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.

Sign up for GitHub

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

Jump to bottom

opt c++ inference code, remove redundant code #1080

Merged
merged 10 commits into from
Mar 18, 2021
Merged

opt c++ inference code, remove redundant code #1080

merged 10 commits into from
Mar 18, 2021

Conversation

zhangjun
Copy link
Collaborator

@zhangjun zhangjun commented Mar 10, 2021 •
edited
Loading

description

c++调用预测库逻辑优化，去除冗余代码

详细如下：

  • 9个EngineCore统一为1个PaddleInferenceEngine，对CPU、GPU、XPU AnalysisConfig逻辑统一处理
    1）去除无用参数DisableGpu
    2）去除未使用参数force_update_static_cache、static_optimization
  • 去除无用InferEngineCreationParams有关代码，直接使用EngineDesc（core/configure/proto/server_configure.proto, 后续对proto统一整合下)
  • AutoLock、GlobalPaddleCreateMutex是InferEngine公用代码，统一移动到infer.h中
  • 修改去掉fluid相关命名

feature：

  • 使用paddle 2.0.1，修改paddle_fluid.a为paddle_inference.a
  • paddle-lite打通，使用最新v2.8分支，支持x86、arm，baidu kunlun xpu部署优化
  • 模型加密功能优化完善

@paddle-bot-old
Copy link

Thanks for your contribution!

@zhangjun zhangjun changed the title [wip] opt c++ inference code, remove redundant code opt c++ inference code, remove redundant code Mar 17, 2021
@TeslaZhao TeslaZhao requested a review from bjjwwang March 17, 2021 11:24
@TeslaZhao TeslaZhao merged commit adccfda into PaddlePaddle:develop Mar 18, 2021
@zhangjun zhangjun deleted the infer branch April 28, 2021 11:34
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@bjjwwang bjjwwang Awaiting requested review from bjjwwang

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@zhangjun @TeslaZhao