User Tools
Site Tools
Table of Contents
Netmodule Routers with KI Features
Goal
This wiki shows how to enable an KICore DX-M1 chip in the router and use it within an LXC container. It also explains how to set up additional utilities within the container.
The background to this project
Enable the router to run its own KI modules locally, directly on the router, without having to use a hyperscaler. Your own data can be used to train the AI modules because it is not shared with third parties. The entire value chain remains under your control and can be flexibly developed further. Applications include intelligent energy management systems, dynamic traffic control systems, and production management. The KI modules can be trained and fine-tuned for their core tasks to achieve optimal results.
Modules in the router
Prerequisites
- NetModule NB2800 Wireless Router with wireless connection
- NetModule Software 5.0.0.103 or newer
- Not available for legacy products NB1600, NB2700, NB3700, NB3710
The wiki was tested with router software nrsw-rootfs-HW17-0.0.0.0 and the LXC container with debina armhf 13.0
1. Installing the Module into the Router Hardware
An adapter is required for the Deepx DX-M1 KI chip to be used with the router. The PCI Express interfaces are implemented as Mini PCIe on the router board. The DX-M1 chip requires a Mini PCIe to M.2 M-key adapter.
The NB2800's circuit board features a DC/DC converter that supplies 3.3 volts to the two Mini-PCIe slots. The maximum output current is 6 amps. A maximum of 12 watts is available for the Mini-PCIe modules. The DX-M1 chip has a maximum power consumption of less than 5 watts.
The module can be installed in slot 1 or 2 on the NB2800.
The DX-M1 chip was inserted into the first slot
To ensure communication between the chip and the router, the module must be configured as Wi-Fi in the BD.
You can check whether the module is present via the router's console.
The module was detected in the router: “02:00.0” (PCI address of the device: Bus 02, Device 00, Function 0).
The device class of the module was correctly identified as “Class 1200” (processing accelerator), i.e., an NPU or AI accelerator
The last entry is generated generically because the name of the hardware is not stored in the lspci/pci.ids database.
2. Additional information
* Deepx DX-M1 KI-Chip Webpage DX-M1 Chip
* Deepx DX-M1 Documentation DX-M1 Documentation
* KI-Models for the Chip KI-Models
* Overview DX-M1 Chip Overview