Get started
Work

PQuantML: A Tool for End-to-End Hardware-aware Model Compression

Year: 2026
Type: article
Abstract: PQuantML is a new open-source, hardware-aware neural network model compression library tailored to end-to-end workflows. Motivated by the need to deploy performant models to environments with strict latency constraints, PQuantML simplifies training of compressed models by providing a unified interface to apply pruning and quantization, either jointly or individually. The library implements multiple pruning methods with different granularities, as well as fixed-point quantization with support for High-Granularity Quantization. We evaluate PQuantML on representative tasks such as the jet substructure classification, so-called jet tagging, an on-edge problem related to real-time LHC data processing. Using various pruning methods with fixed-point quantization, PQuantML achieves substantial parameter and bit-width reductions while maintaining accuracy. The resulting compression is further compared against existing tools, such as QKeras and HGQ.
DOI: 10.48550/arxiv.2603.26595
Authors: Niemi, Roope, Petrovych, Anastasiia, Das, Arghya Ranjan, Lupi, Enrico, Sun, Chang, Danopoulos, Dimitrios, Helbing, Marlon Joshua, Liu, Mia, Dittmeier, Sebastian, Kagan, Michael, Loncar, Vladimir, Pierini, Maurizio
Institutions: European Organization for Nuclear Research, Purdue University West Lafayette, California Institute of Technology, University of Padua, Heidelberg University, SLAC National Accelerator Laboratory, Institute of Physics Belgrade
Language: English
Open Access status: green
OpenAlex ID: W7143371898
FWCI:
Cites:
Cited by:
Related to: