Skip to content
Other

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 8080
Read moreDetails
Repository 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.
Discuss Telegram 0 19

Will it run?

Working out the memory needs

The bot is still collecting this model's weight sizes; the estimate will appear here in a few minutes. Meanwhile you can rent a GPU with headroom.

Massed ComputeOpen Massed Compute

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # Renesas/Pi05
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download Renesas/Pi05 --local-dir ~/models/Pi05
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to Pi05
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of Pi05 (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

Renesas/Pi05
Author
Renesas
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

190

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments