Module runtime 

Generic inference runtime for edge computing

This module provides a generic interface for running inference on various deep learning models using different backends.

Modules

onnx

ONNX Runtime backend for liquid-edge inference

Structs

InferenceInput

Generic input for inference operations

InferenceOutput

Generic output from inference operations

InferenceRuntime

Main inference runtime that manages different backends

Traits

RuntimeBackend

Generic inference runtime trait