google-ai-edge/LiteRT
LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization
C++3.3K stars429 forks+211 today
What it does
LiteRT is Google's high-performance machine learning and generative AI framework for edge devices, offering advanced GPU/NPU acceleration and efficient model deployment.
Star history
Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.
Tracking
- Last trending
- 2026-04-25
Creator kit
Hook
Revolutionize on-device ML with LiteRT! 🚀 #GoogleAI #EdgeComputing
Content angles
- A deep dive into how LiteRT optimizes GPU/NPU acceleration for edge devices.
- Comparing the performance of LiteRT against TensorFlow Lite in real-world scenarios.
- Exploring the new LiteRT Compiled Model API and its benefits for developers.
Who should care
AI researchers, ML engineers, and developers interested in on-device machine learning and generative AI.