llama-cpp

LLM inference in C/C++

Run the following Vcpkg command to install the port.

vcpkg install llama-cpp

Usage details are not available for this port.

• llama-cpp[download]≥v5975#0

  All

  Support downloading a model from an URL

  Feature Dependencies

  • curl

    All
• llama-cpp[server]≥v9030#0

  All

  Build llama-server and llama-cli

• llama-cpp[tools]≥v5975#0

  All

  Build tools

  Feature Dependencies

  • miniaudio

    All
  • stb

    All

• cpp-httplib

  All
• ggml

  All
• nlohmann-json

  All
• vcpkg-cmake

  All
• vcpkg-cmake-config

  All