Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How to customize the dependency environment of FastDeploy #965

Closed
geekchen007 opened this issue Dec 25, 2022 · 3 comments
Closed

How to customize the dependency environment of FastDeploy #965

geekchen007 opened this issue Dec 25, 2022 · 3 comments

Comments

@geekchen007
Copy link

geekchen007 commented Dec 25, 2022

问题描述

FastDeploy是一个很优秀的部署工具,在使用过程中对比之前的依赖管理,有以下疑问:
1)之前的部署策略是依赖的后端用什么,依赖环境就装什么。比如单独装onnx。但是现在fastdeploy“支持CPU和Nvidia GPU的部署,默认集成Paddle Inference、ONNX Runtime、OpenVINO以及TensorRT推理后端,Vision视觉模型模块,Text文本NLP模型模块”,这在测试开发阶段很方便,但是实际部署后,是否存在依赖环境冗余?

2)默认集成Paddle Inference、ONNX Runtime、OpenVINO以及TensorRT推理后端,Vision视觉模型模块,Text文本NLP模型模块的相关代码可以定制化裁剪吗?

参考依赖说明
https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install/download_prebuilt_libraries.md#1

image

@geekchen007 geekchen007 changed the title FastDeploy的依赖环境是否存在冗余? FastDeploy的依赖环境怎样定制化裁剪 Dec 25, 2022
@geekchen007
Copy link
Author

相关代码在这FastDeploy/build_gpu.sh at develop · PaddlePaddle/FastDeploy
https://github.com/PaddlePaddle/FastDeploy/blob/develop/python/scripts/build_gpu.sh

export ENABLE_ORT_BACKEND=ON
export ENABLE_OPENVINO_BACKEND=ON
export ENABLE_PADDLE_BACKEND=ON
export ENABLE_TRT_BACKEND=ON
export TRT_DIRECTORY=/fastdeploy/libs/TensorRT-8.4.1.5
export CUDA_DIRECTORY=/usr/local/cuda
export ENABLE_VISION=ON
export WITH_GPU=ON
export CMAKE_CXX_COMPILER=/usr/local/gcc-8.2/bin/g++

@geekchen007 geekchen007 changed the title FastDeploy的依赖环境怎样定制化裁剪 怎样对FastDeploy的依赖环境定制化裁剪? Dec 25, 2022
@jiangjiajun
Copy link
Collaborator

相关代码在这FastDeploy/build_gpu.sh at develop · PaddlePaddle/FastDeploy https://github.com/PaddlePaddle/FastDeploy/blob/develop/python/scripts/build_gpu.sh

export ENABLE_ORT_BACKEND=ON
export ENABLE_OPENVINO_BACKEND=ON
export ENABLE_PADDLE_BACKEND=ON
export ENABLE_TRT_BACKEND=ON
export TRT_DIRECTORY=/fastdeploy/libs/TensorRT-8.4.1.5
export CUDA_DIRECTORY=/usr/local/cuda
export ENABLE_VISION=ON
export WITH_GPU=ON
export CMAKE_CXX_COMPILER=/usr/local/gcc-8.2/bin/g++

对的,可在这里自行根据选择编译

@geekchen007 geekchen007 changed the title 怎样对FastDeploy的依赖环境定制化裁剪? How to customize the dependency environment of FastDeploy Jan 9, 2023
@jiangjiajun
Copy link
Collaborator

此ISSUE由于一年未更新,将会关闭处理,如有需要,可再次更新打开。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants