Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Tuowei, Li, Kun, Hao, Zixu, Bai, Donglin, Ren, Ju, Zhang, Yaoxue, Cao, Ting, Yang, Mao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909854110580736
author Wang, Tuowei
Li, Kun
Hao, Zixu
Bai, Donglin
Ren, Ju
Zhang, Yaoxue
Cao, Ting
Yang, Mao
author_facet Wang, Tuowei
Li, Kun
Hao, Zixu
Bai, Donglin
Ren, Ju
Zhang, Yaoxue
Cao, Ting
Yang, Mao
contents The adaptation of pre-trained large language models (LLMs) to diverse downstream tasks via fine-tuning is critical for numerous applications. However, the inefficiency of parameter-efficient fine-tuning (PEFT) techniques presents significant challenges in terms of time investments and operational costs. In this paper, we first introduce a nuanced form of sparsity, termed Shadowy Sparsity, which is distinctive in fine-tuning and has not been adequately addressed for acceleration. Under Shadowy Sparsity, we propose Long Exposure, an efficient system to accelerate PEFT for LLMs. Long Exposure comprises three key components: Shadowy-sparsity Exposer employs a prolonged sensing range to capture more sparsity details under shadowy sparsity; Sequence-oriented Predictor provides efficient yet accurate predictions to handle large sequence inputs and constantly-evolving parameters; and Dynamic-aware Operator facilitates more structured computational patterns and coalesced memory accesses, addressing dynamic sparse operations. Extensive evaluations show that Long Exposure outperforms state-of-the-arts with up to a $2.49\times$ speedup in end-to-end fine-tuning, offering promising advancements in accelerating PEFT for LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2510_15964
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity
Wang, Tuowei
Li, Kun
Hao, Zixu
Bai, Donglin
Ren, Ju
Zhang, Yaoxue
Cao, Ting
Yang, Mao
Machine Learning
Artificial Intelligence
Computation and Language
The adaptation of pre-trained large language models (LLMs) to diverse downstream tasks via fine-tuning is critical for numerous applications. However, the inefficiency of parameter-efficient fine-tuning (PEFT) techniques presents significant challenges in terms of time investments and operational costs. In this paper, we first introduce a nuanced form of sparsity, termed Shadowy Sparsity, which is distinctive in fine-tuning and has not been adequately addressed for acceleration. Under Shadowy Sparsity, we propose Long Exposure, an efficient system to accelerate PEFT for LLMs. Long Exposure comprises three key components: Shadowy-sparsity Exposer employs a prolonged sensing range to capture more sparsity details under shadowy sparsity; Sequence-oriented Predictor provides efficient yet accurate predictions to handle large sequence inputs and constantly-evolving parameters; and Dynamic-aware Operator facilitates more structured computational patterns and coalesced memory accesses, addressing dynamic sparse operations. Extensive evaluations show that Long Exposure outperforms state-of-the-arts with up to a $2.49\times$ speedup in end-to-end fine-tuning, offering promising advancements in accelerating PEFT for LLMs.
title Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2510.15964