: add 512MiB to darwin minimum, metal doesn't have partial offloading overhead (#4068)	vor 1 Jahr
payload.go	058f6cd2cc Move nested payloads to installer and zip file on windows	vor 1 Jahr
server.go	321d57e1a0 Removing go routine calling .wait from load.	vor 1 Jahr
status.go	58d95cc9bd Switch back to subprocessing for llama.cpp	vor 1 Jahr