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
20598c18d7
separate routes
2023-07-06 10:37:05 -04:00
cd3b7e9bac
client updates
2023-07-06 10:36:58 -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
371a9cd9b2
wip go engine
...
Co-authored-by: Patrick Devine <pdevine@sonic.net>
2023-07-06 10:31:18 -04:00
Michael Yang
Jeffrey Morgan
Bruce MacDonald