国内镜像

https://mirrors.cloud.tencent.com/nvidia-machine-learning/ubuntu1804/x86_64/

检查系统版本
source /etc/os-release && echo $VERSION_ID
导入apt仓库和其GPG key
# 第一步若输出 18.04，请用下面的命令
curl -fsSL https://mirrors.cloud.tencent.com/nvidia-machine-learning/ubuntu1804/x86_64/7fa2af80.pub | apt-key add -
echo "deb https://mirrors.cloud.tencent.com/nvidia-machine-learning/ubuntu1804/x86_64//" > /etc/apt/sources.list.d/cuda.list
安装所需版本的tensorRT
此次参照TensorFlow的官方文档

https://www.tensorflow.org/install/gpu

# 这里以7.1.3版本为例
apt-get install -y --no-install-recommends libnvinfer7=7.1.3-1+cuda11.0 \
    libnvinfer-dev=7.1.3-1+cuda11.0 \
    libnvinfer-plugin7=7.1.3-1+cuda11.0