# LiteRT | google-ai-edge | Knowledge Base | Instagit

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

GitHub Stars: 1.8k

Repository: https://github.com/google-ai-edge/LiteRT

---

## Articles

### [LiteRT Security Features: Defense-in-Depth for On-Device Machine Learning](/google-ai-edge/LiteRT/what-kind-of-security-features-does-litect-offer)

Explore LiteRT security features including defense-in-depth, sandboxing for untrusted models, and strict input validation for on-device ML. Protect your applications effectively.

- Tags: deep-dive
- Published: 2026-03-13

### [How to Optimize Model Size with LiteRT: Quantization and External Weights Explained](/google-ai-edge/LiteRT/how-to-optimize-model-size-with-litect)

Optimize model size with LiteRT using quantization and external weights. Reduce footprints up to 4x or separate large weights from metadata.

- Tags: how-to-guide
- Published: 2026-03-13

### [LiteRT Ecosystem Tools: Complete Guide to Command-Line Utilities for Model Deployment](/google-ai-edge/LiteRT/what-tools-are-part-of-the-litect-ecosystem)

Explore the LiteRT ecosystem and its 13 command-line tools for deploying, analyzing, and debugging TensorFlow Lite models on CPU, GPU, and NPU hardware. Get started with google-ai-edge/LiteRT today.

- Tags: deep-dive
- Published: 2026-03-13

### [LiteRT Usage Examples: Complete Guide to On-Device Inference](/google-ai-edge/LiteRT/where-can-i-find-examples-of-litect-usage)

Explore LiteRT usage examples in the official repository including interpreter demos and CompiledModel API implementations for on-device inference on hardware accelerators.

- Tags: tutorial
- Published: 2026-03-13

### [How to Contribute to the LiteRT Project: A Complete Developer Guide](/google-ai-edge/LiteRT/how-to-contribute-to-the-litect-project)

Learn how to contribute to the LiteRT project by following this developer guide. Sign the CLA, fork the repo, build locally, and submit your PR for our AI edge computing project.

- Tags: how-to-guide
- Published: 2026-03-13

### [LiteRT Known Issues and Limitations: Critical Constraints for Edge AI Deployment](/google-ai-edge/LiteRT/what-are-the-known-issues-or-limitations-of-litect)

Discover LiteRT known issues and limitations including stateless LSTM support, GPU operator whitelists, and NPU API version matching. Optimize your edge AI deployment.

- Tags: deep-dive
- Published: 2026-03-13

### [How to Debug Applications Using LiteRT: A Complete Guide](/google-ai-edge/LiteRT/how-to-debug-applications-using-litect)

Learn how to debug applications with LiteRT. This guide details using command-line tools and the LiteRtProfilerT API to inspect tensors, find errors, and profile performance across CPU, GPU, and NPU.

- Tags: how-to-guide
- Published: 2026-03-13

### [Does LiteRT Support On-Device Training? Current Capabilities and Future Roadmap](/google-ai-edge/LiteRT/does-litect-support-on-device-training)

LiteRT currently offers inference-only runtime. Discover its capabilities and explore the planned roadmap for future on-device training support in this technical overview.

- Tags: deep-dive
- Published: 2026-03-13

### [LiteRT Performance Benchmarks: Measuring Latency, Memory, and Throughput](/google-ai-edge/LiteRT/what-are-the-performance-benchmarks-for-litect)

Discover LiteRT performance benchmarks. Measure latency memory footprint and throughput of TensorFlow Lite models with LiteRTs C++ benchmark tool. Optimize your edge AI performance now.

- Tags: performance
- Published: 2026-03-13

### [How to Compile LiteRT from Source: Docker, CMake, and Bazel Guide](/google-ai-edge/LiteRT/how-to-compile-litect)

Compile LiteRT from source using Docker, CMake, or Bazel. Follow our guide for reproducible containerized builds and cross-compilation for Android. Get started easily.

