Sample-aware Adaptive Structured Pruning for Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kong, Jun, Ma, Xinge, Wang, Jin, Zhang, Xuejie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929748577353728
author Kong, Jun
Ma, Xinge
Wang, Jin
Zhang, Xuejie
author_facet Kong, Jun
Ma, Xinge
Wang, Jin
Zhang, Xuejie
contents Large language models (LLMs) have achieved outstanding performance in natural language processing, but enormous model sizes and high computational costs limit their practical deployment. Structured pruning can effectively reduce the resource demands for deployment by removing redundant model parameters. However, the randomly selected calibration data and fixed single importance estimation metrics in existing structured pruning methods lead to degraded performance of pruned models. This study introduces AdaPruner, a sample-aware adaptive structured pruning framework for LLMs, aiming to optimize the calibration data and importance estimation metrics in the structured pruning process. Specifically, AdaPruner effectively removes redundant parameters from LLMs by constructing a structured pruning solution space and then employing Bayesian optimization to adaptively search for the optimal calibration data and importance estimation metrics. Experimental results show that the AdaPruner outperforms existing structured pruning methods on a family of LLMs with varying pruning ratios, demonstrating its applicability and robustness. Remarkably, at a 20\% pruning ratio, the model pruned with AdaPruner maintains 97\% of the performance of the unpruned model.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06184
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sample-aware Adaptive Structured Pruning for Large Language Models
Kong, Jun
Ma, Xinge
Wang, Jin
Zhang, Xuejie
Computation and Language
Artificial Intelligence
Machine Learning
Large language models (LLMs) have achieved outstanding performance in natural language processing, but enormous model sizes and high computational costs limit their practical deployment. Structured pruning can effectively reduce the resource demands for deployment by removing redundant model parameters. However, the randomly selected calibration data and fixed single importance estimation metrics in existing structured pruning methods lead to degraded performance of pruned models. This study introduces AdaPruner, a sample-aware adaptive structured pruning framework for LLMs, aiming to optimize the calibration data and importance estimation metrics in the structured pruning process. Specifically, AdaPruner effectively removes redundant parameters from LLMs by constructing a structured pruning solution space and then employing Bayesian optimization to adaptively search for the optimal calibration data and importance estimation metrics. Experimental results show that the AdaPruner outperforms existing structured pruning methods on a family of LLMs with varying pruning ratios, demonstrating its applicability and robustness. Remarkably, at a 20\% pruning ratio, the model pruned with AdaPruner maintains 97\% of the performance of the unpruned model.
title Sample-aware Adaptive Structured Pruning for Large Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2503.06184