intel/linux-npu-driver

Intel® NPU (Neural Processing Unit) Driver

What it solves

This project provides the necessary driver for the Intel® NPU (Neural Processing Unit), allowing Linux systems to communicate with and utilize the AI inference accelerator integrated into Intel® Core™ Ultra CPUs.

How it works

It acts as a kernel driver that enables the hardware accelerator (referred to in the kernel as the Versatile Processing Unit or VPU) to execute artificial neural network tasks in an energy-efficient manner.

Who it’s for

Developers and users of Linux-based AI PCs equipped with Intel® Core™ Ultra CPUs who need to enable hardware-accelerated AI inference.

Highlights

  • Supports Intel® Core™ Ultra generation CPUs (Meteor Lake).
  • Enables energy-efficient execution of AI tasks.
  • Integrates with the Intel® OneApi Level Zero and OpenVINO™ ecosystem.

Related

  • Project
    amd/xdna-driver

    A Linux kernel driver and XRT SHIM library that enables AI inference acceleration on AMD XDNA (NPU) devices for RyzenAI processors.

  • Project
    SearchSavior/OpenArc

    An OpenVINO-powered inference engine for Intel devices that serves LLMs, VLMs, and speech models via OpenAI-compatible endpoints.

  • Project
    aws-neuron/aws-neuron-sdk

    AWS Neuron is an SDK for high-performance deep learning and generative AI, enabling the deployment and profiling of workloads on AWS Inferentia and Trainium accelerators.

  • Project
    microsoft/onnxruntime-genai

    A high-performance API for running generative AI models on-device using ONNX Runtime, handling the full generative loop from pre-processing to sampling.

  • Project
    InfiniTensor/InfiniTensor

    InfiniTensor is an open‑source C++ runtime that imports ONNX graphs, applies generic graph rewrites, and executes them on CPU or on custom accelerator back‑ends (InfiniOps/InfiniRT). It offers Python bindings, a test suite, and a modular design that lets hardware vendors plug in their own kernels.