Docker_Images_EN.md 5.2 KB
Newer Older
B
barrierye 已提交
1 2
# Docker Images

T
TeslaZhao 已提交
3
([简体中文](Docker_Images_CN.md)|English)
B
barrierye 已提交
4 5 6 7 8 9 10

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

## Get docker image

You can get images in two ways:

B
bjjwwang 已提交
11
1. Pull image directly from dockerhub or `registry.baidubce.com ` through TAG:
B
barrierye 已提交
12 13

   ```shell
T
TeslaZhao 已提交
14
   docker pull registry.baidubce.com/paddlepaddle/serving:<TAG> 
B
barrierye 已提交
15 16 17 18 19 20 21
   ```

2. Building image based on dockerfile

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

   ```shell
B
bjjwwang 已提交
22
   docker build -f tools/${DOCKERFILE} -t <image-name>:<images-tag> .
B
barrierye 已提交
23 24
   ```

B
barrierye 已提交
25

B
barrierye 已提交
26

B
barrierye 已提交
27 28
## Image description

J
Jiawei Wang 已提交
29
If you want to customize your Serving based on source code, use the version with the suffix - devel.
B
barrierye 已提交
30

B
bjjwwang 已提交
31 32
**cuda10.1-cudnn7-gcc54 image is not ready, you should run from dockerfile if you need it.**

B
bjjwwang 已提交
33
If you need to develop and compile based on the source code, please use the version with the suffix -devel.
T
TeslaZhao 已提交
34
**In the TAG column, 0.8.0 can also be replaced with the corresponding version number, such as 0.5.0/0.4.1, etc., but it should be noted that some development environments only increase with a certain version iteration, so not all environments All have the corresponding version number can be used.**
B
bjjwwang 已提交
35 36

|                         Description                         |   OS    |             TAG              |                          Dockerfile                          |
B
fix doc  
barrierye 已提交
37
| :----------------------------------------------------------: | :-----: | :--------------------------: | :----------------------------------------------------------: |
T
TeslaZhao 已提交
38 39 40 41 42 43
|                       CPU development                        | Ubuntu16 |         0.8.0-devel         |        [Dockerfile.devel](../tools/Dockerfile.devel)         |
|              GPU (cuda10.1-cudnn7-tensorRT6-gcc54) development               | Ubuntu16 | 0.8.0-cuda10.1-cudnn7-gcc54-devel (not ready) | [Dockerfile.cuda10.1-cudnn7-gcc54.devel](../tools/Dockerfile.cuda10.1-cudnn7-gcc54.devel) |
|              GPU (cuda10.1-cudnn7-tensorRT6) development               | Ubuntu16 | 0.8.0-cuda10.1-cudnn7-devel | [Dockerfile.cuda10.1-cudnn7.devel](../tools/Dockerfile.cuda10.1-cudnn7.devel) |
|              GPU (cuda10.2-cudnn7-tensorRT6) development               | Ubuntu16 | 0.8.0-cuda10.2-cudnn7-devel | [Dockerfile.cuda10.2-cudnn7.devel](../tools/Dockerfile.cuda10.2-cudnn7.devel) |
|              GPU (cuda10.2-cudnn8-tensorRT7) development               | Ubuntu16 | 0.8.0-cuda10.2-cudnn8-devel | [Dockerfile.cuda10.2-cudnn8.devel](../tools/Dockerfile.cuda10.2-cudnn8.devel) |
|              GPU (cuda11.2-cudnn8-tensorRT8) development               | Ubuntu16 | 0.8.0-cuda11.2-cudnn8-devel | [Dockerfile.cuda11.2-cudnn8.devel](../tools/Dockerfile.cuda11.2-cudnn8.devel) |
B
barrierye 已提交
44

W
wangjiawei04 已提交
45 46
**Java Client:**
```
T
TeslaZhao 已提交
47
registry.baidubce.com/paddlepaddle/serving:0.8.0-cuda10.2-java
W
wangjiawei04 已提交
48 49 50 51
```

