How to use TensorRT after updating CUDA 11.4 on JetPack 5.1.2

[mfatihaydogdu]

Hello,

We have updated our CUDA version from 11.4 to 12.2 on Xavier Dev Board with JetPack 5.1.2 according to Trying to update to CUDA 11.8 on Nvidia Xavier Dev Board

To get TensorRT compatible with CUDA 11.8, is it OK to follow the build from source procedure in TensorRT GitHub page GitHub - NVIDIA/TensorRT at release/8.5?
Do we also need an updated CUDNN?

Or we do not any update other than CUDA 12.2 update since it is written in Jetpack 5.1.2 documentation that Starting with JetPack 5.0.2, upgrade to latest and greatest CUDA releases from CUDA 11.8 onwards without the need to update Jetson Linux other JetPack components.??

[AastaLLL]

Hi,

To use TensorRT on JetPack 5, please stay on the default CUDA 11.4.
Since only CUDA is upgradable on JetPack 5. No TensorRT package can work with CUDA 12.2 or 11.8 on JetPack 5.
The TensorRT GitHub contains the Python binding source instead of the core libraries.

Thanks.