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

I have a laptop with Windows 10, and a 960M as graphic card.
When I run a speicific project this error appears:

2024-03-29 14:43:59.4468751 [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
[03/29/24 14:43:59] ERROR    Unable to validate model artifacts, clearing cache: Unable to run test inference. Cause: [ONNXRuntimeError] : 1 : FAIL :  roboflow.py:612                             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

the inference-gpu library from roboflow asks for onnx-runtime version 1.15, which also requires cuda 11.8 (supported by my graphic card).
I also downloaded the correct cudnn folder and added it to the PATH folder.
Also downloaded correct pytorch version (in case it was needed), and drivers are updated…

Basically I don’t know what’s going on: may someone give me an hand?