Problem when installing a docker image

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

Description

When I try to build a TensorRT image via the follwing command:

docker build -t torch_tensorrt -f ./docker/Dockerfile --build-arg TENSORRT_VERSION=8.5.1.7 .

I have the following error message:

ERROR: failed to solve: process "/bin/sh -c TENSORRT_MAJOR_VERSION=`echo ${TENSORRT_VERSION} | cut -d '.' -f 1` &&     apt-get install -y libnvinfer${TENSORRT_MAJOR_VERSION}=${TENSORRT_VERSION}.*                        libnvinfer-plugin${TENSORRT_MAJOR_VERSION}=${TENSORRT_VERSION}.*                        libnvinfer-dev=${TENSORRT_VERSION}.*                        libnvinfer-headers-dev=${TENSORRT_VERSION}.*                        libnvinfer-headers-plugin-dev=${TENSORRT_VERSION}.*                        libnvinfer-plugin-dev=${TENSORRT_VERSION}.*                        libnvonnxparsers${TENSORRT_MAJOR_VERSION}=${TENSORRT_VERSION}.*                        libnvonnxparsers-dev=${TENSORRT_VERSION}.*" did not complete successfully: exit code: 100
exit status 1

Can you help me ?

Environment

TensorRT Version: 8.5.1.7
GPU Type: NVIDIA GeForce RTX 3060
Nvidia Driver Version: 535.230.02
CUDA Version: ?
CUDNN Version: ?
Operating System + Version: Linux Mint 21
Python Version (if applicable): 3.9 or 3.10 or 3.13 !!!
TensorFlow Version (if applicable): 2.11.0
PyTorch Version (if applicable): 2.5.1
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