Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →orchestra-research/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.
Passed 19 of 20 test cases with the skill, and 7 of 20 without it.
and 21 more in the full report
14 fixed8 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
We want to quickly spin up an OpenPI policy server for the simulated ALOHA environment using the standard pre-trained checkpoint preset. What CLI command starts this server?
| Checked | Without skill | With skill |
|---|---|---|
| Runs scripts/serve_policy.py with --env ALOHA_SIM | Missed | Passed |
The instructions your model reads when the skill loads.
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.
Clone the public repo, install the workspace, then serve a pretrained policy:
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
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)
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:
src/openpi/training/config.pytest cases passed, vs 7 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.