LGMMDec 10, 2024

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

arXiv:2412.07268v19 citationsh-index: 28Has CodeMM
Originality Synthesis-oriented
AI Analysis

This work addresses the need for standardized evaluation in model efficiency for researchers and practitioners, though it is incremental as it benchmarks existing methods rather than proposing new ones.

The paper tackles the lack of comprehensive benchmarks for post-training sparsity (PTS) by introducing PTSBench, which evaluates over 10 fine-grained techniques on 40+ model architectures across 3 tasks, providing new insights and an open-source framework.

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}.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes