domains / families / research / openrlhf

openrlhf

separate

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

When to use

• Training large models (7B-70B+) with RL
• Need vLLM inference acceleration
• Want distributed architecture with Ray
• Have multi-node GPU cluster
• Need PPO/GRPO/RLOO/DPO in one framework
• **PPO**: Maximum control, best for complex rewards
• **GRPO**: Memory-efficient, no critic needed
• **RLOO**: Modified PPO with per-token KL

Skill page

Source