llama-cpp 9030

LLM inference in C/C++

Dependencies

Not used by any other package

download - Support downloading a model from an URL

Dependencies

server - Build llama-server and llama-cli

tools - Build tools

Dependencies

This package supports the following triplets:

Supported on all triplets

In classic mode, run the following vcpkg command:

 vcpkg install llama-cpp

In manifest mode, run the following vcpkg command in your project directory:

 vcpkg add port llama-cpp