No kernel image is available for execution on the device: what to do?

1

I know there are several other questions about this, but obviously none of them helped.
I have the following:

-NVIDIA 960M (cc=5.0)
-pytorch: 2.1.1
-Cuda: 11.8

However,

YOLOv5  2023-12-12 Python-3.9.5 torch-2.1.1+cu118 CUDA:0 (NVIDIA GeForce GTX 960M, 2048MiB)
024-05-22 11:42:51.0616616 [E:onnxruntime:, sequential_executor.cc:514 onnxruntime::ExecuteKernel] Non-zero status code returned while running QuickGelu node. Name:'QuickGelu' 
Status Message: CUDA error cudaErrorNoKernelImageForDevice:no kernel image is available for execution on the device
YoloV5 failed --> Exception raised: [ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running QuickGelu node. Name:'QuickGelu' Status Message: CUDA error cudaErrorNoKernelImageForDevice:no kernel image is available for execution on the device

I swear I have no idea on why it’s happening.
The torch version is stable and cuda is supported… what’s going on?

2

The error seems to be raised by ONNXRuntime so you might want to check their GPU architecture support.