Google open-sources ML Drift, a cross-platform on-device GPU inference engine under Apache 2.0
Overview
Google's AI Edge Team has open-sourced ML Drift, a GPU compute engine for on-device AI inference, under the Apache 2.0 license.
According to Google's developer blog, it runs across OpenGL ES, OpenCL, Metal, and WebGPU and serves as the core GPU acceleration engine within LiteRT, succeeding the legacy TFLite GPU delegate, which will no longer receive new features.
Google cites benchmarks showing up to 40% lower frame latency in YouTube Shorts and up to 30% faster on-device performance in Adobe Lightroom and Photoshop; these figures are Google's own claims, not independently verified. For Android developers using unbundled runtimes to minimize app binary size, ML Drift acceleration is available now in standalone LiteRT packages, and Google says it is coming soon to LiteRT in Google Play Services.
Written by AI from the articles below · updated Oct 8, 7:52 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Google Developers BlogPickGoogle open-sources ML Drift, a cross-platform GPU engine for on-device AI
AIGoogle's AI Edge Team open-sourced ML Drift under Apache 2.0, a GPU compute engine for on-device AI inference across OpenGL ES, OpenCL, Metal, and WebGPU. It serves as the core GPU acceleration engine within LiteRT and succeeds the legacy TFLite GPU delegate, which will no longer receive new features. The post cites benchmarks showing up to 40% lower frame latency in YouTube Shorts and up to 30% faster on-device performance in Adobe Lightroom and Photoshop.
Heat trend
Not enough continuous observations to show a trend yet.