RuntimeError: CUDA error: no kernel image is available for execution on the device

I faced this error when I tried to work with pytorch and cuda 12 on my RTX 2080 Ti. and when I downgraded the cuda version it was not working too.

someone has ideas on how I can work on pytorch with cuda 12

Hi there @Dorra and welcome to the NVIDIA developer forums!

You will need to share a bit more details about your issue, especially logs, system details, etc. for people to be able to help you. But first and foremost I moved your topic to the CUDA setup category since I suspect that your problems already started there.

I hope you get your problems resolved!

Hi @MarkusHoHo
I am working on ubuntu 20.04.
my graphic card is RTX 3080 Ti 16 gb with driver version 525 and cuda 12.0.
I tried to run a program that uses the deep learning library PyTorch.
I got the following error:
RuntimeError: CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.