Edge Developer Kit Reference Scripts

This repository provides simplified developer kit reference setup scripts for various Intel platforms and GPUs.

Note: The main branch contains the latest development version of the project. It may include experimental features, work in progress, or unstable code.

Table of Contents

• Recommended Edge Design Support
• Architecture Overview
• System Requirements
• Quick Start
• Use Cases
• Troubleshooting
• Support
• Disclaimer

Recommended Edge Design Support

Product Collection	Code Name	Support	Validated Hardware
Intel® Arc™ Pro B-Series Graphics	Products formerly Battlemage	📋 Planned
Intel® Arc™ B-Series Graphics	Products formerly Battlemage	✅ Supported
Intel® Arc™ A-Series Graphics	Products formerly Alchemist	✅ Supported
Intel® Core™ Ultra Processors (Series 2)	Products formerly Arrow Lake	✅ Supported	Innodisk Intel® Core™ Ultra Series 2 Reference Kit IEI TANK-XM813 AAEON UP Xtreme ARL ASRock Industrial NUC BOX-255H
Intel® Core™ Ultra processors (Series 1)	Products formerly Meteor Lake	✅ Supported	Seavo* PIR-1014A AIoT Developer Kit AAEON* UP Xtreme i14 ASRock Industrial* NUC BOX-155H Asus* NUC 14 Pro
Intel® Core™ processors (Series 2)	Products formerly Bartlett Lake	📋 Planned
Intel® Core™ processors (Series 1)	Products formerly Raptor Lake	✅ Supported
Intel® Core™ Processor N-series	Products formerly Twin Lake	✅ Supported	AAEON RS-UPN-ADLN355-A10-0864

Architecture Overview

edge-developer-kit-reference-scripts/
├── main_installer.sh              # Main entry point
├── platform_detection.sh          # Platform and hardware detection
├── npu_installer.sh               # NPU drivers (Core Ultra)
├── gpu_installer.sh               # GPU drivers and tools
├── openvino_installer.sh          # OpenVINO and camera use cases
├── print_summary_table.sh         # Summarize post installation
└── usecases/                      # Reference implementation 

System Requirements

• Operating System: Ubuntu 24.04 LTS (Desktop)
• Kernel: HWE kernel (auto-installed by script)
• User Privileges: Requires sudo/root access
• Internet Connection: Needed for package installation
• Graphics: Integrated (iGPU) and/or discrete (dGPU) GPU

Quick Start

1. Install Operating System Install the latest Ubuntu* 24.04 LTS Desktop. Refer to the Ubuntu Desktop installation tutorial if needed.

2. Run Setup Script

   This step will configure the basic setup of the platform. Ensure all requirements have been met before proceeding.

   git clone https://github.com/intel/edge-developer-kit-reference-scripts.git
   cd edge-developer-kit-reference-scripts
   sudo ./main_installer.sh

   After installation finishes, you may be asked to reboot your system. Reboot when prompted. Installation is completed when you see this message:

   ✓ Platform configured

   System reboot is required.

3. Re-run the Installer

   After rebooting, run the installer again to complete the setup:

   sudo ./main_installer.sh

Use Cases

1. Intel® Distribution of OpenVINO™ Toolkit
2. Open WebUI with Ollama
3. LLM RAG Toolkit
4. AI Video Analytics
5. Digital Avatar
6. Time Coordinated Computing (TCC)
7. Smart Parking
8. Video Summarization & Visual RAG

Troubleshooting

Common Issues

Wrong Kernel Version:

✗ Unsupported kernel version: 6.8.x
This installer requires kernel 6.11.x
Please install HWE kernel: sudo apt install linux-generic-hwe-24.04

Permission Error:

✗ This script must be run with sudo or as root user

Platform-Specific Issues

Platform Not Detected:

• Check /sys/class/dmi/id/product_name
• Add to appropriate platform list

NPU Not Detected:

• Confirm you are using a Core Ultra platform
• Check for NPU device: ls /dev/intel-npu*
• If missing, reboot the system and rerun the installer

GPU Issues:

• Run the GPU installer separately: ./gpu_installer.sh
• Verify GPU detection: lspci | grep -i vga
• If issues persist, check for error messages in the terminal and review relevant log files
• Reboot the system after driver installation if prompted

Log Files & Troubleshooting Steps

During installation, logs are displayed in real time. For deeper troubleshooting, consult these sources:

• APT Package Logs: /var/log/apt/
• Docker Logs: docker logs [container_name]
• NPU Driver Logs: /var/log/intel-npu.log
• Installer Output: Review terminal messages for errors or warnings

Troubleshooting Checklist:

• Review relevant log files for error details
• Confirm your hardware matches the supported platforms
• Test individual installer scripts (e.g., gpu_installer.sh, npu_installer.sh)
• Search for known issues in GitHub Issues
• When reporting a bug, include platform model, OS version, and log excerpts

For further assistance, open an issue on GitHub with detailed information.

Disclaimer

This repository contains pre-production code and is intended for testing and evaluation purposes only. The code and features provided here are in development and may be incomplete, unstable, or subject to change without notice. Use this repository at your own risk.

The reference scripts provided in this repository have been validated and tested on the hardware listed in the documentation. While we strive to ensure compatibility and performance, these scripts may not function as expected on other hardware configurations. Users may encounter issues or unexpected behavior when running the scripts on untested hardware. If you encounter any issues or have suggestions for improvements, we welcome you to open an issue.

GStreamer License Notice: GStreamer* is an open source framework licensed under LGPL. See https://gstreamer.freedesktop.org/documentation/frequently-asked-questions/licensing.html. You are solely responsible for determining if your use of GStreamer requires any additional licenses. Intel is not responsible for obtaining any such licenses, nor liable for any licensing fees due, in connection with your use of GStreamer.