Work

Next Generation Triggers ML Optimization: Quantization Techniques for Scalable Inference

Year: 2025

Type: article

Abstract: Quantization is the use of a lower precision for the model parameters. It is a useful technique, as it lowers significantly the size of a model, while trying to preserve the accuracy. Some runtimes like ONNX offer the possibility to do dynamic quantization. The tasks will be to explore and evaluate the different techniques for model quantization to offer users a view of their model metrics under such a compression. The outcomes of this project will provide decision support for the users whether to use quantization for inference and/or training.

Source: CERN Document Server (European Organization for Nuclear Research)

DOI: 10.17181/t45bn-2hj98

Author: Sadek, Najla

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Schmidt Family Foundation

OpenAlex ID: W6962740144

FWCI:

Cites:

Cited by:

Related to: