Crate autoagents_onnx 

Liquid Edge - Generic Edge Inference Runtime

A lightweight, efficient inference runtime designed for edge computing environments. Supports multiple backends for running deep learning models on edge devices.

Re-exports

pub use device::cpu;

pub use device::cpu_with_threads;

pub use device::Device;

pub use error::EdgeError;

pub use error::EdgeResult;

pub use model::Model;

pub use runtime::inference::OnnxBackend;

pub use runtime::inference::OnnxModel;

pub use runtime::onnx_model;

pub use runtime::InferenceInput;

pub use runtime::InferenceOutput;

pub use runtime::InferenceRuntime;

Modules

chat

autoagents-onnx backend implementation for local model inference.

device

Device abstraction for liquid-edge inference

error

Error types for autoagents-onnx runtime

model

Model abstraction layer for autoagents-onnx

runtime

Onnx inference runtime for edge computing