Download
LiteRT is an experimental, real-time inference runtime built by Google AI Edge to run lightweight ML models on edge devices with ultra-low latency. It focuses on delivering predictable and consistent performance for models used in time-critical applications like robotics, AR/VR, and IoT. LiteRT is designed to be hardware-agnostic, with minimal dependencies and tight control over execution scheduling.
Features
- Real-time inference execution for edge ML models
- Ultra-low latency and jitter optimization
- Works with small, performance-critical models
- Hardware-agnostic and lightweight runtime
- Deterministic execution with predictable scheduling
- Designed for robotics, AR/VR, and embedded use cases
Project Samples
Categories
Artificial IntelligenceLicense
Apache License V2.0Follow LiteRT
Other Useful Business Software
Go From AI Idea to AI App Fast
Access Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of LiteRT!