- Tags: how-to-guide
- Published: 2026-03-13

### [Hardware Platforms Supported by LiteRT: CPU, GPU, and NPU Coverage](/google-ai-edge/LiteRT/what-hardware-platforms-are-supported-by-litect)

Explore LiteRT hardware support including CPU GPU and NPU acceleration across Android iOS Linux macOS Windows Web and IoT devices optimizing on-device ML inference.

- Tags: api-reference
- Published: 2026-03-13

### [Can LiteRT Be Used for Real-Time AI Applications? Architecture and Implementation Guide](/google-ai-edge/LiteRT/can-litect-be-used-for-real-time-ai-applications)

Explore LiteRT for real-time AI applications. Discover how its architecture delivers sub-30ms inference on edge devices with asynchronous acceleration and efficient memory management.

- Tags: architecture
- Published: 2026-03-13

### [How LiteRT Optimizes AI Models for Edge Devices](/google-ai-edge/LiteRT/how-does-litect-optimize-ai-models-for-edge-devices)

Discover how LiteRT optimizes AI models for edge devices by converting TensorFlow Lite models into efficient integer formats. Reduce latency and memory use for CPU, GPU, and NPU.

- Tags: deep-dive
- Published: 2026-03-13

### [What Types of AI Models Can LiteRT Run? A Complete Guide to On-Device AI](/google-ai-edge/LiteRT/what-kind-of-ai-models-can-litect-run)

Explore the AI models LiteRT supports. Run TensorFlow Lite models for vision, NLP, audio, generative AI and more on optimized hardware accelerators like CPU, GPU, NPU.

- Tags: deep-dive
- Published: 2026-03-13

### [LiteRT Prerequisites: Complete Setup Guide for Linux, macOS, and Windows](/google-ai-edge/LiteRT/are-there-any-prerequisites-for-litect)

Discover LiteRT prerequisites for effortless setup across Linux macOS and Windows. Get started with Docker or platform specific toolchains today.

- Tags: getting-started
- Published: 2026-03-13

### [How to Install LiteRT: Complete Setup Guide for Docker, Bazel, and CMake](/google-ai-edge/LiteRT/how-to-install-litect)

Install LiteRT quickly using Docker, Bazel, or CMake. Follow our complete setup guide for the fastest Docker build with a single script.

- Tags: how-to-guide
- Published: 2026-03-13

### [LiteRT Programming Languages: Complete Guide to Multi-Language Inference](/google-ai-edge/LiteRT/what-programming-languages-does-litect-support)

Explore LiteRT programming languages like C C++ Python JS Kotlin Java and Swift for seamless cross-platform on-device ML inference Unlock powerful AI capabilities.

- Tags: tutorial
- Published: 2026-03-13

### [Main Features of LiteRT: On-Device AI Runtime Capabilities](/google-ai-edge/LiteRT/what-are-the-main-features-of-litect)

Explore LiteRTs key features for on-device AI. Discover GPU/NPU acceleration, compiled model API, dynamic tensor resizing, and generative AI optimizations for high-performance ML.

- Tags: deep-dive
- Published: 2026-03-13

### [How to Get Started with LiteRT: A Complete Guide to On-Device AI Inference](/google-ai-edge/LiteRT/how-to-get-started-with-litect)

Get started with LiteRT, Google's open-source framework for fast on-device AI inference. Optimize TensorFlow Lite models for CPUs, GPUs, and NPUs with this complete guide.

- Tags: getting-started
- Published: 2026-03-13

### [Where to Find the LiteRT Repository: Official GitHub Location and Source Structure](/google-ai-edge/LiteRT/where-can-i-find-the-litect-repository)

Locate the LiteRT repository on GitHub. Access the full source code for Google's lightweight ML runtime, including build configurations, at google-ai-edge/LiteRT.

- Tags: getting-started
- Published: 2026-03-13

### [What Is LiteRT For: Google's On-Device ML and GenAI Inference Framework](/google-ai-edge/LiteRT/what-is-litect-for)

Discover LiteRT, Google's high-performance runtime for deploying ML and GenAI on edge devices. Its unified C++ API supports cross-platform hardware acceleration.

- Tags: getting-started
- Published: 2026-03-13