missing VC++ Runtime Library of nvonnxparser.dll on Windows 7
api-ms-win-core-libraryloader-l1-2-0.dll
I’m guessing this can be solved by installing the VC++ Redist, but it’s not clear to me which version should be installed, and the VC++ runtime doesn’t seem to be explained in the TensorRT documentation
Environment
TensorRT Version: 7.2.3.4 GPU Type: unknown Nvidia Driver Version: CUDA Version: 11.1 CUDNN Version: 8 Operating System + Version: Windows 7
Hi,
Request you to share the ONNX model and the script if not shared already so that we can assist you better.
Alongside you can try few things:
validating your model with the below snippet
check_model.py
import sys
import onnx
filename = yourONNXmodel
model = onnx.load(filename)
onnx.checker.check_model(model).
2) Try running your model with trtexec command.
In case you are still facing issue, request you to share the trtexec “”–verbose"" log for further debugging
Thanks!
Sorry, I forgot to give the background of the question:
We developed a C++ program for model inference on Windows PCs, which works fine on Windows 10. However, on Windows 7, there will be a problem that the program cannot be started because of missing DLLs, and Windows error messages are as follows
We checked with the Dependency Walker that the DLL was introduced by the nvonnxparser. So I want to know how to install the runtime environment nvonnxparser.dll required in Windows 7.
Hi @739119168 ,
I see you are using a very old version of TRT, for updated features and performance, we highly recommend you to use latest version of TRT.
Can you try upgrading trt if possible and let us know if issue persist?