Description
I want to build a container of Tensorrt 8.4+cuda11.4 according to this tutorial https://github.com/NVIDIA/TensorRT/tree/8.4.1。
Then I get the following error.
Step 19/28 : RUN if [ "${CUDA_VERSION}" = "10.2" ] ; then v="${TRT_VERSION%.}-1+cuda${CUDA_VERSION}" && apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub && apt-get update && sudo apt-get install libnvinfer8=${v} libnvonnxparsers8=${v} libnvparsers8=${v} libnvinfer-plugin8=${v} libnvinfer-dev=${v} libnvonnxparsers-dev=${v} libnvparsers-dev=${v} libnvinfer-plugin-dev=${v} python3-libnvinfer=${v}; else v="${TRT_VERSION%.}-1+cuda${CUDA_VERSION%.}" && apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub && apt-get update && sudo apt-get install libnvinfer8=${v} libnvonnxparsers8=${v} libnvparsers8=${v} libnvinfer-plugin8=${v} libnvinfer-dev=${v} libnvonnxparsers-dev=${v} libnvparsers-dev=${v} libnvinfer-plugin-dev=${v} python3-libnvinfer=${v}; fi
---> Running in 1a2fd308bb55
Warning: apt-key output should not be parsed (stdout is not a terminal)
Executing: /tmp/apt-key-gpghome.0Z4XcLaQfG/gpg.1.sh --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub
gpg: requesting key from 'https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub'
gpg: key A4B469963BF863CC: "cudatools cudatools@nvidia.com" not changed
gpg: Total number processed: 1
gpg: unchanged: 1
Hit:1 http://archive.ubuntu.com/ubuntu focal InRelease
Hit:2 http://security.ubuntu.com/ubuntu focal-security InRelease
Hit:3 http://ppa.launchpad.net/ubuntu-toolchain-r/test/ubuntu focal InRelease
Hit:4 http://archive.ubuntu.com/ubuntu focal-updates InRelease
Hit:5 http://archive.ubuntu.com/ubuntu focal-backports InRelease
Hit:6 https://developer.download.nvidia.cn/compute/cuda/repos/ubuntu2004/x86_64 InRelease
Reading package lists...
Reading package lists...
Building dependency tree...
Reading state information...
E: Version '8.4.1-1+cuda11.4' for 'libnvinfer8' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvonnxparsers8' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvparsers8' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvinfer-plugin8' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvinfer-dev' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvonnxparsers-dev' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvparsers-dev' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvinfer-plugin-dev' was not found
E: Version '8.4.1-1+cuda11.4' for 'python3-libnvinfer' was not found
The command '/bin/bash -c if [ "${CUDA_VERSION}" = "10.2" ] ; then v="${TRT_VERSION%.}-1+cuda${CUDA_VERSION}" && apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub && apt-get update && sudo apt-get install libnvinfer8=${v} libnvonnxparsers8=${v} libnvparsers8=${v} libnvinfer-plugin8=${v} libnvinfer-dev=${v} libnvonnxparsers-dev=${v} libnvparsers-dev=${v} libnvinfer-plugin-dev=${v} python3-libnvinfer=${v}; else v="${TRT_VERSION%.}-1+cuda${CUDA_VERSION%.}" && apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub && apt-get update && sudo apt-get install libnvinfer8=${v} libnvonnxparsers8=${v} libnvparsers8=${v} libnvinfer-plugin8=${v} libnvinfer-dev=${v} libnvonnxparsers-dev=${v} libnvparsers-dev=${v} libnvinfer-plugin-dev=${v} python3-libnvinfer=${v}; fi' returned a non-zero code: 100
My command is ：./docker/build.sh --file docker/ubuntu-20.04.Dockerfile --tag tensorrt-ubuntu20.04-cuda11.6 --cuda 11.4.2
and it show ：
docker build -f docker/ubuntu-20.04.Dockerfile --build-arg CUDA_VERSION=11.4.2 --build-arg uid=0 --build-arg gid=0 --tag=tensorrt-ubuntu20.04-cuda11.6 .
Does Tensorrt8.4 not support cuda11.4, but only 11.6? The same error occurred when I first used tensor 8.5
Please give me some suggestions. My GPU driver limits me to using cuda11.4 at most, and I cannot update the driver. thank you
Environment
TensorRT Version:
NVIDIA GPU:
NVIDIA Driver Version:
CUDA Version:
CUDNN Version:
Operating System:
Python Version (if applicable):
Tensorflow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if so, version):
Relevant Files
Steps To Reproduce
Description
I want to build a container of Tensorrt 8.4+cuda11.4 according to this tutorial https://github.com/NVIDIA/TensorRT/tree/8.4.1。
Then I get the following error.
