LoRS: Efficient Low-Rank Adaptation for Sparse Large Language Model

TL;DR

LoRS is a novel method that enhances the efficiency of fine-tuning sparse large language models by reducing memory and computation costs while maintaining or improving performance.

Contribution

It introduces weight recompute and graph rearrangement strategies to improve LoRA efficiency on sparse LLMs, along with better adapter initialization.

Findings

Reduces memory and computation during fine-tuning

Outperforms existing LoRA approaches in effectiveness

Maintains high performance with lower resource consumption

Abstract

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with additional masking mechanisms. Despite these successes, such approaches suffer from an increased memory and computation overhead, which affects efficiency of LoRA methods. In response to this limitation, we introduce LoRS, an innovative method designed to achieve both memory and computation efficiency when fine-tuning sparse LLMs. To mitigate the substantial memory and computation demands associated with preserving sparsity, our approach incorporates strategies of weight recompute and computational graph rearrangement. In addition, we also improve the effectiveness of LoRS through better adapter initialization. These innovations lead to a notable reduction in memory and computation consumption during the fine-tuning phase, all while achieving performance levels that outperform existing LoRA approaches.