Conversion from onnx to TensorRT engine

AI & Data Science Deep Learning (Training & Inference) TensorRT
,
1

Description

while conversion from onnx to tensorrt ""ImportError: /home/amogh/scratch/anaconda3/envs/gbc/lib/python3.8/site-packages/pycuda/_driver.cpython-38-x86_64-linux-gnu.so: undefined symbol: cuDevicePrimaryCtxRelease_v2""

Note:
UserWarning: Failed to import the CUDA driver interface, with an error message indicating that the version of your CUDA header does not match the version of your CUDA driver.

Environment

TensorRT Version: 8.6.1
GPU Type: Quadro P5000-16GB
Nvidia Driver Version:
CUDA Version: 11.3
Operating System + Version: ubuntu 18.04
Python Version (if applicable): 3.8
PyTorch Version (if applicable): 1.13
Baremetal or Container (if container which image + tag): none

4

Hi,

The above issue looks setup-related. Ensure that you have the correct NVIDIA GPU driver installed that is compatible with the CUDA version. You can check your GPU driver version by running nvidia-smi. Please make sure you are able to run a CUDA sample correctly.

Thank you.