mnn-llm

mnn-llm

1,614 Stars // C++ // 2‏/3‏/2026

mnn-llm is a high-quality open-source project making waves in the tech community. Whether you are exploring Artificial Intelligence, East Asian tech innovations, or advanced software architecture, this guide covers everything you need to know about this repository.

mnn-llm AI Technology - mnn-llm

mnn-llm

mnn-llm AI Technology - License mnn-llm AI Technology - Download mnn-llm AI Technology - Documentation Status

English

该项目代码已经Merge到MNN.

示例工程

  • cli: 使用命令行编译,android编译参考android_build.sh
  • web: 使用命令行编译,运行时需要指定web资源
  • android: 使用Android Studio打开编译;
  • ios: 使用Xcode打开编译;🚀🚀🚀该示例代码100%由ChatGPT生成🚀🚀🚀
  • python: 对mnn-llm的python封装mnnllm
  • other: 新增文本embedding;

模型导出与下载

llm模型导出onnxmnn模型请使用llm-export

模型下载

构建

CI构建状态:

mnn-llm AI Technology - Build Status mnn-llm AI Technology - Build Status mnn-llm AI Technology - Build Status mnn-llm AI Technology - Build Status mnn-llm AI Technology - Build Status mnn-llm AI Technology - Build Status

本地编译

# clone
git clone --recurse-submodules https://github.com/wangzhaode/mnn-llm.git
cd mnn-llm

# linux
./script/build.sh

# macos
./script/build.sh

# windows msvc
./script/build.ps1

# python wheel
./script/py_build.sh

# android
./script/android_build.sh

# android apk
./script/android_app_build.sh

# ios
./script/ios_build.sh

一些编译宏:

  • BUILD_FOR_ANDROID: 编译到Android设备;
  • LLM_SUPPORT_VISION: 是否支持视觉处理能力;
  • DUMP_PROFILE_INFO: 每次对话后dump出性能数据到命令行中;

默认使用CPU,如果使用其他后端或能力,可以在编译MNN时添加MNN编译宏

  • cuda: -DMNN_CUDA=ON
  • opencl: -DMNN_OPENCL=ON
  • metal: -DMNN_METAL=ON

4. 执行

# linux/macos
./cli_demo ./Qwen2-1.5B-Instruct-MNN/config.json # cli demo
./web_demo ./Qwen2-1.5B-Instruct-MNN/config.json ../web # web ui demo

# windows
.\Debug\cli_demo.exe ./Qwen2-1.5B-Instruct-MNN/config.json
.\Debug\web_demo.exe ./Qwen2-1.5B-Instruct-MNN/config.json ../web

# android
adb push android_build/MNN/OFF/arm64-v8a/libMNN.so /data/local/tmp
adb push android_build/MNN/express/OFF/arm64-v8a/libMNN_Express.so /data/local/tmp
adb push android_build/libllm.so android_build/cli_demo /data/local/tmp
adb push Qwen2-1.5B-Instruct-MNN /data/local/tmp
adb shell "cd /data/local/tmp && export LD_LIBRARY_PATH=. && ./cli_demo ./Qwen2-1.5B-Instruct-MNN/config.json"

Reference

reference

Ready to dive deeper?

Explore the source code, contribute, or implement this high-quality solution in your next project:

View on GitHub

Related Topics:

#Artificial Intelligence #Machine Learning #Deep Learning #East Asia Tech #China AI Development #Open Source #GitHub Repositories #Large Language Models #Neural Networks #Tech Innovation