An Open Source Machine Learning Framework for Everyone

LLM inference in C/C++

A library for efficient similarity search and clustering of dense vectors.

Windows Subsystem for Linux

MLX: An array framework for Apple silicon

Karabiner-Elements is a powerful tool for customizing keyboards on macOS

🎤⌨️ Acoustic keyboard eavesdropping

High-speed Large Language Model Serving for Local Deployment

Fast inference engine for Transformer models

oneAPI Deep Neural Network Library (oneDNN)

A lightweight library for portable low-level GPU computation using WebGPU.

Kernels & AI inference engine for mobile devices.

Swift API for MLX

Fast, Flexible and Portable Structured Generation

A high-quality speech analysis, manipulation and synthesis system

TinyChatEngine: On-Device LLM Inference Library

Suno AI's Bark model in C/C++ for fast text-to-speech generation

Speech-to-text server framework with next-gen Kaldi

Easy and Efficient Quantization for Transformers

A minimalistic C++ Jinja templating engine for LLM chat templates

Thin wrapper around GGML to make life easier

An in-process trace collector using the Rust tracing framework and the Perfetto C++ SDK