OpenSource/ollama @ mxyng/mllama

Michael Yang 75a07dd8f7 integrate mllama.cpp to server.cpp		7 月之前
..
ext_server	75a07dd8f7 integrate mllama.cpp to server.cpp	6 月之前
generate	d632e23fba Add Windows arm64 support to official builds (#5712)	7 月之前
llama.cpp @ 8962422b1c	5e2653f9fe llm: update llama.cpp commit to 8962422 (#6618)	8 月之前
patches	7d5e0ff80e add server.cpp and patches	7 月之前
filetype.go	d6f692ad1a Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322)	11 月之前
ggla.go	6b252918fb update convert test to check result data	9 月之前
ggml.go	bf612cd608 Merge pull request #6260 from ollama/mxyng/mem	7 月之前
ggml_test.go	cb42e607c5 llm: speed up gguf decoding by a lot (#5246)	10 月之前
gguf.go	6ffb5cb017 add conversion for microsoft phi 3 mini/medium 4k, 128	8 月之前
llm.go	d632e23fba Add Windows arm64 support to official builds (#5712)	7 月之前
llm_darwin.go	cd5c8f6471 Optimize container images for startup (#6547)	7 月之前
llm_linux.go	cd5c8f6471 Optimize container images for startup (#6547)	7 月之前
llm_windows.go	dbba73469d runner: Set windows above normal priority (#6905)	7 月之前
memory.go	56318fb365 Improve logging on GPU too small (#6666)	7 月之前
memory_test.go	77903ab8b4 llama3.1	8 月之前
server.go	a2d33ee390 linter feeding	7 月之前
status.go	04210aa6dd Catch one more error log	9 月之前