Converter plugin / LiteRT Converter
Machine Learning Inference Advisor (MLIA)
Bring LiteRT into the flow.
Convert supported TensorFlow Lite models into TOSA-oriented artifacts for downstream MLIA backends.
View on GitHub (opens in a new tab)Converter plugin
Work with LiteRT Converter.
01
Pair with a target plugin
Install a target plugin for the hardware you want to analyze, then add this converter for LiteRT inputs.
Read the guide (opens in a new tab)02Follow the conversion
Trace a .tflite model into the TOSA-oriented path.
Read the guide 03Inspect the artifacts
Understand MLIR text, bytecode, and diagnostics.
Read the guidePart of MLIA
Start with the right setup.
This converter runs within MLIA workflows; it is not a separate analysis command.
Documentation
Find your next step.
Under the hood
Explore the implementation.
Find integration details and contributor guidance.