#litert

[ follow ]
Artificial intelligence
fromInfoQ
1 day ago

Google's New LiteRT Accelerator Supercharges AI Workloads on Snapdragon-powered Android Devices

QNN enables up to 100x CPU and 10x GPU speedups by delegating LiteRT models to NPUs on Snapdragon 8 devices, improving latency and power efficiency.
Artificial intelligence
fromInfoQ
6 months ago

Google Enhances LiteRT for Faster On-Device Inference

LiteRT simplifies on-device ML inference with enhanced GPU and NPU support for faster performance and lower power consumption.
[ Load more ]