OpenSource/ollama @ bmizerany/client-registry

jmorganca fcf4d60eee llm: add back check for empty token cache		il y a 1 an
..
ext_server	fcf4d60eee llm: add back check for empty token cache	il y a 1 an
generate	8a65717f55 Do not build AVX runners on ARM64	il y a 1 an
llama.cpp @ 952d03dbea	e33d5c2dbc update llama.cpp commit to `952d03d`	il y a 1 an
patches	85801317d1 Fix clip log import	il y a 1 an
ggla.go	8b2c10061c refactor tensor query	il y a 1 an
ggml.go	435cc866a3 fix: mixtral graph	il y a 1 an
gguf.go	14476d48cc fixes for gguf (#3863)	il y a 1 an
llm.go	86e67fc4a9 Add import declaration for windows,arm64 to llm.go	il y a 1 an
llm_darwin_amd64.go	58d95cc9bd Switch back to subprocessing for llama.cpp	il y a 1 an
llm_darwin_arm64.go	58d95cc9bd Switch back to subprocessing for llama.cpp	il y a 1 an
llm_linux.go	58d95cc9bd Switch back to subprocessing for llama.cpp	il y a 1 an
llm_windows.go	058f6cd2cc Move nested payloads to installer and zip file on windows	il y a 1 an
memory.go	f81f308118 fix gemma, command-r layer weights	il y a 1 an
payload.go	058f6cd2cc Move nested payloads to installer and zip file on windows	il y a 1 an
server.go	7aa08a77ca llm: dont cap context window limit to training context window (#3988)	il y a 1 an
status.go	58d95cc9bd Switch back to subprocessing for llama.cpp	il y a 1 an