Hover any photo on any page — it turns 3D. Depth is computed in your browser, on your GPU: MoGe-2 on LiteRT.js (WebGPU), ~70 ms per image.
No server, no upload — images never leave your device.
code: https://t.co/sKGxN4xusI
model: https://t.co/TXDSmhUP9M
Hold Shift — your cursor becomes a flashlight. Any photo, any page, relit live on your GPU. MoGe-2 on LiteRT.js (WebGPU) returns normals with depth: zero extra inference. Images never leave your device.
code: https://t.co/sKGxN4xusI
model: https://t.co/TXDSmhUP9M
Gemma 4 E2B goes super fast on Intel AI PCs thanks to LiteRT NPU support on OpenVINO!
⚡1.3x faster prefill performance over GPU
📈2.8x improvement in performance-per-watt
🔋Runs background LLM tasks with zero thermal throttling or heavy battery drain
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 facial animation on Android
🔷 Argmax: 2x speedup in speech-to-text with industry-leading latency
🔷 Google AI Edge Portal: cross-device benchmarking with NPU support
Explore how it works → https://t.co/4WgfzvuviQ
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://t.co/AC4jUpdxRo