For now we plan to follow the NativeApp demo in https://github.com/pytorch/android-demo-app, to support inference on mobile devices. After OPs reduction we still get libpytorch_jni.so with size about 11M for arm64-v8a. So,
- Is it possible to reduce it further? I have tried turned off some cmake options including USE_MKLDNN, but it seems no effect.
- Is there any other clean way to build a c++ dedicated library like libtorch_cpu.so getting rid of jni stuff, to support c++ native linkage.