This document applies to the following applications:
| MLFB Number | Application description |
|---|---|
| MLFB 6AV2170-0LA10-0AA0 | AI Inference Server with support for single pipeline version |
| MLFB 6AV2170-0LA10-1AA0 | AI Inference Server with support for multiple pipeline version |
| MLFB 6AV2170-0LA11-0AA0 | AI Inference Server with support for GPU accelerated hardware |
Each chapter is valid for both applications except for those statements where the MLFB numbers are explicitly stated.
Notice: Only one AI Inference Server application instance (from the above list) can be installed on an edge device. It means you can install MLFB 6AV2170-0LA10-0AA0 or MLFB 6AV2170-0LA10-1AA0 or MLFB 6AV2170-0LA11-0AA0 on a single edge device. You cannot install e.g. MLFB 6AV2170-0LA11-0AA0 and MLFB 6AV2170-0LA10-1AA0 applications on a single device.
Notice: It's the Customer's responsibility to verify end-to-end functionality with PLC data writeback before putting it to production environment.
Notice: The AI model (pipeline) is a code generated by the user, and it is the responsibility of the user to ensure that it is free of viruses/Trojans. The app was scanned for viruses before release on Siemens Industrial Edge. The pipeline cannot be scanned due to the type of mobile code.
Notice: Please do not include sensitive information (like user credentials) in the configuration package (pipeline).
Notice: To prevent memory exhaustion on Industrial PCs, AI Inference Server enforces a memory usage limit per application. If an application exceeds its allocated memory threshold, Industrial Edge automatically terminates and restarts the process to preserve system integrity and ensure continued operation. For Industrial Edge Virtual Devices (IEVD), the same memory enforcement behavior applies. However, it is the customer’s responsibility to provision sufficient memory to each virtual device to enable proper enforcement and avoid unexpected application termination.
Notice: Always evaluate available system resources prior to starting a pipeline.
CAUTION: AI Inference Server should not be used in mission-critical scenarios with high risks (i.e. development, construction, maintenance or operation of systems, the failure of which could lead to a life-threatening situation or to catastrophic damage ("critical application")). Examples of critical applications: Use in avionics, navigation, autonomous vehicle applications, AI solutions for automotive products, the military, medicine, life support or other life-critical applications.