**XPU:**
```
J
Jiawei Wang 已提交
52 53
registry.baidubce.com/paddlepaddle/serving:xpu-arm # for arm xpu user
registry.baidubce.com/paddlepaddle/serving:xpu-x86 # for x86 xpu user
W
wangjiawei04 已提交
54
```
B
barrierye 已提交
55 56 57 58 59

## 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. 

W
wangjiawei04 已提交
60
The machine running the CUDA container **only requires the NVIDIA driver**, the CUDA toolkit does not have to be installed.
B
barrierye 已提交
61 62

For the relationship between CUDA toolkit version, Driver version and GPU architecture, please refer to [nvidia-docker wiki](https://github.com/NVIDIA/nvidia-docker/wiki/CUDA).
W
wangjiawei04 已提交
63 64 65 66 67 68 69

# (Attachment) The List of All the Docker images

Develop Images:

| Env      | Version | Docker images tag            | OS        | Gcc Version |
|----------|---------|------------------------------|-----------|-------------|
T
TeslaZhao 已提交
70
|    CPU   | >=0.5.0 | 0.8.0-devel                 | Ubuntu 16 |  8.2.0       |
W
wangjiawei04 已提交
71
|          | <=0.4.0 | 0.4.0-devel                  | CentOS 7  | 4.8.5       |
T
TeslaZhao 已提交
72
| Cuda10.1 | >=0.5.0 | 0.8.0-cuda10.1-cudnn7-devel  | Ubuntu 16 |   8.2.0       |
B
bjjwwang 已提交
73
|          | <=0.4.0 | 0.4.0-cuda10.1-cudnn7-devel    | CentOS 7  | 4.8.5     |
T
TeslaZhao 已提交
74
| Cuda10.2+Cudnn7 | >=0.5.0 | 0.8.0-cuda10.2-cudnn7-devel  | Ubuntu 16 |   8.2.0       |
B
bjjwwang 已提交
75
|          | <=0.4.0 | Nan                          | Nan       | Nan         |
T
TeslaZhao 已提交
76
| Cuda10.2+Cudnn8 | >=0.5.0 | 0.8.0-cuda10.2-cudnn8-devel  | Ubuntu 16 |   8.2.0       |
W
wangjiawei04 已提交
77
|          | <=0.4.0 | Nan                          | Nan       | Nan         |
T
TeslaZhao 已提交
78
| Cuda11.2 | >=0.5.0 | 0.8.0-cuda11.2-cudnn8-devel | Ubuntu 16 |    8.2.0       |
W
wangjiawei04 已提交
79 80
|          | <=0.4.0 | Nan                          | Nan       | Nan         |

B
bjjwwang 已提交
81

W
wangjiawei04 已提交
82 83
Running Images:

T
TeslaZhao 已提交
84
Running Images is lighter than Develop Images, and Running Images are made up with serving whl and bin, but without develop tools like cmake because of lower image size. If you want to know about it, plese check the document [Paddle Serving on Kubernetes](./Run_On_Kubernetes_CN.md).
B
bjjwwang 已提交
85

S
ShiningZhang 已提交
86 87 88 89 90 91
| Env      | Version | Docker images tag            | OS        | Gcc Version | Size |
|----------|---------|------------------------------|-----------|-------------|------|
|    CPU   | 0.8.0 | 0.8.0-runtime                 | Ubuntu 16 |  8.2.0       | 3.9 GB |
| Cuda10.1 | 0.8.0 | 0.8.0-cuda10.1-cudnn7-runtime  | Ubuntu 16 |   8.2.0       | 10 GB |
| Cuda10.2 | 0.8.0 | 0.8.0-cuda10.2-cudnn8-runtime  | Ubuntu 16 |   8.2.0       | 10.1 GB |
| Cuda11.2 | 0.8.0 | 0.8.0-cuda11.2-cudnn8-runtime| Ubuntu 16 |    8.2.0       | 14.2 GB |