32a8edabae
use `Makefile` for dependency building instead of `go generate`
2023-07-06 10:59:27 -04:00
d24b2a8c58
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
2023-07-06 10:37:05 -04:00
f61b221cf9
remove debug print statements
2023-07-06 10:37:05 -04:00
d3f9d71c77
fix crash in bindings
2023-07-06 10:37:05 -04:00
cd3b7e9bac
client updates
2023-07-06 10:36:58 -04:00
76310d0bc5
fix llama.cpp build
2023-07-06 10:31:18 -04:00
f1e5a55101
move prompt templates out of python bindings
2023-07-06 10:31:18 -04:00
9448e62f38
add llama.cpp go bindings
2023-07-06 10:31:18 -04:00
Jeffrey Morgan
Michael Yang