Build an Android chat application with ONNX Runtime API
Introduction
Create a development environment
Build ONNX Runtime
Build ONNX Runtime Generate() API
Run a benchmark on an Android phone
Build and run an Android chat app
Review
Next Steps

  Log an issue

  Fork and edit

  Discuss on Discord

Cross-compile the ONNX Runtime Generate() API for Android CPU

The Generate() API in ONNX Runtime is designed for text generation tasks using models like Phi-3. It implements the generative AI loop for ONNX models, including:

  • pre- and post-processing
  • inference with ONNX Runtime
  • logits processing
  • search and sampling
  • KV cache management. You can learn more by reading the ONNX Runtime generate() API page .

Clone onnxruntime-genai repo

Within your Windows PowerShell prompt, checkout the source repo:

    

        
        
            C:\Users\$env:USERNAME
git clone https://github.com/microsoft/onnxruntime-genai
cd onnxruntime-genai
git checkout 1e4d289502a61265c3b07efb17d8796225bb0b7f
Note

You might be able to use later commits. These steps have been tested with the commit 1e4d289502a61265c3b07efb17d8796225bb0b7f.

Build for Android CPU

Ninja generator is used to build on Windows for Android. Make sure you have set JAVA_HOME before running the following command:

    

        
        
            python -m pip install requests 
python3.11 build.py --build_java --android --android_home C:\Users\$env:USERNAME\AppData\Local\Android\Sdk --android_ndk_path C:\Users\$env:USERNAME\AppData\Local\Android\Sdk\ndk\27.0.12077973 --android_abi arm64-v8a --config Release

When the build is complete, confirm the shared library has been created:

    

        
        ls build\Android\Release\onnxruntime-genai.so
Back
Next