Agent skill · research science · zechenzhangagi
fine-tuning-serving-openpi
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.
Why this skill is useful
Adds executable scripts for fine-tuning and serving OpenPI models that are not available in public documentation.
What it needs
Requires jax, torch, transformers, uv installed locally. About 7k tokens when loaded. Last updated 2026-06-16. 11,472 stars on the source repository.
What this skill does
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: 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. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills zechenzhangagi/openpi