Individual skill
post-training-openrlhf
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.
cli-tool/components/skills/ai-research/post-training-openrlhf/SKILL.md
Source commit ad81bf053f80b626801decf425f501ba49983d98
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 33,212
- Repository last updated
- Nov 8, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- anthropic Repository topic
- anthropic-claude Repository topic
- claude Repository topic
- claude-code Repository topic
- agent-skills Repository topic
- ai-agents Repository topic
- claude-code-plugins Repository topic
- cli Repository topic
- mcp Repository topic
- registry Repository topic
- post-training Declared skill tag
- openrlhf Declared skill tag
- rlhf Declared skill tag
- ppo Declared skill tag
- grpo Declared skill tag
- rloo Declared skill tag
- dpo Declared skill tag
- ray Declared skill tag
- vllm Declared skill tag
- distributed-training Declared skill tag
- large-models Declared skill tag
- zero-3 Declared skill tag
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesSKILL.mdcore · 8,384 bytesreferences/algorithm-comparison.mddoc · 9,783 bytesreferences/custom-rewards.mddoc · 15,865 bytesreferences/hybrid-engine.mddoc · 7,266 bytesreferences/multi-node-training.mddoc · 11,099 bytes
Read excerpt
# 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