Pi05 Server
NPU Server for Running the pi0.5 Robotic Model
2 min readupdated
The pi05-server tool lets you deploy the pi0.5 vision-language-action model directly on hardware boards featuring an NPU (neural processing unit). The server accepts camera images, current robot state, and a text task via HTTP requests, returning a sequence of 50 future actions. The model uses W8A8 quantization (8-bit weights and activations) for both the language model and the action expert, ensuring efficient performance on embedded hardware.
Key features
- NPU acceleration: The model is loaded once at startup and processes requests on the NPU.
- W8A8 quantization: 8-bit weights for the language model and action expert by default.
- Ready-to-use HTTP API: Endpoints for sending actions (
POST /v1/actions), health checks, and getting info. - State management: Request queue support and reproducibility via seed or fixed noise.
What you can do
- Run the server on a robotic board (aarch64) with NPU support.
- Send frames from three cameras, robot state, and a text command (prompt) to generate movement trajectories.
- Test the model using a Python client and compare results with reference runs.
Example
sh pi05-server-0.1.0-Linux.sh --skip-license --exclude-subdir
./pi05-server -w model.safetensors \
-w-llm-w8a8 pi05_llm_w8a8.gguf \
-w-ae-w8a8 pi05_ae_w8a8.gguf \
--host 0.0.0.0 --port 8080Read more
DetailsRepository files: server executable,
model.safetensors (vision encoder and embeddings), plus GGUF files for the language model and expert.Input data: Exactly 3 camera images (scaled to 224x224), a robot state array, and a text prompt.
Output data: An array of 50 steps by 32 normalized action values.










Comments