verl: Volcano Engine Reinforcement Learning for LLMs

An independent Python feature port of Claude Code, entirely rewritting from scratch using oh-my-codex. Educational Purpose only.

Lightweight coding agent that runs in your terminal

slime is an LLM post-training framework for RL Scaling.

Democratizing Reinforcement Learning for LLMs

A set of examples based on verl for end-to-end RL training recipes.

Post-training with Tinker

TensorDict is a pytorch dedicated tensor container.

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory…

Ongoing research training transformer models at scale

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Fast and memory-efficient exact attention

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

Tensors and Dynamic neural networks in Python with strong GPU acceleration

🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents. https://oasis.camel-ai.org

Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)

A series of math-specific large language models of our Qwen2 series.