{"id":13438777,"url":"https://github.com/OAID/Tengine","last_synced_at":"2025-03-20T06:31:22.518Z","repository":{"id":37720117,"uuid":"115765590","full_name":"OAID/Tengine","owner":"OAID","description":"Tengine is a lite, high performance, modular inference engine for embedded device ","archived":false,"fork":false,"pushed_at":"2025-03-06T07:12:55.000Z","size":18730,"stargazers_count":4450,"open_issues_count":244,"forks_count":971,"subscribers_count":210,"default_branch":"tengine-lite","last_synced_at":"2025-03-19T10:18:03.145Z","etag":null,"topics":["acl","arm","artificial-intelligence","cnn","container","cuda","machine-learning","mips","npu","nvdla","onnx","pytorch","riscv","supperedge","tensorflow","tensorrt","x86-64"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/OAID.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-12-30T01:21:41.000Z","updated_at":"2025-03-14T15:58:34.000Z","dependencies_parsed_at":"2024-10-27T22:37:16.198Z","dependency_job_id":null,"html_url":"https://github.com/OAID/Tengine","commit_stats":null,"previous_names":[],"tags_count":21,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OAID%2FTengine","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OAID%2FTengine/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OAID%2FTengine/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OAID%2FTengine/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/OAID","download_url":"https://codeload.github.com/OAID/Tengine/tar.gz/refs/heads/tengine-lite","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244422591,"owners_count":20450239,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["acl","arm","artificial-intelligence","cnn","container","cuda","machine-learning","mips","npu","nvdla","onnx","pytorch","riscv","supperedge","tensorflow","tensorrt","x86-64"],"created_at":"2024-07-31T03:01:08.371Z","updated_at":"2025-03-20T06:31:22.483Z","avatar_url":"https://github.com/OAID.png","language":"C++","readme":"\u003cdiv align=\"center\"\u003e\n  \u003cimg width=\"40%\" src=\"logo-Tengine.png\"\u003e\n  \u003ch3\u003e \u003ca href=\"https://tengine-docs.readthedocs.io/en/latest/\"\u003e Documentation \u003c/a\u003e | \u003ca href=\"https://tengine.readthedocs.io/zh_CN/latest/\"\u003e 中文文档 \u003c/a\u003e  \u003c/h3\u003e\n\u003c/div\u003e\n\n简体中文 | [English](./README_EN.md)\n\n# Tengine\n\n[![GitHub license](http://OAID.github.io/pics/apache_2.0.svg)](./LICENSE)\n[![GitHub Workflow Status](https://img.shields.io/github/actions/workflow/status/OAID/Tengine/build-and-test.yml?branch=tengine-lite)](https://github.com/OAID/Tengine/actions)\n[![Test Status](https://img.shields.io/travis/OAID/Tengine/tengine-lite?label=test)](https://travis-ci.org/OAID/Tengine)\n[![codecov](https://codecov.io/gh/OAID/Tengine/branch/tengine-lite/graph/badge.svg?token=kz9NcQPRrk)](https://codecov.io/gh/OAID/Tengine)\n[![Language grade: C/C++](https://img.shields.io/lgtm/grade/cpp/g/OAID/Tengine.svg?logo=lgtm\u0026logoWidth=18)](https://lgtm.com/projects/g/OAID/Tengine/context:cpp)\n\n\n## 简介\n\n**Tengine** 由 **[OPEN AI LAB](http://www.openailab.com)** 主导开发，该项目实现了深度学习神经网络模型在嵌入式设备上的**快速**、**高效**部署需求。为实现在众多 **AIoT** 应用中的跨平台部署，本项目使用 **C 语言**进行核心模块开发，针对嵌入式设备资源有限的特点进行了深度框架裁剪。同时采用了完全分离的前后端设计，有利于 CPU、GPU、NPU 等异构计算单元的快速移植和部署，降低评估、迁移成本。\n\nTengine 核心代码由 4 个模块组成：\n\n- [**device**](source/device)：NN Operators 后端模块，已提供 CPU、GPU、NPU 参考代码；\n- [**scheduler**](source/scheduler)：框架核心部件，包括 NNIR、计算图、硬件资源、模型解析器的调度和执行模块；\n- [**operator**](source/operator)：NN Operators 前端模块，实现 NN Operators 注册、初始化；\n- [**serializer**](source/serializer)：模型解析器，实现 tmfile 格式的网络模型参数解析。\n\n\n## 架构简析\n\n![Tengine 架构](doc/docs_zh/images/architecture.png)\n\n## 快速上手\n\n### 编译\n\n- [快速编译](doc/docs_zh/source_compile) 基于 cmake 实现简单的跨平台编译。\n\n### 示例\n\n- [examples](examples/) 提供基础的分类、检测算法用例，根据 issue 需求持续更新。\n- [源安装](doc/docs_zh/quick_start/apt-get-install_user_manual.md) 提供ubuntu系统的apt-get命令行安装和试用，目前支持x86/A311D硬件。\n\n### 模型仓库\n\n- [百度网盘](https://pan.baidu.com/s/1JsitkY6FVV87Kao6h5yAmg) （提取码：7ke5）\n\n- [Google Drive](https://drive.google.com/drive/folders/1hunePCa0x_R-Txv7kWqgx02uTCH3QWdS?usp=sharing)\n\n### 转换工具\n\n- [预编译版本](https://github.com/OAID/Tengine/releases/download/lite-v1.2/convert_tool.zip) ：提供 Ubuntu 18.04 系统上预编译好的模型转换工具；\n- [在线转换版本](https://convertmodel.com/#outputFormat=tengine) ：基于 WebAssembly 实现（浏览器本地转换，模型不会上传；\n- [源码编译](https://github.com/OAID/Tengine/tree/tengine-lite/tools/convert_tool) ：建议在服务器或者PC上编译，指令如下：\n  ```\n  mkdir build \u0026\u0026 cd build\n  cmake -DTENGINE_BUILD_CONVERT_TOOL=ON ..\n  make -j`nproc`\n  ```\n\n### 量化工具\n\n- [源码编译](tools/quantize/README.md)：已开源量化工具源码，已支持 uint8/int8。\n\n### 速度评估\n\n- [Benchmark](benchmark/) 基础网络速度评估工具，欢迎大家更新。\n\n### NPU Plugin\n\n- [TIM-VX](doc/docs_zh/source_compile/compile_timvx.md) VeriSilicon NPU 使用指南。\n\n### AutoKernel Plugin\n\n- [AutoKernel](https://github.com/OAID/AutoKernel.git) 是一个简单易用，低门槛的自动算子优化工具，AutoKernel Plugin实现了自动优化算子一键部署到 Tengine 中。\n\n### Container\n\n- [SuperEdge](https://github.com/superedge/superedge) 借助 SuperEdge 边缘计算的开源容器管理系统，提供更便捷的业务管理方案；\n- [How to use Tengine with SuperEdge](doc/docs_zh/source_compile/deploy_SuperEdge.md) 容器使用指南；\n- [Video Capture user manual](doc/docs_zh/source_compile/demo_videocapture.md) Demo 依赖文件生成指南。\n\n## Roadmap\n\n- [Road map](doc/docs_zh/introduction/roadmap.md)\n\n## 致谢\n\nTengine Lite 参考和借鉴了下列项目：\n\n- [Caffe](https://github.com/BVLC/caffe)\n- [Tensorflow](https://github.com/tensorflow/tensorflow)\n- [MegEngine](https://github.com/MegEngine/MegEngine)\n- [ONNX](https://github.com/onnx/onnx)\n- [ncnn](https://github.com/Tencent/ncnn)\n- [FeatherCNN](https://github.com/Tencent/FeatherCNN)\n- [MNN](https://github.com/alibaba/MNN)\n- [Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite)\n- [ACL](https://github.com/ARM-software/ComputeLibrary)\n- [stb](https://github.com/nothings/stb)\n- [convertmodel](https://convertmodel.com)\n- [TIM-VX](https://github.com/VeriSilicon/TIM-VX)\n- [SuperEdge](https://github.com/superedge/superedge)\n\n## License\n\n- [Apache 2.0](LICENSE)\n\n## 澄清说明\n\n- [在线上报功能] 在线上报功能主要目的是了解Tengine的使用信息，信息用于优化和迭代Tengine，不会影响任何正常功能。该功能默认开启，如需关闭，可修改如下配置关闭：(主目录 CMakeLists.txt )  OPTION (TENGINE_ONLINE_REPORT \"online report\" OFF)\n\n## FAQ\n\n- [FAQ 常见问题](doc/docs_zh/introduction/faq.md)\n\n## 技术讨论\n\n- Github issues\n- QQ 群: 829565581\n- Email: Support@openailab.com\n","funding_links":[],"categories":["C++","\u003ca name=\"Tools\"\u003e\u003c/a\u003e13. Tools","Inference Engines","General Resources","其他_机器学习与深度学习","Lighter and Deployment Frameworks","PROJECTS","Networks","Libraries","\u003ca name=\"Tools\"\u003e\u003c/a\u003e9. Tools"],"sub_categories":["13.7 Deployment","Tengine","Project:","2023","Inference Framework"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOAID%2FTengine","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FOAID%2FTengine","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOAID%2FTengine/lists"}