verl-project/verl

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

The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.

Stable and Efficient Reinforcement Learning for Trillion-Parameter LLMs

Scalable toolkit for efficient model reinforcement

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

Ludic – an LLM-RL library for the era of experience

Post-training framework for large models, from new objectives to new rollout systems.

An LLM post-training framework with vLLM for RL Scaling

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)