Oonxruntime error on AWS

I am running inference on an AWS machine with T4 GPU on it. The model was trainned using roboflow training. When i run following code

import cv2
import supervision as sv
import inference
model = inference.get_model("aoi-gneuy/7")

The warning comes as follows:

2024-05-18 00:14:10.009689729 [W:onnxruntime:Default, onnxruntime_pybind_state.cc:640 CreateExecutionProviderInstance] Failed to create CUDAExecutionProvider. Please reference https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements to ensure all dependencies are met.

i have do pip install of both inference and inference-gpu, will this matter to this issue?

Hey @Ronald_Tse

We’ve seen this issue happen when CUDA is not properly installed. I recommend seeing this page:

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.