Unmet dependencies while installing TensorRT with CUDA 12.2

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

Description

I am trying to install tensorrt and following the instructions here:

I do:

sudo dpkg -i nv-tensorrt-local-repo-ubuntu2204-8.6.1-cuda-12.0_1.0-1_amd64.deb
sudo cp /var/nv-tensorrt-local-repo-ubuntu2204-8.6.1-cuda-12.0/*-keyring.gpg /usr/share/keyrings/

But when I get to running:
sudo apt-get install tensorrt

I get the error:

The following packages have unmet dependencies.
 libnvinfer-samples : Depends: cuda-nvcc-12-1 but it is not installable or
                               cuda-nvcc-12-0 but it is not installable
E: Unable to correct problems, you have held broken packages.

Even though

  1. I already have CUDA and NVCC installed in
    /usr/local/cuda-12.2/bin/nvcc
  2. I can successfully build and run the factory samples in
    TensorRT-8.6.1.6/samples/sampleOnnxMNIST/

Update: It looks like TensorRT is not supported for CUDA 12.2?

Environment

TensorRT Version: TensorRT-8.6.1.6
GPU Type: RTX 2060
Nvidia Driver Version: 535
CUDA Version: 12.2
CUDNN Version:
Operating System + Version: Ubuntu 22.04
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

6 Likes
3

Hi,
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.

Thanks!