Step 19/28 : RUN if [ "${CUDA_VERSION}" = "10.2" ] ; then v="${TRT_VERSION%.}-1+cuda${CUDA_VERSION}" && apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub && apt-get update && sudo apt-get install libnvinfer8=${v} libnvonnxparsers8=${v} libnvparsers8=${v} libnvinfer-plugin8=${v} libnvinfer-dev=${v} libnvonnxparsers-dev=${v} libnvparsers-dev=${v} libnvinfer-plugin-dev=${v} python3-libnvinfer=${v}; else v="${TRT_VERSION%.}-1+cuda${CUDA_VERSION%.}" && apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub && apt-get update && sudo apt-get install libnvinfer8=${v} libnvonnxparsers8=${v} libnvparsers8=${v} libnvinfer-plugin8=${v} libnvinfer-dev=${v} libnvonnxparsers-dev=${v} libnvparsers-dev=${v} libnvinfer-plugin-dev=${v} python3-libnvinfer=${v}; fi
---> Running in 1a2fd308bb55
Warning: apt-key output should not be parsed (stdout is not a terminal)
Executing: /tmp/apt-key-gpghome.0Z4XcLaQfG/gpg.1.sh --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub
gpg: requesting key from 'https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub'
gpg: key A4B469963BF863CC: "cudatools cudatools@nvidia.com" not changed
gpg: Total number processed: 1
gpg: unchanged: 1
Hit:1 http://archive.ubuntu.com/ubuntu focal InRelease
Hit:2 http://security.ubuntu.com/ubuntu focal-security InRelease
Hit:3 http://ppa.launchpad.net/ubuntu-toolchain-r/test/ubuntu focal InRelease
Hit:4 http://archive.ubuntu.com/ubuntu focal-updates InRelease
Hit:5 http://archive.ubuntu.com/ubuntu focal-backports InRelease
Hit:6 https://developer.download.nvidia.cn/compute/cuda/repos/ubuntu2004/x86_64 InRelease
Reading package lists...
Reading package lists...
Building dependency tree...
Reading state information...
E: Version '8.4.1-1+cuda11.4' for 'libnvinfer8' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvonnxparsers8' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvparsers8' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvinfer-plugin8' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvinfer-dev' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvonnxparsers-dev' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvparsers-dev' was not found
E: Version '8.4.1-1+cuda11.4' for 'libnvinfer-plugin-dev' was not found
E: Version '8.4.1-1+cuda11.4' for 'python3-libnvinfer' was not found
The command '/bin/bash -c if [ "${CUDA_VERSION}" = "10.2" ] ; then v="${TRT_VERSION%.}-1+cuda${CUDA_VERSION}" && apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub && apt-get update && sudo apt-get install libnvinfer8=${v} libnvonnxparsers8=${v} libnvparsers8=${v} libnvinfer-plugin8=${v} libnvinfer-dev=${v} libnvonnxparsers-dev=${v} libnvparsers-dev=${v} libnvinfer-plugin-dev=${v} python3-libnvinfer=${v}; else v="${TRT_VERSION%.}-1+cuda${CUDA_VERSION%.}" && apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub && apt-get update && sudo apt-get install libnvinfer8=${v} libnvonnxparsers8=${v} libnvparsers8=${v} libnvinfer-plugin8=${v} libnvinfer-dev=${v} libnvonnxparsers-dev=${v} libnvparsers-dev=${v} libnvinfer-plugin-dev=${v} python3-libnvinfer=${v}; fi' returned a non-zero code: 100
My command is ：./docker/build.sh --file docker/ubuntu-20.04.Dockerfile --tag tensorrt-ubuntu20.04-cuda11.6 --cuda 11.4.2
and it show ：
docker build -f docker/ubuntu-20.04.Dockerfile --build-arg CUDA_VERSION=11.4.2 --build-arg uid=0 --build-arg gid=0 --tag=tensorrt-ubuntu20.04-cuda11.6 .
Does Tensorrt8.4 not support cuda11.4, but only 11.6? The same error occurred when I first used tensor 8.5
Please give me some suggestions. My GPU driver limits me to using cuda11.4 at most, and I cannot update the driver. thank you
Environment
TensorRT Version:
NVIDIA GPU:
NVIDIA Driver Version:
CUDA Version:
CUDNN Version:
Operating System:
Python Version (if applicable):
Tensorflow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if so, version):
Relevant Files
Steps To Reproduce