TensorRT 7.2.3.4 installation issue

I am trying to install tensor rt as per the Nvidia guidelines Installation Guide :: NVIDIA Deep Learning TensorRT Documentation

my environment:
Ubuntu 18.04,
CUDA Toolkit 11.2.1 ,
cuDNN 8.1.1

using debian installation method. getting the dependency error when running
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: libnvinfer7 (= 7.2.3-1+cuda11.1) but it is not going to be installed
Depends: libnvinfer-plugin7 (= 7.2.3-1+cuda11.1) but it is not going to be installed
Depends: libnvparsers7 (= 7.2.3-1+cuda11.1) but it is not going to be installed
Depends: libnvonnxparsers7 (= 7.2.3-1+cuda11.1) but it is not going to be installed
Depends: libnvinfer-bin (= 7.2.3-1+cuda11.1) but it is not going to be installed
Depends: libnvinfer-dev (= 7.2.3-1+cuda11.1) but it is not going to be installed
Depends: libnvinfer-plugin-dev (= 7.2.3-1+cuda11.1) but it is not going to be installed
Depends: libnvparsers-dev (= 7.2.3-1+cuda11.1) but it is not going to be installed
Depends: libnvonnxparsers-dev (= 7.2.3-1+cuda11.1) but it is not going to be installed
Depends: libnvinfer-samples (= 7.2.3-1+cuda11.1) but it is not going to be installed
Depends: libnvinfer-doc (= 7.2.3-1+cuda11.1) but it is not going to be installed
N: Ignoring file ‘preferences’ in directory ‘/etc/apt/sources.list.d/’ as it has no filename extension
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 am following the installation steps as per the link:
PyCUDA installed
Installed CUDA toolkit 11.2.1
Installed cuDNN 8.1.1
Downloaded TensorRT 7.2.3.4 local repo debian package for ubuntu 18.04
sudo dpkg -i nv-tensorrt-repo-{os}-{tag}_1-1_amd64.deb
sudo apt-key add /var/nv-tensorrt-repo-${tag}/7fa2af80.pub
sudo apt-get update

Error while executing the step:
sudo apt-get install tensorrt

The issue is solved.

i have installed cuda toolkit 11.2.1 as the installation procedure said so,
but somewhere it is also mentioned that TensorRT requires toolkit 11.1.1

i have removed toolkit 11.2.1 and replaced it with 11.1.1 my installation is successful.

1 Like

i am facing the same issue but it didn’t solve after changing cuda toolkit to 11.1.1
when trying to install using:
sudo apt-get install libnvinfer7 libnvonnxparsers7 libnvparsers7 libnvinfer-plugin7

The following packages have unmet dependencies:
libnvinfer7 : Depends: libcublas.so.11 but it is not installable or
libcublas-11-1 but it is not installable
Depends: cuda-nvrtc-11-1 but it is not installable
E: Unable to correct problems, you have held broken packages.

please help with this , urgent.

Hi @thaha1,

Please make sure you’re following 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

If you need further assistance, we recommend you to post your concern on CUDA Setup and Installation - NVIDIA Developer Forums to get better help.

Thanks!

@spolisetty i have done the exact setup as explained in the documentation.
Kindely let me know if there any workaround.
OS: UBUNTU 18.04
Installed cuda from run file , added to path , LD_LIBRARY_PATH.
Installed CUDNN , then pycuda.
TRT version 7.2.3 gives this issue .Please look into this