Skip to main content
HZhao.3
Visitor II
December 14, 2025
Solved

What's the newest ONNX Runtime version that the X-CUBE-AI 10.2.0 supports?

  • December 14, 2025
  • 1 reply
  • 1344 views

I want to train some small DL models with Nvidia's RTX 50 series GPU, which can work properly only with CUDA 12.x. I've learned that the CUDA 12.x is only compatible with ONNX Runtime 1.17.x or newer version. So I want to know if the X-CUBE-AI 10.2.0 support ONNX Runtime 1.17.x or newer version? If it can, I would like use the X-CUBE-AI 10.2.0 to deploy my DL models on the STM32 MCUs.

Best answer by hamitiya

Hello @HZhao.3 

X-CUBE-AI 10.2.0 uses ST Edge AI Core 2.2.0 which is delivered with ONNX Runtime 1.18.1.

You can find all the embedded tools using the command `stedgeai --tools-version`

 

> stedgeai --tools-version
stedgeai - ST Edge AI Core v2.2.0-20266 2adc00962
- Python version : 3.9.13
- Numpy version : 1.26.4
- TF version : 2.18.0
- TF Keras version : 3.7.0
- ONNX version : 1.15.0
- ONNX RT version : 1.18.1

 

Also,  ST Edge AI Core 3.0  has been delivered and uses ONNX RT 1.19.2.

 

Best regards,

Yanis

1 reply

hamitiya
hamitiyaBest answer
ST Employee
December 15, 2025

Hello @HZhao.3 

X-CUBE-AI 10.2.0 uses ST Edge AI Core 2.2.0 which is delivered with ONNX Runtime 1.18.1.

You can find all the embedded tools using the command `stedgeai --tools-version`

 

> stedgeai --tools-version
stedgeai - ST Edge AI Core v2.2.0-20266 2adc00962
- Python version : 3.9.13
- Numpy version : 1.26.4
- TF version : 2.18.0
- TF Keras version : 3.7.0
- ONNX version : 1.15.0
- ONNX RT version : 1.18.1

 

Also,  ST Edge AI Core 3.0  has been delivered and uses ONNX RT 1.19.2.

 

Best regards,

Yanis

​In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.