How to install python3-libnvinfer/python3-libnvinfer-dev in my anaconda virtual environment


I installed CUDA DRIVER/CUDA toolkit/CUDNN/TensorRT by network Repo method one by one. Everything is OK except I failed to import tensort in my anaconda environment because tensorrt pybinding library was installed to my system default python path.

Can you guide me how to install python3-libnvinfer/python3-libnvinfer-dev/onnx-graphsurgeon/uff-converter-tf to Anaconda virtual enviroment? I tried to find related .whl files under /usr/src/tensorrt/ for manual installation but I can’t find “python” filefolder which existed in Tar installation way.


TensorRT Version: nv-tensorrt-repo-ubuntu2004-cuda11.3-trt8.0.1.6-ga-20210626_1-1_amd64.deb
GPU Type: Tesla V100 PCIE
Nvidia Driver Version: 465.19.01
CUDA Version: cuda-toolkit-11-3_11.3.1
CUDNN Version: |libcudnn8-dev_8.2.1.32-1+cuda11.3_amd64.deb
Operating System + Version: Ubuntu20.04.1+5.11.0
Python Version (if applicable): 3.9.6
TensorFlow Version (if applicable): 2.6.0
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Steps To Reproduce

Please include:

  • Exact steps/commands to build your repro
  • Exact steps/commands to run your repro
  • Full traceback of errors encountered

Please refer to the installation steps from the below link if in case you are missing on anything
Also, we suggest you to use TRT NGC containers to avoid any system dependency related issues.


I did installation following link step by step: Installation Guide :: NVIDIA Deep Learning TensorRT Documentation. However, I don’t know how to use “apt-get install” or “conda install” command to install TensorRT’s python API pacakage to my conda environment not system default python path. Do you hanve any method?

Hi @quxinqq ,
Can you please try using the whl files from the tar package to install TRT in anconda.