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.
Chip vendors who manufacture NPUs provide LiteRT delegates to allow your app to
use their specific hardware on each user's device.
Qualcomm® AI Engine Direct Delegate
The Qualcomm® AI Engine Direct Delegate enables users to run LiteRT models using
the AI Engine Direct runtime. The delegate is backed by Qualcomm's Neural
Network API.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-06-18 UTC."],[],[],null,["The Android ecosystem encompasses a wide range of devices with diverse neural\nprocessing units (NPUs). Leveraging these specialized NPUs can significantly\naccelerate LiteRT (TFLite) model inference and reduce energy consumption\ncompared to CPU or GPU execution, enhancing the user experience in your\napplications.\n\nChip vendors who manufacture NPUs provide LiteRT delegates to allow your app to\nuse their specific hardware on each user's device.\n\nQualcomm® AI Engine Direct Delegate\n\nThe Qualcomm® AI Engine Direct Delegate enables users to run LiteRT models using\nthe [AI Engine Direct runtime](https://www.qualcomm.com/developer/software/qualcomm-ai-engine-direct-sdk). The delegate is backed by Qualcomm's Neural\nNetwork API.\n\nThe Qualcomm® AI Engine Direct Delegate is available on [Maven Central](https://central.sonatype.com/artifact/com.qualcomm.qti/qnn-litert-delegate). For\nmore information, see the [Qualcomm Neural Network documentation](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/tflite_delegate.html).\n\nComing soon\n\nWe look forward to supporting delegates from the following vendors in the coming\nmonths:\n\n- Google Pixel\n- MediaTek\n- Samsung System LSI\n\nStay tuned for updates and further instructions on using these delegates to\nharness the power of NPUs in your TFLite models."]]
