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.
Installs just this skill. Get the whole plugin for auto-invocation.
⚡ How it fires
How this skill gets triggered: by you, by Claude, or both.
Fires itselfClaude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/post-training-openrlhf
👁️ Context preview
The summary Claude sees to decide when to auto-load this skill.
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.
📊 Stats
Stars29,853
Forks3,189
LanguagePython
LicenseMIT
📦 Ships with claude-code-templates
</> SKILL.md
post-training-openrlhf.SKILL.md
---name: openrlhf-training
description: 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.
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Post-Training, OpenRLHF, RLHF, PPO, GRPO, RLOO, DPO, Ray, vLLM, Distributed Training, Large Models, ZeRO-3]
dependencies: [openrlhf, ray, vllm, torch, transformers, deepspeed]
---# OpenRLHF - High-Performance RLHF Training
## Quick start
OpenRLHF is a Ray-based RLHF framework optimized for distributed training with vLLM inference acceleration.
**Installation**:
```bash
# Launch Docker container
docker run --runtime=nvidia -it --rm --shm-size="10g" --cap-add=SYS_ADMIN \
-v $PWD:/openrlhf nvcr.io/nvidia/pytorch:25.02-py3 bash
# Uninstall conflicts
sudo pip uninstall xgboost transformer_engine flash_attn pynvml -y
# Install OpenRLHF with vLLM
pip install openrlhf[vllm]
```
**PPO Training** (Hybrid Engine):
**Hybrid Engine GPU sharing**: See [references/hybrid-engine.md](references/hybrid-engine.md) for vLLM sleep mode, DeepSpeed sleep mode, and optimal node allocation.
**Algorithm comparison**: See [references/algorithm-comparison.md](references/algorithm-comparison.md) for PPO vs GRPO vs RLOO vs REINFORCE++ benchmarks and hyperparameters.
**Multi-node setup**: See [references/multi-node-training.md](references/multi-node-training.md) for Ray cluster configuration and fault tolerance.
**Custom reward functions**: See [references/custom-rewards.md](references/custom-rewards.md) for reinforced fine-tuning and agent RLHF.
