PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wnag, Zining, Guo, Jinyang, Gong, Ruihao, Yong, Yang, Liu, Aishan, Huang, Yushi, Liu, Jiaheng, Liu, Xianglong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915056156934144
author Wnag, Zining
Guo, Jinyang
Gong, Ruihao
Yong, Yang
Liu, Aishan
Huang, Yushi
Liu, Jiaheng
Liu, Xianglong
author_facet Wnag, Zining
Guo, Jinyang
Gong, Ruihao
Yong, Yang
Liu, Aishan
Huang, Yushi
Liu, Jiaheng
Liu, Xianglong
contents With the increased attention to model efficiency, post-training sparsity (PTS) has become more and more prevalent because of its effectiveness and efficiency. However, there remain questions on better practice of PTS algorithms and the sparsification ability of models, which hinders the further development of this area. Therefore, a benchmark to comprehensively investigate the issues above is urgently needed. In this paper, we propose the first comprehensive post-training sparsity benchmark called PTSBench towards algorithms and models. We benchmark 10+ PTS general-pluggable fine-grained techniques on 3 typical tasks using over 40 off-the-shelf model architectures. Through extensive experiments and analyses, we obtain valuable conclusions and provide several insights from both algorithms and model aspects. Our PTSBench can provide (1) new observations for a better understanding of the PTS algorithms, (2) in-depth and comprehensive evaluations for the sparsification ability of models, and (3) a well-structured and easy-integrate open-source framework. We hope this work will provide illuminating conclusions and advice for future studies of post-training sparsity methods and sparsification-friendly model design. The code for our PTSBench is released at \href{https://github.com/ModelTC/msbench}{https://github.com/ModelTC/msbench}.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07268
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models
Wnag, Zining
Guo, Jinyang
Gong, Ruihao
Yong, Yang
Liu, Aishan
Huang, Yushi
Liu, Jiaheng
Liu, Xianglong
Machine Learning
Multimedia
With the increased attention to model efficiency, post-training sparsity (PTS) has become more and more prevalent because of its effectiveness and efficiency. However, there remain questions on better practice of PTS algorithms and the sparsification ability of models, which hinders the further development of this area. Therefore, a benchmark to comprehensively investigate the issues above is urgently needed. In this paper, we propose the first comprehensive post-training sparsity benchmark called PTSBench towards algorithms and models. We benchmark 10+ PTS general-pluggable fine-grained techniques on 3 typical tasks using over 40 off-the-shelf model architectures. Through extensive experiments and analyses, we obtain valuable conclusions and provide several insights from both algorithms and model aspects. Our PTSBench can provide (1) new observations for a better understanding of the PTS algorithms, (2) in-depth and comprehensive evaluations for the sparsification ability of models, and (3) a well-structured and easy-integrate open-source framework. We hope this work will provide illuminating conclusions and advice for future studies of post-training sparsity methods and sparsification-friendly model design. The code for our PTSBench is released at \href{https://github.com/ModelTC/msbench}{https://github.com/ModelTC/msbench}.
title PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models
topic Machine Learning
Multimedia
url https://arxiv.org/abs/2412.07268