The Android ecosystem encompasses a wide range of devices with diverse neural processing units (NPUs). Leveraging these specialized NPUs can significantly accelerate LiteRT (TFLite) model inference and reduce energy consumption compared to CPU or GPU execution, enhancing the user experience in your applications.
TFLite delegates are currently under development to allow your app to utilize the specific hardware on each user's device. These delegates will be provided by the chip vendors who manufacture the NPUs.
We look forward to supporting delegates from the following vendors in the coming months:
- Google Pixel
- MediaTek
- Qualcomm
- Samsung System LSI
Stay tuned for updates and further instructions on using these delegates to harness the power of NPUs in your TFLite models.