ggml ORG

Tensor library for machine learning

Low-level C++ tensor library for running machine learning models on CPU and accelerators, with integer quantisation and no runtime allocations.

LLM inference in C/C++

Run large language models locally on your computer or server using optimized C++ code, with no heavy dependencies or external APIs required.

Vim plugin for LLM-assisted code/text completion

VS Code extension for LLM-assisted code/text completion

Local LLM-assisted text completion for Qt Creator.

Port of OpenAI's Whisper model in C/C++

C++ port of OpenAI's Whisper speech-to-text model that runs offline on any device, from desktops to Raspberry Pi, without Python or heavy dependencies.

A cosy home for your LLMs.

LLM-based code completion engine

CI for ggml and related projects

llama.cpp's official website

No description.

Build and install script for llama.app

No description.

No description.

:octocat:⚙️🗑️ A GitHub Action to free disk space on an Ubuntu runner.

Use for testing CI

self-hosted GHA runners in containers

github action to speedup building using ccache

Brand assets for llama.app / llama.cpp

Github action to create releases

Set up your GitHub Actions workflow with a specific version of Xcode