A user-friendly tool chain that enables the seamless execution of ONNX models using JAX as the backend.

A simple, performant and scalable Jax LLM!

⚡ Flashbax: Accelerated Replay Buffers in JAX

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

Lean theorem proving interface which feels like pen-and-paper proofs.

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

Use your Neovim like using Cursor AI IDE!

Open source codebase powering the HuggingChat app

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.

aider is AI pair programming in your terminal

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

High-performance In-browser LLM Inference Engine

Universal LLM Deployment Engine with ML Compilation

Fast and memory-efficient exact attention

Large Language Model Text Generation Inference

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

JAX-based neural network library

♟️ Vectorized RL game environments in JAX

🕹️ A diverse suite of scalable reinforcement learning environments in JAX

RL Environments in JAX 🌍

Schedule-Free Optimization in PyTorch

A library for advanced large language model reasoning

Training Sparse Autoencoders on Language Models

Run PyTorch LLMs locally on servers, desktop and mobile

An Extensible Deep Learning Library

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

SGLang is a fast serving framework for large language models and vision language models.

Generative AI extensions for onnxruntime