Here we maintain the list of supported platforms for deployment.
- x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down performance)
- glibc >= 2.24, libstdc++6 >= 6.3
- TensorFlow Lite runtime
- Cortex-A53 compatible ARMv7 SoC with Neon support
- Raspbian Buster-compatible distribution
- TensorFlow Lite runtime
- Cortex-A72 compatible Aarch64 SoC
- ARMbian Buster-compatible distribution
- TensorFlow Lite runtime
- ARMv7 SoC with Neon support
- Android 7.0-10.0
- NDK API level >= 21
- TensorFlow Lite runtime
- Aarch64 SoC
- Android 7.0-10.0
- NDK API level >= 21
- TensorFlow Lite runtime
- x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down performance)
- macOS >= 10.10
- TensorFlow Lite runtime
- x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down performance)
- Windows Server >= 2012 R2 ; Windows >= 8.1
- TensorFlow Lite runtime