# Fine Tuning Serving Openpi

Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using...

- Repository: https://github.com/Orchestra-Research/AI-Research-SKILLs (14176 stars)
- Category: Testing
- License: MIT
- Last updated: 2026-10-11
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add Orchestra-Research/AI-Research-SKILLs --skill fine-tuning-serving-openpi -g -a claude-code -y`
Codex: `npx skills add Orchestra-Research/AI-Research-SKILLs --skill fine-tuning-serving-openpi -g -a codex -y`
Cursor: `npx skills add Orchestra-Research/AI-Research-SKILLs --skill fine-tuning-serving-openpi -g -a cursor -y`
Gemini CLI: `npx skills add Orchestra-Research/AI-Research-SKILLs --skill fine-tuning-serving-openpi -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add Orchestra-Research/AI-Research-SKILLs`

## Description

Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# OpenPI Fine-Tuning and Serving

End-to-end workflows for fine-tuning and serving Physical Intelligence's OpenPI models (pi0, pi0-fast, pi0.5) on robot manipulation tasks from the public `openpi` repository. Covers blank-machine setup, JAX training, PyTorch training, checkpoint conversion, and policy inference serving.

## Quick start

Clone the public repo, install the workspace, then serve a pretrained policy:

```bash
git clone --recurse-submodules https://github.com/Physical-Intelligence/openpi.git
cd openpi
GIT_LFS_SKIP_SMUDGE=1 uv sync
GIT_LFS_SKIP_SMUDGE=1 uv pip install -e .
uv run scripts/serve_policy.py --env DROID
```

```python
from openpi_client import websocket_client_policy

client = websocket_client_policy.WebsocketClientPolicy(host="localhost", port=8000)
result = client.infer(observation)
actions = result["actions"]  # numpy array of shape (chunk_size, action_dim)
```

## Core concepts

**Model family**: OpenPI implements three model variants from Physical Intelligence:

| Model | Architecture | Speed | Quality | Typical use |
|-------|-------------|-------|---------|-------------|
| pi0 | Flow-matching VLA | Baseline | Highest | Research, complex tasks |
| pi0-fast | Autoregressive action tokens | 2-5x faster | Good | Real-time control |
| pi0.5 | pi0 + improved vision encoder | Baseline | Best | Latest default |

**Key design choices**:
- **Dual backend**: JAX (primary, official training) and PyTorch (community, deployment-friendly)
- **Config-driven**: All training/serving parameters defined in `src/openpi/training/config.py`
- **Norm stats**: Every config requires precomputed normalization statistics before training
- **WebSocket serving**: Policy servers expose a WebSocket API for low-latency inference

**Training loop invariant**: After every config or dataset change, always re-run this cycle:
1. Compute norm stats → 2. Train → 3. Serve checkpoint → 4. Validate inference

## Compute requirements

The rest: https://github.com/Orchestra-Research/AI-Research-SKILLs/blob/HEAD/18-multimodal/openpi/SKILL.md