LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Lossless DFlash speculative decoding for MLX on Apple Silicon

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

The official Python client for the Hugging Face Hub.

Run LLMs with MLX

Train the smallest LM you can that fits in 16MB. Best model wins!

Training-Ready RL Environments + Evals

Verifiers for LLM Reinforcement Learning

A trainable PyTorch reproduction of AlphaFold 3.

Get AI-powered command suggestions **directly** in your zsh shell.

AlphaFold 3 inference pipeline.

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

Easy-to-use interface and extensive collection of testing tools for optimizing performance and user experience.

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

Chai-1, SOTA model for biomolecular structure prediction

A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.

Aim 💫 — An easy-to-use & supercharged open-source AI metadata tracker (experiment tracking, AI agents tracing)

Fast and memory-efficient exact attention

🏕️ Development environment for machine learning

High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI …