TensorRT installation fails, missing libnvinfer-samples

Description

I am trying to install TensorRT (cuda11.4-trt8.2.0.6-ea-20210922) but I keep getting the error :

The following packages have unmet dependencies:
tensorrt : Depends: libnvinfer-samples (= 8.2.0-1+cuda11.4) but it is not going to be installed
E: Unable to correct problems, you have held broken packages.

Could the cause be that I am Using CUDA version 11.5 and the TenosrRT is for 11.4?

Greetings and thanks in advance.

Environment

TensorRT Version: nv-tensorrt-repo-ubuntu2004-cuda11.4-trt8.2.0.6-ea-20210922_1-1_amd64
GPU Type: NVIDIA Corporation TU117GLM [Quadro T1000 Mobile] / Quadro T1000/PCIe/SSE2
Nvidia Driver Version: 495.29.05
CUDA Version: 11.5
CUDNN Version: –
Operating System + Version: Ubuntu 20.04
Python Version (if applicable): 3.8.10

Steps To Reproduce

os=“ubuntu2004”
tag=“cuda11.4-trt8.2.0.6-ea-20210922”
sudo dpkg -i nv-tensorrt-repo-${os}-${tag}_1-1_amd64.deb
sudo apt-key add /var/nv-tensorrt-repo-${os}-${tag}/7fa2af80.pub
sudo apt-get update
sudo apt-get install tensorrt

Reading package lists… Done
Building dependency tree
Reading state information… Done
Some packages could not be installed. This may mean that you have
requested an impossible situation or if you are using the unstable
distribution that some required packages have not yet been created
or been moved out of Incoming.
The following information may help to resolve the situation:

The following packages have unmet dependencies:
tensorrt : Depends: libnvinfer-samples (= 8.2.0-1+cuda11.4) but it is not going to be installed
E: Unable to correct problems, you have held broken packages.

Hi,
Please refer to the installation steps from the below link if in case you are missing on anything
https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html
Also, we suggest you to use TRT NGC containers to avoid any system dependency related issues.
https://ngc.nvidia.com/catalog/containers/nvidia:tensorrt

Thanks!

I had to install cuda 11.4 then it worked.

For this I followed CUDA Toolkit 11.4 Downloads but specified cuda 11.4 in the last command.

sudo apt-get -y install cuda-11.4

3 Likes

I have cuda-11.5 and met the same problem