Google Enhances LiteRT for Faster On-Device Inference
The new release of LiteRT, formerly known as TensorFlow Lite, introduces a new API to simplify on-device ML inference, enhanced GPU acceleration, support for Qualcomm NPU (Neural Processing Unit) accelerators, and advanced inference features.
Gemma 3n Available for On-Device Inference Alongside RAG and Function Calling Libraries
Google has announced that Gemma 3n is now available in preview on the new LiteRT Hugging Face community, alongside many previously released models. Gemma 3n is a multimodal small language model that supports text, image, video, and audio inputs. It also supports finetuning, customization through retrieval-augmented generation (RAG), and function calling using new AI Edge SDKs.
Google Brings Gemini Nano to ML Kit with New On-Device GenAI APIs
The new GenAI APIs recently added to ML Kit enable developers to use Gemini Nano for on-device inference in Android apps, supporting features like summarization, proofreading, rewriting, and image description.
How Tripadvisor Migrated to The Composable Architecture for Their SwiftUI App
In a thourough article, Tripadvisor iOS principal engineer Ben Sarrazin described their journey toward adopting The Composable Architecture (TCA) for their existing iOS app, moving away from the Model-View-ViewModel-Coordinator (MVVM-C) architecture.