Download Edge Microvisor Toolkit

[stevenhoenisch]

The versions of Edge Microvisor Toolkit demonstrate the capabilities of Intel platforms for edge AI workloads through yet-to-be-upstreamed Linux kernel patches from Intel that optimize performance and other capabilities for Intel processors. All the versions of Edge Microvisor Toolkit use Linux kernel 6.12 from Intel. Here's where to download or build the version you want:

• Download the current ISO of the Developer Node and authenticate it with its SHA256. A mutable, ready-made version for development, customization, testing, benchmarking, and VM exploration, the developer node uses GRUB as the bootloader, works with DNF or TDNF for RPM package management, and supports K3s, Docker, and other cloud-native technology. Secure boot and full-disk encryption is enabled only for the real-time version; dm-verity is not enabled for either version.

• Get the latest weekly release of the RAW image for the real-time or non-RT Developer Node. Its latest weekly release is posted in GitHub Discussions under 📣 announcements. For predictable performance, the real-time developer node uses the Preempt_RT patch for Linux Kernel 6.12; see using the real-time version. 🚀 You can convert a RAW image to VHD or VHDX by using a tool like qemu-img convert.

• Build the immutable Standalone Node. The standalone node is an easy-to-install immutable version integrated with Kubernetes and foundational extensions to help partners quickly evaluate edge AI applications on virtual machines and containers powered by Intel platforms. It uses systemd-boot as the bootloader, atomic updates with a rollback option, and SELinux in permissive mode. The use of secure boot and full-disk encryption is optional; dm-verity is turned on by default.

• Build your own custom mutable or immutable version by selecting a predefined JSON image configuration file and a package list file that determine the image's properties and capabilities. In addition, you can create your own image configuration file and package list to build exactly the version that you want -- a powerful approach to customizing a Linux operating system to validate your edge AI workload on Intel processors.

• Deploy a version with Edge Manageability Framework. Versions of the toolkit are coupled with Edge Manageability Framework to help deliver early access to next-generation Intel platform features. Edge Manageability Framework automates the rollout of new OS profiles to compatible hardware platforms so that you can quickly deploy the latest Intel optimizations. See the framework's GitHub repository.

For more information, see selecting a version of Edge Microvisor Toolkit.

For help installing and configuring a version of Edge Microvisor Toolkit, see the the documentation website or check out the demo videos on YouTube. 🎥