// AI news · 2026-10-28 · Google AI Changelog
Google launches LiteRT for faster Android inference
Google introduces LiteRT in Play Services for faster on-device ML inference, with up to 1.4x GPU speed improvement via ML Drift and CompiledModel API.
Published 2026-10-28 08:00 (Beijing time)Source Google AI ChangelogAuto-summarised, fact-checked against source
01Summary
Apps reduce size by ~8 MB as the runtime is now bundled in Play Services. Support spans Android 7+, Wear OS 4+, and Android Automotive OS. The runtime enables cross-platform execution and maintains backward compatibility with legacy CPU inference.
Summarised from the original article by an open-source model, then checked automatically: every number and English name must appear in the source. The original article is authoritative.
02Key points
- GPU inference speeds up by ~1.4x using ML Drift and CompiledModel API.
- App size reduced by ~8 MB as LiteRT is now provided via Play Services.
- Supports Android 7+, Wear OS 4+, and Android Automotive OS (Android 11+).
- Maintains backward compatibility with legacy Interpreter API for CPU inference.
03Source
Smaller apps and faster GPU inference with LiteRT in Google Play services
Google AI Changelog · published 2026-10-28 08:00 Beijing time
05Related news
- Google releases Agents CLI eval loop for agent quality hill-climbing2026-10-28 · Google AI Changelog
- Gemini Notebook adds built-in audio recorder to Android and iOS2026-10-28 · 9to5Google
- Oracle AI Database@Google Cloud Adds Gemini Integration and Agentic Capabilities2026-10-28 · Google Cloud
- Google proposes 'sleep framework' for LLM continual learning2026-10-28 · Google Research Blog
- Eight Examples of Gemini 4 Argon in Action2026-10-27 · Google Gemini
- Gemini Robotics ER 2 Now Available on Google Cloud2026-10-27 · Google Cloud AI/ML
From AIMap AI news: collected from 1,100+ official and media sources. Summaries only restate the original article; follow the link for the full story. All AI news · Today