dotnet cuda docker

[skywalkerisnull]

Hello everyone,

We have been having some trouble getting dotnet (C#) to work with CUDA in docker. We have the CPU version working, but when we use the latest-cuda, we get an error such as:

fail: DnnInference.Core.Application.Dnn.OnnxBase[0]
      exception happpend
      Microsoft.ML.OnnxRuntime.OnnxRuntimeException: [ErrorCode:RuntimeException] /onnxruntime_src/include/onnxruntime/core/common/logging/logging.h:313 static const onnxruntime::logging::Logger& onnxruntime::logging::LoggingManager::DefaultLogger() Attempt to use DefaultLogger but none has been registered.
      
         at Microsoft.ML.OnnxRuntime.NativeApiStatus.VerifySuccess(IntPtr nativeStatus)
         at Microsoft.ML.OnnxRuntime.SessionOptions.MakeSessionOptionWithCudaProvider(Int32 deviceId)

The base image we are using is:

FROM mcr.microsoft.com/azureml/onnxruntime:latest-cuda

We had the service running with the same base image in python and only needed to install our python dependencies and it was able to execute on the GPU. Any ideas or things we could look into to make it work with dotnet on CUDA in a container?