opendilab/LightRFT

Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

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

Scalable toolkit for efficient model reinforcement

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

Agentic RL Training at Scale

Democratizing Reinforcement Learning for LLMs

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning