# google-ai-edge/LiteRT

> LiteRT is Google's on-device runtime for high-performance ML and GenAI deployment on edge platforms, the successor to TensorFlow Lite. It converts models from PyTorch, TensorFlow, and JAX into .tflite or .litertlm format and runs them on CPU, GPU, and NPU.

- Magnitude: 1.4 out of 10 — Quiet
- Stars: 3,437 total · +1 star today, ≈ 2 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: C++ · License: Apache-2.0 · Created: 2024-09-04 · Last push: 2026-09-25
- GitHub: https://github.com/google-ai-edge/LiteRT · Homepage: https://ai.google.dev/edge/litert/next/overview · Page: https://gitnova.dev/en/r/google-ai-edge/LiteRT

## Useful for

- Convert a PyTorch model to .tflite with LiteRT Torch Converter
- Run a quantized LLM on an Android device with NPU acceleration
- Deploy client-side ML inference in the browser via WebGPU and WASM with LiteRT.js

## Why it’s here

- 1 star so far today, about 2 expected by the end of the day.
- GitHub Trending C++ today: #8, +5 stars.
- Recent forks include notable developers: @onuralpszr (805 followers), @Surfndez (380 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 460
- Issues and pull requests: 10,261
- Watchers: 27
- Average over the last week: 3 per day
- Usual pace: 4 per day
- Stars in the last hour (measured): 0
- Latest release: v2.2.0 (2026-08-13)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-08-27 … 2026-09-25: 4, 3, 1, 3, 5, 5, 3, 7, 2, 3, 4, 1, 4, 6, 2, 2, 4, 5, 4, 3, 4, 2, 4, 4, 2, 2, 2, 8, 4, 1

## Spotted in now

- GitHub Trending C++ today: #8, +5 stars

## Similar by description

1. **microsoft/onnxruntime** — 1.3 · Steady · Language models · C++ · +2 stars today, ≈ 4 by evening
   Cross-platform accelerator for ML inference and training. Runs models from PyTorch, TensorFlow, scikit-learn and others via the ONNX format with graph optimizations and hardware acceleration.
   Full card: https://gitnova.dev/en/r/microsoft/onnxruntime.md
2. **openvinotoolkit/openvino** — 1.0 · Steady · Language models · C++ · +1 star today, ≈ 2 by evening
   OpenVINO is an open-source toolkit for optimizing and deploying deep learning model inference on Intel CPU, GPU and NPU. It supports models from PyTorch, TensorFlow, ONNX, Keras, PaddlePaddle, JAX/Flax and Hugging Face with C++, Python, C…
   Full card: https://gitnova.dev/en/r/openvinotoolkit/openvino.md
3. **NVIDIA/TensorRT-LLM** — 1.3 · Steady · Language models · Python · +0 stars today, ≈ 1 by evening
   NVIDIA library for optimizing inference of large language models and visual generative models on GPUs, with a Python API, specialized kernels, and an efficient C++/Python runtime.
   Full card: https://gitnova.dev/en/r/NVIDIA/TensorRT-LLM.md
4. **openxla/xla** — 1.1 · Steady · Language models · C++ · +2 stars today, ≈ 3 by evening
   XLA (Accelerated Linear Algebra) is an open-source ML compiler for GPUs, CPUs, and ML accelerators. It takes models from PyTorch, TensorFlow, and JAX and optimizes them for high-performance execution across different hardware.
   Full card: https://gitnova.dev/en/r/openxla/xla.md
5. **General-Instinct/InstinctFlash** — 2.7 · Early signal · Hardware, IoT & robotics · C++ · +1 star today, ≈ 4 by evening
   A high-performance serving runtime for robotics models (VLA, WAM, policies) with FP8 acceleration and optimized kernels on Jetson Thor and RTX 4090/5090.
   Full card: https://gitnova.dev/en/r/General-Instinct/InstinctFlash.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-25 14:45 UTC, updated every 30 minutes.