amd/xdna-driver

AMD XDNA Driver (amdxdna.ko) for Linux and XRT SHIM library

What it solves

This project provides the necessary Linux kernel driver (amdxdna.ko) and XRT SHIM library to enable support for AMD XDNA devices (NPUs) on Linux. It allows users to run AI applications by bridging the hardware device with the Xilinx Runtime (XRT) environment.

How it works

The project consists of a kernel-level driver that manages the NPU hardware and a plugin package that includes the XRT SHIM library and firmware binaries. The driver is mirrored from the Linux kernel staging tree and is integrated into the system via DKMS (Dynamic Kernel Module Support) to ensure it compiles and loads correctly across different kernel versions.

Who it’s for

Developers and users with RyzenAI processors who want to run AI inference applications on their NPU under Ubuntu, Arch Linux, or Fedora.

Highlights

  • Multi-distro support: Provides build and installation recipes for Ubuntu, Arch Linux, and Fedora.
  • XRT Integration: Specifically designed to work with the Xilinx Runtime (XRT) to provide a standardized interface for NPU access.
  • Firmware Management: Bundles matching firmware binaries to prevent version mismatch errors between the driver and the hardware.
  • Inference Focus: Optimized specifically for accelerating ML inference rather than training.

Related

  • Project
    intel/linux-npu-driver

    A Linux kernel driver for the Intel® NPU, enabling energy-efficient AI inference acceleration on Intel® Core™ Ultra CPUs.

  • Project
    Xilinx/XRT

    A runtime software interface that provides an abstracted layer for managing and interacting with AMD NPUs and FPGAs across different hardware platforms.

  • Project
    amd/RyzenAI-SW

    A suite of tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen AI-based PCs to maximize hardware acceleration.

  • 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
    baidu/vLLM-Kunlun

    A hardware plugin that enables vLLM to run on Kunlun XPU, providing optimized kernels and support for a wide range of LLMs and multimodal models.