CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning

Drive OSS standards and tools for data curation and evaluation creation for state of the art AI agents

Standardize benchmark wrapping so the community can wrap various otherwise-incompatible benchmarks uniformly and use them everywhere.

A high-throughput and memory-efficient inference and serving engine for LLMs

Code for paper "The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning"

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

The personal finance app for everyone

A scalable asynchronous reinforcement learning implementation with in-flight weight updates.

Recipes to scale inference-time compute of open models

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Simple RL training for reasoning

Fully open reproduction of DeepSeek-R1

Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models

A bibliography and survey of the papers surrounding o1

The MATH Dataset (NeurIPS 2021)

TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle

🙃 A delightful community-driven (with 2,500+ contributors) framework for managing your zsh configuration. Includes 300+ optional plugins (rails, git, macOS, hub, docker, homebrew, node, php, python…

The official Meta Llama 3 GitHub site

A blazing fast inference solution for text embeddings models

WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?

🌎💪 BrowserGym, a Gym environment for web task automation

Code for Contrastive Preference Learning (CPL)

Firefly III: a personal finances manager

Home of StarCoder2!

Easy and Efficient Quantization for Transformers

A Comprehensive Assessment of Trustworthiness in GPT Models