apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-08 10:00:29 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
Files
40e080a40cf6b6a42c08e7b9caaaaa627bc69bf5
FastDeploy/serving/docs/zh_CN/compile.md
czr-gc da84da7448 [Serving]: add ipu support for serving. (#10) (#470) 
* feat(ipu): add ipu docker for serving. (#10)

* feat(ipu): add ipu docker for serving.

* feat(ipu): enable ipu docker in serving.

* fix(): fix typo and issues in IPU.

* remove unused env path.

* doc(ipu): add ipu docker build doc and fix typo.

* fix(): clean apt cache in docker.

* fix(ipu): fix typo.
2022-11-02 09:50:58 +08:00

1.2 KiB
Raw Blame History

服务化部署镜像编译

本文档介绍如何制作FastDploy镜像

制作GPU镜像

FastDploy发布的GPU镜像基于Triton Inference Server的21.10版本进行制作，如果有其他CUDA版本需求，可以参照NVIDIA 官网中展示的版本信息修改Dockerfile和scripts中的脚本.

# 进入serving目录执行脚本编译fastdeploy和服务化的backend
cd serving
bash scripts/build.sh

# 退出到FastDeploy主目录，制作镜像
cd ../
docker build -t paddlepaddle/fastdeploy:0.3.0-gpu-cuda11.4-trt8.4-21.10 -f serving/Dockerfile .

制作CPU镜像

# 进入serving目录执行脚本编译fastdeploy和服务化的backend
cd serving
bash scripts/build.sh OFF

# 退出到FastDeploy主目录，制作镜像
cd ../
docker build -t paddlepaddle/fastdeploy:0.3.0-cpu-only-21.10 -f serving/Dockerfile_cpu .

制作IPU镜像

# 进入serving目录执行脚本编译fastdeploy和服务化的backend
cd serving
bash scripts/build_fd_ipu.sh

# 退出到FastDeploy主目录，制作镜像
cd ../
docker build -t paddlepaddle/fastdeploy:0.3.0-ipu-only-21.10 -f serving/Dockerfile_ipu .