Github https://github.com/google-ai-edge/LiteRT-CLI
The LiteRT Command Line Interface (CLI) is a convenient toolkit to streamline
LiteRT development workflows. It supports converting,
quantizing, compiling, running, benchmarking, and visualizing LiteRT
(.tflite) models on various hardware (CPU, GPU, NPU) across platforms
(desktop, mobile, or cloud).
Key Capabilities
- Installation: Quick setup using
uvorpip. - Common Commands: Streamlined workflows for
downloading, converting (
PyTorch/Hugging Face), quantizing, AOT compiling, running, benchmarking, and visualizing models. - Troubleshooting & Resources: Verified platforms, Colab notebooks, quick start demos, and common fixes.
To get started, proceed to the Installation guide.