Neural-Forge

Lightweight framework for deploying machine learning models to edge devices. Optimized for low-latency inference.

Features

• Edge-ready: Deploy to any Edge environment.
• Low latency: Sub-millisecond inference times.
• Model optimization: Automatic quantization and pruning.

Installation

pip install neural-forge

Quick Start

from neural_forge import Model


model = Model.load("model.onnx")
model.optimize()
model.deploy(target="edge")