English
Related papers

Related papers: Quantization Dominates Rank Reduction for KV-Cache…

200 papers

KV caching is a fundamental technique for accelerating Large Language Model (LLM) inference by reusing key-value (KV) pairs from previous queries, but its effectiveness under limited memory is highly sensitive to the eviction policy. The…

Machine Learning · Computer Science 2026-01-28 Fangzhou Wu , Sandeep Silwal , Qiuyi , Zhang

The key-value (KV) cache is a primary memory bottleneck in Transformers. We propose Low-Rank Key-Value (LRKV) attention, which reduces KV cache memory by exploiting redundancy across attention heads, while being compute efficient. Each…

Machine Learning · Computer Science 2026-04-09 James O'Neill , Robert Clancy , Mariia Matskevichus , Fergal Reid

Quantization-Aware Training (QAT) is one of the prevailing neural network compression solutions. However, its stability has been challenged for yielding deteriorating performances as the quantization error is inevitable. We find that the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Junbiao Pang , Tianyang Cai

Large Language Models (LLMs) require substantial computational resources during generation. While the Key-Value (KV) cache significantly accelerates this process by storing attention intermediates, its memory footprint grows linearly with…

Computation and Language · Computer Science 2025-08-05 Yi Su , Quantong Qiu , Yuechi Zhou , Juntao Li , Qingrong Xia , Ping Li , Xinyu Duan , Zhefeng Wang , Min Zhang

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

Computation and Language · Computer Science 2024-10-31 Suyu Ge , Yunan Zhang , Liyuan Liu , Minjia Zhang , Jiawei Han , Jianfeng Gao

Large multimodal models (LMMs) have advanced significantly by integrating visual encoders with extensive language models, enabling robust reasoning capabilities. However, compressing LMMs for deployment on edge devices remains a critical…

Artificial Intelligence · Computer Science 2025-07-29 Te Zhang , Yuheng Li , Junxiang Wang , Lujun Li

Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance across diverse applications. However, their computational overhead during deployment remains a critical bottleneck. While Key-Value (KV) caching effectively…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Insu Han , Zeliang Zhang , Zhiyuan Wang , Yifan Zhu , Susan Liang , Jiani Liu , Haiting Lin , Mingjie Zhao , Chenliang Xu , Kun Wan , Wentian Zhao

Post Training Quantization (PTQ), a mainstream model compression technique, often leads to the paradoxical 'low error, high loss' phenomenon because it focuses solely on minimizing quantization error. The root cause lies in the Hessian…

Machine Learning · Computer Science 2026-01-30 Jinhao Zhang Yunquan Zhang , Zicheng yan , Boyang Zhang , Jun Sun , Daning Cheng

Large language models (LLMs) have demonstrated remarkable performance on long-context tasks, but are often bottlenecked by memory constraints. Namely, the KV cache, which is used to significantly speed up attention computations, grows…

We introduce GPTAQ, a novel finetuning-free quantization method for compressing large-scale transformer architectures. Unlike the previous GPTQ method, which independently calibrates each layer, we always match the quantized layer's output…

Machine Learning · Computer Science 2025-05-15 Yuhang Li , Ruokai Yin , Donghyun Lee , Shiting Xiao , Priyadarshini Panda

This paper presents a compression framework for Reservoir Computing that enables systematic design-space exploration of trade-offs among quantization levels, pruning rates, model accuracy, and hardware efficiency. The proposed approach…

Hardware Architecture · Computer Science 2026-03-11 Atousa Jafari , Mahdi Taheri , Hassan Ghasemzadeh Mohammadi , Christian Herglotz , Marco Platzner

Sequence model based NLP applications can be large. Yet, many applications that benefit from them run on small devices with very limited compute and storage capabilities, while still having run-time constraints. As a result, there is a need…

Computation and Language · Computer Science 2020-10-08 Urmish Thakker , Jesse Beu , Dibakar Gope , Ganesh Dasika , Matthew Mattina

Recent work on KV cache quantization, culminating in TurboQuant, has approached the Shannon entropy limit for per-vector compression of transformer key-value caches. We observe that this limit applies to a strictly weaker problem than the…

Machine Learning · Computer Science 2026-04-20 Gregory Magarshak

Scaling model size significantly challenges the deployment and inference of Large Language Models (LLMs). Due to the redundancy in LLM weights, recent research has focused on pushing weight-only quantization to extremely low-bit (even down…

Artificial Intelligence · Computer Science 2024-10-23 Yifei Liu , Jicheng Wen , Yang Wang , Shengyu Ye , Li Lyna Zhang , Ting Cao , Cheng Li , Mao Yang

While neural networks have advanced the frontiers in many applications, they often come at a high computational cost. Reducing the power and latency of neural network inference is key if we want to integrate modern networks into edge…

Machine Learning · Computer Science 2021-06-16 Markus Nagel , Marios Fournarakis , Rana Ali Amjad , Yelysei Bondarenko , Mart van Baalen , Tijmen Blankevoort

Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similarity search, but key…

Computation and Language · Computer Science 2025-03-10 Giulio Corallo , Orion Weller , Fabio Petroni , Paolo Papotti

Large language models (LLMs) have demonstrated remarkable performance, but their long-context reasoning remains constrained by the excessive memory required for the Key-Value (KV) cache. This makes KV cache compression a critical step…

Machine Learning · Computer Science 2025-09-30 Xianglong Yan , Zhiteng Li , Tianao Zhang , Haotong Qin , Linghe Kong , Yulun Zhang , Xiaokang Yang

We show that the key-value (KV) cache in transformer attention heads admits a natural decomposition into a low-rank \emph{shared context} component and a full-rank \emph{per-token} residual, well described by the spiked random matrix model.…

Machine Learning · Computer Science 2026-05-06 Pei-Chun Su

Memory consumption of the Key-Value (KV) cache represents a major bottleneck for efficient large language model inference. While attention-score-based KV cache pruning shows promise, it faces critical practical limitations: attention scores…

Artificial Intelligence · Computer Science 2025-10-02 Alessio Devoto , Maximilian Jeblick , Simon Jégou

Long-context inference in large language models is increasingly bottlenecked by the memory and compute cost of the KV-Cache. Low-rank factorization compresses KV projections by writing $W \approx A * B$, where A produces latent KV states…

Machine Learning · Computer Science 2026-02-11 Jihao Xin , Tian Lyu , David Keyes , Hatem Ltaief , Marco Canini