Stars
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
A computer algebra system written in pure Python
DeepEP: an efficient expert-parallel communication library
plasTeX plugin to build formalization blueprints.
A collection of formalized statements of conjectures in Lean.
Advanced Privacy-Preserving Federated Learning framework
Ongoing research training transformer language models at scale, including: BERT & GPT-2
Supercharge huggingface transformers with model parallelism.
The full dataset behind paperswithcode.com
An annotated implementation of the Transformer paper.
Development repository for the Triton language and compiler
Puzzles for exploring transformers
What would you do with 1000 H100s...
Solve puzzles. Improve your pytorch.
Convert PDF to markdown + JSON quickly with high accuracy
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
A Next-Generation Training Engine Built for Ultra-Large MoE Models
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)
DSPy: The framework for programming—not prompting—language models
Ongoing research training transformer models at scale
An educational resource to help anyone learn deep reinforcement learning.
Tutorials for Quantum Algorithms with Qiskit implementations.