paper-with-me

Papers

Iterative Structured Pruning for Large Language Models with Multi-Domain Calibration

2026-01-06 · Guangxin Wu, Hao Zhang, Zhang Zhibin, Jiafeng Guo, Xueqi Cheng arxiv

Large Language Models (LLMs) have achieved remarkable success across a wide spectrum of natural language processing tasks. However, their ever-growing scale introduces significant barriers to real-world deployment, including substantial computational overhead, memory footprint, and inference latency. While model pruning presents a viable solution to these challenges, existing unstructured pruning techniques often yield irregular sparsity patterns that necessitate specialized hardware or software support. In this work, we explore structured pruning, which eliminates entire architectural components and maintains compatibility with standard hardware accelerators. We introduce a novel structured pruning framework that leverages a hybrid multi-domain calibration set and an iterative calibration strategy to effectively identify and remove redundant channels. Extensive experiments on various models across diverse downstream tasks show that our approach achieves significant compression with minimal performance degradation.

📄 PDF Abstract BibTeX arXiv:2601.02674

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models

2025-10-20 · Ziyan Wang, Enmao Diao, Qi Le, Pu Wang 외 arxiv

Structured pruning is a practical approach to deploying large language models (LLMs) efficiently, as it yields compact, hardware-friendly architectures. However, the dominant local paradigm is task-agnostic: by optimizin…

Iterative Activation-based Structured Pruning

2022-01-22 · Kaiqi Zhao, Animesh Jain, Ming Zhao

Deploying complex deep learning models on edge devices is challenging because they have substantial compute and memory resource requirements, whereas edge devices' resource budget is limited. To solve this problem, exten…

PIP: Perturbation-based Iterative Pruning for Large Language Models

2025-01-25 · Yi Cao, Wei-Jie Xu, Yucheng Shen, Weijie Shi 외

The rapid increase in the parameter counts of Large Language Models (LLMs), reaching billions or even trillions, presents significant challenges for their practical deployment, particularly in resource-constrained enviro…

Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations

2024-07-08 · Bowen Shen, Zheng Lin, Daren Zha, Wei Liu 외

Structured pruning fundamentally reduces computational and memory overheads of large language models (LLMs) and offers a feasible solution for end-side LLM deployment. Structurally pruned models remain dense and high-pre…

Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models

2023-08-07 · Seungcheol Park, Hojun Choi, U Kang

Given a pretrained encoder-based language model, how can we accurately compress it without retraining? Retraining-free structured pruning algorithms are crucial in pretrained language model compression due to their signi…

Language ModelingLanguage ModellingModel Compression