Michael Yang f8ff2d6879 enable metal gpu acceleration ... ggml-metal.metal must be in the same directory as the ollama binary otherwise llama.cpp will not be able to find it and load it. 1. go generate llama/llama_metal.go 2. go build . 3. ./ollama serve		2023-07-05 18:11:12 -07:00
..
binding	fix crash in bindings	2023-07-05 16:28:18 -04:00
.gitignore	add llama.cpp go bindings	2023-07-03 16:32:48 -04:00
CMakeLists.txt	enable metal gpu acceleration	2023-07-05 18:11:12 -07:00
llama.go	remove debug print statements	2023-07-05 16:29:12 -04:00
llama_cublas.go	add llama.cpp go bindings	2023-07-03 16:32:48 -04:00
llama_metal.go	enable metal gpu acceleration	2023-07-05 18:11:12 -07:00
llama_openblas.go	add llama.cpp go bindings	2023-07-03 16:32:48 -04:00
options.go	add llama.cpp go bindings	2023-07-03 16:32:48 -04:00