====== 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===
----

{{:app-notes:ki_chip.jpg?950|}}

----
===== Prerequisites =====

    * NetModule NB2800 Wireless Router with wireless connection
    * NetModule Software [[https://share.netmodule.com/public/system-software/5.0/5.0.0.103/|5.0.0.103]] or newer
    * Not available for legacy products NB1600, NB2700, NB3700, NB3710

**
<WRAP center round important 90%>
The wiki was tested with router software nrsw-rootfs-HW17-0.0.0.0 and the LXC container with debina armhf 13.0
</WRAP>
**

----

===== - 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.

{{:app-notes:ki_adapter.jpg?900|}}


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.

{{:app-notes:ki_pcie.png?300|}}
 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.

<konsole>
=== BDINFO ===
bd/0/pd_module0:           slot=0,caps=wlan-main:wlan-aux                    
bd/0/pd_module1:           slot=1,caps=wlan-main:wlan-aux                    
bd/0/pd_module2:           slot=2,caps=wwan-main:wwan-aux:gnss-active:voice  
bd/0/pd_module3:           slot=3,caps=wwan-main:wwan-aux:voice              
</konsole>

You can check whether the module is present via the router's console.

<konsole>
lspci
02:00.0 Class 1200: 1ff4:0000
</konsole>

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.




----



===== - Additional information =====

 * Deepx DX-M1 KI-Chip [[https://deepx.ai/products/dx-m1/#RelatedProducts|Webpage DX-M1 Chip]]

 * Deepx DX-M1 Documentation [[https://nx.docs.scailable.net/ai-accelerators-support/advanced/deepx-support|DX-M1 Documentation]]

 * KI-Models for the Chip [[https://developer.deepx.ai/modelzoo/| KI-Models]]

 * Overview  DX-M1 Chip [[https://radxa.com/products/aicore/dx-m1| Overview]]


----