home/categories/machine-learning/orchestra-research-ai-research-skills-06-post-training-openrlhf-skill-md
machine-learningdata-ai
openrlhf-training
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.
maintainer
Orchestra-Research
更新於 11/20/2025
星標
6563
分支
515
quick start
Installation and usage
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.
安裝
$ install --globalskills.sh
使用
安裝後，您可以通過在終端運行以下命令來使用此技能：
skills use openrlhf-training