English
Related papers

Related papers: Not All Bits Are Equal: Scale-Dependent Memory Opt…

200 papers

One critical challenge for large language models (LLMs) for making complex reasoning is their reliance on matching reasoning patterns from training data, instead of proactively selecting the most appropriate cognitive strategy to solve a…

Computation and Language · Computer Science 2025-03-18 Qin Liu , Wenxuan Zhou , Nan Xu , James Y. Huang , Fei Wang , Sheng Zhang , Hoifung Poon , Muhao Chen

As large language models (LLMs) process increasing context windows, the memory usage of KV cache has become a critical bottleneck during inference. The mainstream KV compression methods, including KV pruning and KV quantization, primarily…

Computation and Language · Computer Science 2025-02-21 Jiebin Zhang , Dawei Zhu , Yifan Song , Wenhao Wu , Chuqiao Kuang , Xiaoguang Li , Lifeng Shang , Qun Liu , Sujian Li

Large language models (LLMs) have achieved remarkable advancements in natural language processing, showcasing exceptional performance across various tasks. However, the expensive memory and computational requirements present significant…

Artificial Intelligence · Computer Science 2025-11-13 Ruihao Gong , Yifu Ding , Zining Wang , Chengtao Lv , Xingyu Zheng , Jinyang Du , Haotong Qin , Jinyang Guo , Michele Magno , Xianglong Liu

Large language models (LLMs) excel at processing long sequences, boosting demand for key-value (KV) caching. While recent efforts to evict KV cache have alleviated the inference burden, they often fail to allocate resources rationally…

Computation and Language · Computer Science 2025-12-25 Ziran Qin , Yuchen Cao , Mingbao Lin , Wen Hu , Shixuan Fan , Ke Cheng , Weiyao Lin , Jianguo Li

Chain-of-Thought (CoT) reasoning in large language models (LLMs) significantly improves accuracy on complex tasks, yet incurs excessive memory overhead due to the long think-stage sequences stored in the Key-Value (KV) cache. Unlike…

Computation and Language · Computer Science 2026-01-27 Zihan Wang , Cheng Tang , Lei Gong , Cheng Li , Chao Wang , teng wang , Wenqi Lou , Xuehai Zhou

The explosive growth of Large Language Models (LLMs), such as GPT-4 with 1.8 trillion parameters, demands a fundamental rethinking of data center architecture to ensure scalability, efficiency, and cost-effectiveness. Our work provides a…

Hardware Architecture · Computer Science 2025-09-09 Jesmin Jahan Tithi , Hanjiang Wu , Avishaii Abuhatzera , Fabrizio Petrini

To reduce memory consumption during LLM inference, prior works have proposed numerous methods that focus on KV cache pruning based on various criteria. While these techniques often accomplish lossless memory reduction on many datasets, they…

Computation and Language · Computer Science 2026-01-07 Xuanfan Ni , Liyan Xu , Chenyang Lyu , Longyue Wang , Mo Yu , Lemao Liu , Fandong Meng , Jie Zhou , Piji Li

The growing demand for Large Language Models (LLMs) in applications such as content generation, intelligent chatbots, and sentiment analysis poses considerable challenges for LLM service providers. To efficiently use GPU resources and boost…

Machine Learning · Computer Science 2024-04-17 Yilong Zhao , Chien-Yu Lin , Kan Zhu , Zihao Ye , Lequn Chen , Size Zheng , Luis Ceze , Arvind Krishnamurthy , Tianqi Chen , Baris Kasikci

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

The rapid advancements in large Language models (LLMs) have significantly enhanced their reasoning capabilities, driven by various strategies such as multi-agent collaboration. However, unlike the well-established performance improvements…

Artificial Intelligence · Computer Science 2026-04-23 Zihan Chen , Song Wang , Zhen Tan , Xingbo Fu , Zhenyu Lei , Peng Wang , Huan Liu , Cong Shen , Jundong Li

Key-Value (KV) cache facilitates efficient large language models (LLMs) inference by avoiding recomputation of past KVs. As the batch size and context length increase, the oversized KV caches become a significant memory bottleneck,…

Machine Learning · Computer Science 2025-02-04 Zunhai Su , Zhe Chen , Wang Shen , Hanyu Wei , Linge Li , Huangqi Yu , Kehong Yuan

Scaling laws enable the optimal selection of data amount and language model size, yet the impact of the data unit, the token, on this relationship remains underexplored. In this work, we systematically investigate how the information…

Computation and Language · Computer Science 2026-05-27 Tomasz Limisiewicz , Artidoro Pagnoni , Srini Iyer , Mike Lewis , Sachin Mehta , Alisa Liu , Margaret Li , Gargi Ghosh , Luke Zettlemoyer

Large Language Models (LLMs) perform well on reasoning benchmarks but often fail when inputs alter slightly, raising concerns about the extent to which their success relies on memorization. This issue is especially acute in Chain-of-Thought…

Computation and Language · Computer Science 2025-08-22 Huihan Li , You Chen , Siyuan Wang , Yixin He , Ninareh Mehrabi , Rahul Gupta , Xiang Ren

In a recent study (Ref. [1]), quantum annealing was reported to exhibit a scaling advantage for approximately solving Quadratic Unconstrained Binary Optimization (QUBO). However, this claim critically depends on the choice of classical…

Quantum Physics · Physics 2025-05-29 J. Pawlowski , P. Tarasiuk , J. Tuziemski , L. Pawela , B. Gardas

Scaling test-time compute through extended chains of thought has become a dominant paradigm for improving large language model reasoning. However, existing research implicitly assumes that longer thinking always yields better results. This…

Artificial Intelligence · Computer Science 2026-04-14 Shu Zhou , Rui Ling , Junan Chen , Xin Wang , Tao Fan , Hao Wang

Large language models (LLMs) with extended context windows enable powerful downstream applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly with sequence length and batch size. Existing…

Computation and Language · Computer Science 2025-10-10 Yuzhe Gu , Xiyu Liang , Jiaojiao Zhao , Enmao Diao

Large Language Models (LLMs) trained via Reinforcement Learning (RL) have recently achieved impressive results on reasoning benchmarks. Yet, growing evidence shows that these models often generate longer but ineffective chains of thought…

Machine Learning · Computer Science 2025-07-02 Jhouben Cuesta-Ramirez , Samuel Beaussant , Mehdi Mounsif

How to efficiently serve LLMs in practice has become exceptionally challenging due to their prohibitive memory and computation requirements. In this study, we investigate optimizing the KV cache, whose memory footprint poses a critical…

Computation and Language · Computer Science 2025-06-10 Akshat Sharma , Hangliang Ding , Jianping Li , Neel Dani , Minjia Zhang

Modern large language models (LLMs) extend context lengths to millions of tokens, enabling coherent, personalized responses grounded in long conversational history. However, the Key-Value (KV) cache grows linearly with the extended dialogue…

Computation and Language · Computer Science 2026-05-21 Minsoo Kim , Arnav Kundu , Han-Byul Kim , Richa Dixit , Minsik Cho

Large reasoning models (LRMs) achieve strong accuracy through test-time scaling, generating longer chains of thought or sampling multiple solutions, but at steep costs in tokens and latency. We argue that memory is a core ingredient for…

Multiagent Systems · Computer Science 2026-03-04 Daivik Patel , Shrenik Patel