llama.cpp

LLM inference in C/C++

Library ggml

Minimal Updated 21 minutes ago

Latest

min add llama.cpp

[ Docs ] [ Changelog ] [ Repo ] [ Security ] [ SBOM ]

What is llama.cpp?

LLM inference in C/C++

Installs the package into the current environment for this session. Use --build or --runtime to persist it as a build-time or runtime dependency.

min add llama.cpp

Listing the package under tasks.<name>.packages makes it available inside that task’s sandbox.

[tasks.dev]
packages = ["llama.cpp"]

Choose build-time for tools needed during compilation, runtime for dynamic libraries loaded at runtime.

min add --build llama.cpp
min add --runtime llama.cpp