Google DeepMindLaunchDevelopersOctober 28, 2026

LiteRT in Google Play services adds GPU inference, 1.4x faster

Read original source →developers.googleblog.com

GPU inference via ML Drift runs about 1.4x faster than the legacy GPU delegate, exposed through the new CompiledModel API. Apps switching from bundled LiteRT shrink by roughly 8 MB, with over 100K Android apps still bundling their own copy.

1 source

More stories today

Open the live feed