Skip to content

Latest commit

 

History

History
78 lines (52 loc) · 4.06 KB

DOCKER_IMAGES.md

File metadata and controls

78 lines (52 loc) · 4.06 KB
Raw

Docker Images

(简体中文|English)

This document maintains a list of docker images provided by Paddle Serving.

Get docker image

You can get images in two ways:

  1. Pull image directly from registry.baidubce.com through TAG:

    docker pull registry.baidubce.com/paddlepaddle/serving:<TAG> # registry.baidubce.com

  2. Building image based on dockerfile

    Create a new folder and copy Dockerfile to this folder, and run the following command:

    docker build -f ${DOCKERFILE} -t <image-name>:<images-tag> .

Image description

Runtime images cannot be used for compilation. If you want to customize your Serving based on source code, use the version with the suffix - devel.

Description OS TAG Dockerfile
CPU development Ubuntu16 latest-devel Dockerfile.devel
GPU (cuda10.1-cudnn7-tensorRT6-gcc54) development Ubuntu16 latest-cuda10.1-cudnn7-gcc54-devel Dockerfile.cuda10.1-cudnn7-gcc54.devel
GPU (cuda10.1-cudnn7-tensorRT6) development Ubuntu16 latest-cuda10.1-cudnn7-devel Dockerfile.cuda10.1-cudnn7.devel
GPU (cuda10.2-cudnn8-tensorRT7) development Ubuntu16 latest-cuda10.2-cudnn8-devel Dockerfile.cuda10.2-cudnn8.devel
GPU (cuda11-cudnn8-tensorRT7) development Ubuntu18 latest-cuda11-cudnn8-devel Dockerfile.cuda11-cudnn8.devel

Java Client:

registry.baidubce.com/paddlepaddle/serving:latest-java

XPU:

registry.baidubce.com/paddlepaddle/serving:xpu-beta

Requirements for running CUDA containers

Running a CUDA container requires a machine with at least one CUDA-capable GPU and a driver compatible with the CUDA toolkit version you are using.

The machine running the CUDA container only requires the NVIDIA driver, the CUDA toolkit does not have to be installed.

For the relationship between CUDA toolkit version, Driver version and GPU architecture, please refer to nvidia-docker wiki.

(Attachment) The List of All the Docker images

Develop Images:

Env Version Docker images tag OS Gcc Version
CPU >=0.5.0 0.6.0-devel Ubuntu 16 8.2.0
<=0.4.0 0.4.0-devel CentOS 7 4.8.5
Cuda10.1 >=0.5.0 0.6.0-cuda10.1-cudnn7-devel Ubuntu 16 8.2.0
0.6.0 0.5.0-cuda10.1-cudnn7-gcc54-devel Ubuntu 16 5.4.0
<=0.4.0 0.6.0-cuda10.1-cudnn7-devel CentOS 7 4.8.5
Cuda10.2 >=0.5.0 0.5.0-cuda10.2-cudnn8-devel Ubuntu 16 8.2.0
<=0.4.0 Nan Nan Nan
Cuda11.0 >=0.5.0 0.6.0-cuda11.0-cudnn8-devel Ubuntu 18 8.2.0
<=0.4.0 Nan Nan Nan

Running Images:

Running Images is lighter than Develop Images, and Running Images are too many due to multiple combinations of python, device environment. If you want to know about it, plese check the document Paddle Serving on Kubernetes..

Tips: If you want to use CPU server and GPU server (version>=0.5.0) at the same time, you should check the gcc version, only Cuda10.1/10.2/11 can run with CPU server owing to the same gcc version(8.2).