llama.cpp

Overview

llama.cpp is a AI & Machine Learning project, described by its maintainers as: "LLM inference in C/C++." Written primarily in C++, it ranks among the most-starred projects on GitHub, with roughly 119.7k stars and 20.4k forks as of the latest data. Topics tagged by the maintainers include ggml — see the "Key topics" section below for a quick explanation of each.

Key topics

• ggml

Getting started

Installation steps vary depending on how a project is packaged, so the most reliable source is always the official README. As a starting point:

Open the official repository ↗

How it compares

Here is how this project sits alongside a few other tools in the same category:

• langchain★ 141.3k · Python
• ollama★ 175.8k · Go
• transformers★ 162.4k · Python

Questions about this project

What is llama.cpp?

llama.cpp is a AI & Machine Learning project, described by its maintainers as: "LLM inference in C/C++." Written primarily in C++, it ranks among the most-starred projects on GitHub, with roughly 119.7k stars and 20.4k forks as of the latest data. Topics tagged by the maintainers include ggml — see the "Key topics" section below for a quick explanation of each.

What license does llama.cpp use?

MIT

How popular is llama.cpp on GitHub?

llama.cpp has roughly 119.7k stars and 20.4k forks on GitHub as of the latest data.

Is llama.cpp actively maintained?

Based on its GitHub activity, this repository has been updated recently, which is generally a good sign of active maintenance.

What language is llama.cpp written in?

llama.cpp is written primarily in C++.

Repository info