An open platform for training, serving and evaluating chat-oriented LLMs—powering Vicuna & Chatbot Arena.
Zero-code CLI & WebUI to fine-tune 100+ LLMs/VLMs with LoRA, QLoRA, PPO, DPO and more.
An open-source, Ray-based framework for scalable Reinforcement Learning from Human Feedback (RLHF).
Volcano Engine Reinforcement Learning library for efficient LLM post-training—open-sourced HybridFlow.
