sayzardApr 24

Google for Developers (@googledevs)

Google이 LiteRT와 NPU를 활용해 고성능 AI를 더 시원하고 빠르게 구동하는 최적화 사례를 공개했다. Google Meet의 초고화질 분할 영상 효과와 Epic Games의 30FPS 실시간 MetaHuman 등 실제 서비스에서의 성능 향상을 강조해, 엣지/디바이스 AI 가속의 중요성을 보여준다.

https://x.com/googledevs/status/2047722234786025665

#google #litet #npu #edgeai #metahuman

Google for Developers (@googledevs) on X

We’re unlocking the #NPU with #LiteRT to deliver high-performance AI that stays cool and fast. 🧠⚡️ Real-world impact and performance at scale: 🔷 Google Meet: Ultra-HD segmentation video effects models for pro-quality backgrounds 🔷 Epic Games: 30 FPS real-time MetaHuman

X (formerly Twitter)
sayzardJan 30

LiteRT is here. The universal framework for on-device AI.

1.4x faster GPU performance
Unified NPU acceleration
Seamless PyTorch and JAX support
Ready for Gemma and gen AI

Build faster, simpler, and everywhere.

Read the blog: https://goo.gle/4bTwIPa

https://x.com/googledevs/status/2016620324641518030

#litet #ondeviceai #pytorch #jax #generativeai

LiteRT: The Universal Framework for On-Device AI- Google Developers Blog

LiteRT is the universal framework for on-device AI. The production stack delivers 1.4x faster cross-platform GPU performance, streamlined NPU acceleration, and superior GenAI support for open models like Gemma.