NetModule Router Wiki

User Tools

Site Tools

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
app-hotes:ai-features [2026/06/24 20:20] – [Goal] grayapp-hotes:ai-features [2026/06/24 20:22] (current) – [2. Additional information] gray
Line 6: Line 6:
  
 ===== The background to this project ===== ===== The background to this project =====
-Enable the router to run its own AI 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 AI modules can be trained and fine-tuned for their core tasks to achieve optimal results.+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=== === Modules in the router===
Line 30: Line 30:
 ===== - Installing the Module into the Router Hardware ===== ===== - Installing the Module into the Router Hardware =====
  
-An adapter is required for the Deepx DX-M1 AI 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.+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|}} {{:app-notes:ki_adapter.jpg?900|}}
Line 74: Line 74:
 ===== - Additional information ===== ===== - Additional information =====
  
- * Deepx DX-M1 AI-Chip [[https://deepx.ai/products/dx-m1/#RelatedProducts|Webpage DX-M1 Chip]]+ * 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]]  * Deepx DX-M1 Documentation [[https://nx.docs.scailable.net/ai-accelerators-support/advanced/deepx-support|DX-M1 Documentation]]
  
- * AI-Models for the Chip [[https://developer.deepx.ai/modelzoo/| AI-Models]]+ * KI-Models for the Chip [[https://developer.deepx.ai/modelzoo/| KI-Models]]
  
  * Overview  DX-M1 Chip [[https://radxa.com/products/aicore/dx-m1| Overview]]  * Overview  DX-M1 Chip [[https://radxa.com/products/aicore/dx-m1| Overview]]

Page Tools

app-hotes/ai-features.1782332407.txt.gz · Last modified: 2026/06/24 20:20 by gray