snap-research/F8Net

[ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization

41
/ 100
Emerging

This project helps machine learning engineers and researchers deploy neural networks more efficiently by making them smaller and faster. It takes a trained neural network and converts its complex internal calculations into simpler 8-bit operations. The output is a highly optimized neural network that maintains accuracy while requiring less computational power, ideal for deployment on devices with limited resources.

No commits in the last 6 months.

Use this if you need to deploy machine learning models on edge devices or in environments where computational resources and energy are scarce.

Not ideal if your primary concern is achieving the absolute highest model accuracy, and you have ample computational resources for model inference.

edge-AI model-optimization embedded-systems resource-constrained-AI neural-network-deployment
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

93

Forks

15

Language

Python

License

Last pushed

May 05, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/snap-research/F8Net"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.