6 lines
186 B
TOML
6 lines
186 B
TOML
[tools]
|
|
"llama.cpp" = { version = "latest", prerelease = "true", version_prefix = "b" }
|
|
|
|
[tasks.serve]
|
|
run = "llama serve --model ./llm/model2.gguf --port 8080 -ngl 99 --ctx-size 16384"
|