OpenSource/ollama @ d78fb62056bffa0264f36cf3e49d0a64c88c032f

Patrick Devine c7cb0f0602 image processing for llama3.2 (#6963)		7 mēneši atpakaļ
..
ext_server	f2890a4494 IBM granite/granitemoe architecture support (#6760)	7 mēneši atpakaļ
generate	c3d321d405 llm: Remove GGML_CUDA_NO_PEER_COPY for ROCm (#7174)	7 mēneši atpakaļ
llama.cpp @ 3f1ae2e32c	f2890a4494 IBM granite/granitemoe architecture support (#6760)	7 mēneši atpakaļ
patches	f2890a4494 IBM granite/granitemoe architecture support (#6760)	7 mēneši atpakaļ
filetype.go	d6f692ad1a Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322)	1 gadu atpakaļ
ggla.go	c7cb0f0602 image processing for llama3.2 (#6963)	7 mēneši atpakaļ
ggml.go	c7cb0f0602 image processing for llama3.2 (#6963)	7 mēneši atpakaļ
ggml_test.go	cb42e607c5 llm: speed up gguf decoding by a lot (#5246)	11 mēneši atpakaļ
gguf.go	c7cb0f0602 image processing for llama3.2 (#6963)	7 mēneši atpakaļ
llm_darwin.go	cd5c8f6471 Optimize container images for startup (#6547)	8 mēneši atpakaļ
llm_linux.go	cd5c8f6471 Optimize container images for startup (#6547)	8 mēneši atpakaļ
llm_windows.go	dbba73469d runner: Set windows above normal priority (#6905)	8 mēneši atpakaļ
memory.go	c7cb0f0602 image processing for llama3.2 (#6963)	7 mēneši atpakaļ
memory_test.go	05cd82ef94 Rename gpu package discover (#7143)	7 mēneši atpakaļ
server.go	c7cb0f0602 image processing for llama3.2 (#6963)	7 mēneši atpakaļ
status.go	04210aa6dd Catch one more error log	9 mēneši atpakaļ