Use LiteRT on Android
Stay organized with collections
Save and categorize content based on your preferences.
LiteRT on Android provides essentials for deploying high performance, custom ML
features into your Android app.
LiteRT for ML runtime
Use LiteRT with Google Play services, Android's official ML inference runtime,
to run high-performance ML inference in your app. Learn more
Hardware Acceleration with LiteRT Delegates
Use LiteRT Delegates distributed using Google Play services to run accelerated
ML on specialized hardware such as GPUs or NPUs. This helps you deliver more
fluid, lower latency user experiences to your users by accessing advanced
on-device compute capabilities.
We provide support for GPU delegates, and we're working with partners
to provide access to their custom delegates using Google Play services to
support advanced use cases. Learn more
Enabled by Google Play services
Use Google Play services to access the LiteRT runtime and delegates. This
ensures use of the latest stable versions while minimizing impact to your app's
binary size. Learn more
Code samples
Review the LiteRT Android code samples and test ML features on your device. Learn more
Get started with LiteRT
Download the example code and get started with LiteRT and Android.
Learn more
Acceleration Service
The Acceleration Service API lets you to safely pick the optimal hardware
acceleration configuration at runtime without having to worry about the
underlying device hardware and drivers. Learn more
Content and code samples on this page are subject to the licenses described in the Content License. Java and OpenJDK are trademarks or registered trademarks of Oracle and/or its affiliates.
Last updated 2024-09-04 UTC.
[[["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complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2024-09-04 UTC."],[],[],null,["# Use LiteRT on Android\n\nLiteRT on Android provides essentials for deploying high performance, custom ML\nfeatures into your Android app.\n\nLiteRT for ML runtime\n---------------------\n\nUse LiteRT with Google Play services, Android's official ML inference runtime,\nto run high-performance ML inference in your app. [Learn more](https://ai.google.dev/edge/lite/android)\n\nHardware Acceleration with LiteRT Delegates\n-------------------------------------------\n\nUse LiteRT Delegates distributed using Google Play services to run accelerated\nML on specialized hardware such as GPUs or NPUs. This helps you deliver more\nfluid, lower latency user experiences to your users by accessing advanced\non-device compute capabilities.\n\nWe provide support for GPU delegates, and we're working with partners\nto provide access to their custom delegates using Google Play services to\nsupport advanced use cases. [Learn more](https://ai.google.dev/edge/lite/android/play_services#hardware-acceleration)\n\nEnabled by Google Play services\n-------------------------------\n\nUse Google Play services to access the LiteRT runtime and delegates. This\nensures use of the latest stable versions while minimizing impact to your app's\nbinary size. [Learn more](https://ai.google.dev/edge/lite/android/play_services)\n\nCode samples\n------------\n\nReview the LiteRT Android code samples and test ML features on your device. [Learn more](https://github.com/tensorflow/examples/tree/master/lite/examples)\n\nGet started with LiteRT\n-----------------------\n\nDownload the example code and get started with LiteRT and Android.\n[Learn more](https://ai.google.dev/edge/lite/android)\n\nAcceleration Service\n--------------------\n\nThe Acceleration Service API lets you to safely pick the optimal hardware\nacceleration configuration at runtime without having to worry about the\nunderlying device hardware and drivers. [Learn more](https://ai.google.dev/edge/lite/android/acceleration_service)"]]
