Google Launches LiteRT Tensor API for Building, Customizing, and Optimizing ML Models for On-Device

By Sergio De Simone · InfoQ · Tuesday, 3 November 2026 at 19:00 (7h ago) · Original article ↗

Google has introduced the LiteRT Tensor API, a lightweight C++ API that allows developers to build, customize, and optimize machine learning models directly for on-device execution. According to Google, it combines the flexibility of native model authoring with cross-platform portability.

You're reading a preview. The full article is published by InfoQ on their website.

Read the full story on InfoQ

Dev

Microsoft improves Windows 11 performance on 8 GB PCs as RAM prices keep climbing

We've got a hunch the memory crunch is taking a bite out of Windows revenue

The Register 4h ago

Dev

Xcode 27.3 adds GitHub Copilot to its built-in coding assistant

Apple released Xcode 27.3 beta 1 today with multiple new features, chief among them an expansion of its built-in coding assistant to support GitHub Copilot. Here are the details. more…

9to5Mac 5h ago

Dev

GSMA warns of growing risks to mobile networks from extreme weather

Mobile comms body wants a joined-up approach from governments and regulators to mitigate downtime

The Register 8h ago

Google Launches LiteRT Tensor API for Building, Customizing, and Optimizing ML Models for On-Device

More Software & Development

Microsoft improves Windows 11 performance on 8 GB PCs as RAM prices keep climbing

Xcode 27.3 adds GitHub Copilot to its built-in coding assistant

GSMA warns of growing risks to mobile networks from extreme weather