English
Related papers

Related papers: ASVD: Activation-aware Singular Value Decompositio…

200 papers

Advances in large language models have driven strong performance across many tasks, but their memory and compute costs still hinder deployment. SVD-based compression reduces storage and can speed up inference via low-rank factors, yet…

Machine Learning · Computer Science 2026-02-04 Ali Abbasi , Chayne Thrash , Haoran Qin , Shansita Sharma , Sepehr Seifi , Soheil Kolouri

We introduce a fast low-rank factorization-based framework for compressing large language models that enables rapid compression of billion-parameter models without retraining. Unlike existing factorization-based approaches that optimize…

Machine Learning · Computer Science 2026-04-03 Atul Kumar Sinha , François Fleuret

Approaches for compressing large-language models using low-rank decomposition have made strides, particularly with the introduction of activation and loss-aware SVD, which improves the trade-off between decomposition rank and downstream…

Machine Learning · Computer Science 2025-12-17 Sidhant Sundrani , Francesco Tudisco , Pasquale Minervini

Singular value decomposition (SVD) is one of the most popular compression methods that approximate a target matrix with smaller matrices. However, standard SVD treats the parameters within the matrix with equal importance, which is a simple…

Computation and Language · Computer Science 2022-12-19 Ting Hua , Yen-Chang Hsu , Felicity Wang , Qian Lou , Yilin Shen , Hongxia Jin

Large language models (LLMs) have rapidly grown in scale, creating substantial memory and computational costs that hinder efficient deployment. Singular value decomposition (SVD) has emerged as an effective post-training compression…

Machine Learning · Computer Science 2026-05-12 Hengyi Zhu , Zhendong Mi , Grace Li Zhang , Shaoyi Huang

The Key-Value (KV) cache is central to the efficiency of transformer-based large language models (LLMs), storing previously computed vectors to accelerate inference. Yet, as sequence length and batch size grow, the cache becomes a major…

Machine Learning · Computer Science 2025-12-08 Damien Lesens , Beheshteh T. Rakhshan , Guillaume Rabusseau

Singular Value Decomposition (SVD) has recently seen a surge of interest as a simple yet powerful tool for large language models (LLMs) compression, with a growing number of works demonstrating 20-80% parameter reductions at minimal…

Machine Learning · Computer Science 2025-08-05 Zishan Shao , Yixiao Wang , Qinsi Wang , Ting Jiang , Zhixu Du , Hancheng Ye , Danyang Zhuo , Yiran Chen , Hai Li

For the efficient inference of Large Language Models (LLMs), the effective compression of key-value (KV) cache is essential. Three main types of KV cache compression techniques, namely sparsity, channel compression, and quantization, have…

Machine Learning · Computer Science 2025-02-24 Hong Yankun , Li Xing , Zhen Hui-Ling , Yu Xianzhi , Liu Wulong , Yuan Mingxuan

Low-rank approximation methods such as singular value decomposition (SVD) and its variants (e.g., Fisher-weighted SVD, Activation SVD) have recently emerged as effective tools for neural network compression. In this setting, decomposition…

Machine Learning · Computer Science 2025-12-02 Haoran Qin , Shansita Sharma , Ali Abbasi , Chayne Thrash , Soheil Kolouri

Training and fine-tuning large language models (LLMs) come with challenges related to memory and computational requirements due to the increasing size of the model weights and the optimizer states. Various techniques have been developed to…

Machine Learning · Computer Science 2025-12-09 Yehonathan Refael , Jonathan Svirsky , Boris Shustin , Wasim Huleihel , Ofir Lindenbaum

The evaluation of layer importance in deep learning has been an active area of research, with significant implications for model optimization and interpretability. Recently, large language models (LLMs) have gained prominence across various…

Computation and Language · Computer Science 2024-11-05 Zichen Song , Yuxin Wu , Sitan Huang , Zhongfeng Kang

The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate this by evicting tokens based on importance scores. However, we show that their reliance on global…

Machine Learning · Computer Science 2026-05-25 Junzhe Yang , Xiaoyu Shen

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…

Machine Learning · Computer Science 2024-10-07 Rongzhi Zhang , Kuang Wang , Liyuan Liu , Shuohang Wang , Hao Cheng , Chao Zhang , Yelong Shen

Large language models deliver strong performance across language and reasoning tasks, but their storage and compute costs remain major barriers to deployment in resource-constrained and latency-sensitive settings. SVD-based post-training…

Machine Learning · Computer Science 2026-05-18 Ali Abbasi , Chayne Thrash , Haoran Qin , Hamed Pirsiavash , Soheil Kolouri

Parameter-Efficient Fine-Tuning (PEFT) has emerged as a critical paradigm for adapting Large Language Models (LLMs) to downstream tasks, among which Low-rank Adaptation (LoRA) represents one of the most widely adopted methodologies.…

Computation and Language · Computer Science 2025-05-22 Jialong Han , Si Zhang , Ke Zhang

Large Language Models (LLMs) are very demanding in terms of their computational resources. Low-rank decompositions of LLM weights, e.g. via Singular Value Decomposition (SVD), is a promising approach for LLM compression, but presents…

Machine Learning · Computer Science 2025-12-04 Roman Rausch , David Jansen , Sukhbinder Singh , Román Orús

Due to the prevalence of large language models (LLMs), key-value (KV) cache reduction for LLM inference has received remarkable attention. Among numerous works that have been proposed in recent years, layer-wise token pruning approaches,…

Computation and Language · Computer Science 2026-04-17 Rei Taniguchi , Yuyang Dong , Makoto Onizuka , Chuan Xiao

Training large language models (LLMs) is highly memory-intensive, as training must store not only weights and optimizer states but also intermediate activations for backpropagation. While existing memory-efficient methods largely focus on…

Machine Learning · Computer Science 2026-05-05 Wen-Da Wei , Han-Bin Fang , Yang-Di Liu , Jiang-Xin Shi , James Kwok , Yu-Feng Li

Large language models (LLMs) have demonstrated remarkable capabilities, yet prohibitive parameter complexity often hinders their deployment. Existing singular value decomposition (SVD) based compression methods simply deem singular values…

Computation and Language · Computer Science 2025-02-24 Dengjie Li , Tiancheng Shen , Yao Zhou , Baisong Yang , Zhongying Liu , Masheng Yang , Bernard Ghanem , Yibo Yang , Yujie Zhong , Ming-Hsuan Yang

Large Language Models (LLMs) confront significant memory challenges due to the escalating KV cache with increasing sequence length. As a crucial technique, existing cross-layer KV cache sharing methods either necessitate modified model…

Machine Learning · Computer Science 2025-08-25 Yixuan Wang , Haoyu Qiao , Lujun Li , Qingfu Zhu , Wanxiang Che