English
Related papers

Related papers: HeadInfer: Memory-Efficient LLM Inference by Head-…

200 papers

Serving long-context LLMs is challenging because request lengths and batch composition vary during token generation, causing the memory footprint to fluctuate significantly at runtime. Offloading KV caches to host memory limits effective…

Artificial Intelligence · Computer Science 2026-03-03 Xinyue Ma , Heelim Hong , Taegeon Um , Jongseop Lee , Seoyeong Choy , Woo-Yeon Lee , Myeongjae Jeon

Large language model (LLM) inference is increasingly bottlenecked by the Key-Value (KV) cache, yet the fine-grained structure of attention-head activations remains poorly understood. We show that pretrained Transformers exhibit a pervasive…

Machine Learning · Computer Science 2026-03-17 Khalid Shaikh , Asmit Kumar Singh , Rebecca Christopher Dsouza , Shikhar Shiromani

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

Transformers have emerged as the backbone of large language models (LLMs). However, generation remains inefficient due to the need to store in memory a cache of key-value representations for past tokens, whose size scales linearly with the…

Computation and Language · Computer Science 2024-07-24 Piotr Nawrot , Adrian Łańcucki , Marcin Chochowski , David Tarjan , Edoardo M. Ponti

The computational and memory demands of large language models for generative inference present significant challenges for practical deployment. One promising solution targeting offline inference is offloading-based batched inference, which…

Hardware Architecture · Computer Science 2026-02-09 Hongsun Jang , Jaeyong Song , Changmin Shin , Si Ung Noh , Jaewon Jung , Jisung Park , Jinho Lee

Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time. The primary culprits are the activations, whose memory footprints scale linearly with sequence length. We…

Computation and Language · Computer Science 2026-03-03 Wenhao Li , Daohai Yu , Gen Luo , Yuxin Zhang , Fei Chao , Rongrong Ji , Yifan Wu , Jiaxin Liu , Ziyang Gong , Zimu Liao

Vision-Language Models (VLMs) have emerged as a critical and fast-growing extension of Large Language Models (LLMs) that enable multimodal reasoning through both text and image inputs. Although VLMs enrich the capabilities of language…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yingbing Huang , Tharun Adithya Srikrishnan , Steven K. Reinhardt , Deming Chen

Transformer-based large language models (LLMs) are now deployed to hundreds of millions of users. LLM inference is commonly performed on batches of sequences that share a prefix, such as few-shot examples or a chatbot system prompt.…

Machine Learning · Computer Science 2024-05-14 Jordan Juravsky , Bradley Brown , Ryan Ehrlich , Daniel Y. Fu , Christopher Ré , Azalia Mirhoseini

The increasing size of large language models (LLMs) challenges their usage on resource-constrained platforms. For example, memory on modern GPUs is insufficient to hold LLMs that are hundreds of Gigabytes in size. Offloading is a popular…

Computation and Language · Computer Science 2024-06-18 Donghyeon Joo , Ramyad Hadidi , Soheil Feizi , Bahar Asgari

Optimizing inference for long-context large language models (LLMs) is increasingly important due to the quadratic compute and linear memory cost of Transformers. Existing approximate inference methods, including key-value (KV) cache…

Computation and Language · Computer Science 2026-02-03 Kevin Galim , Ethan Ewer , Wonjun Kang , Minjae Lee , Hyung Il Koo , Kangwook Lee

Multimodal large language models (MLLMs) are plagued by exorbitant inference costs attributable to the profusion of visual tokens within the vision encoder. The redundant visual tokens engenders a substantial computational load and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Jiedong Zhuang , Lu Lu , Ming Dai , Rui Hu , Jian Chen , Qiang Liu , Haoji Hu

A recent trend in LLMs is developing recurrent sub-quadratic models that improve long-context processing efficiency. We investigate leading large long-context models, focusing on how their fixed-size recurrent memory affects their…

Machine Learning · Computer Science 2025-09-10 Assaf Ben-Kish , Itamar Zimerman , M. Jehanzeb Mirza , Lior Wolf , James Glass , Leonid Karlinsky , Raja Giryes

Key-value (KV) caching is critical for efficient inference in large language models (LLMs), yet its memory footprint scales linearly with context length, resulting in a severe scalability bottleneck. Existing approaches largely treat KV…

Computation and Language · Computer Science 2026-04-23 Gradwell Dzikanyanga , Weihao Yang , Hao Huang , Donglei Wu , Shihao Wang , Wen Xia , Sanjeeb K C

A large language model (LLM) is one of the most important emerging machine learning applications nowadays. However, due to its huge model size and runtime increase of the memory footprint, LLM inferences suffer from the lack of memory…

Hardware Architecture · Computer Science 2025-04-22 Soojin Hwang , Jungwoo Kim , Sanghyeon Lee , Hongbeen Kim , Jaehyuk Huh

Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value (KV) cache during…

Computation and Language · Computer Science 2025-07-16 Luohe Shi , Zuchao Li , Lefei Zhang , Guoming Liu , Baoyuan Qi , Hai Zhao

In recent times, the emergence of Large Language Models (LLMs) has resulted in increasingly larger model size, posing challenges for inference on low-resource devices. Prior approaches have explored offloading to facilitate low-memory…

Performance · Computer Science 2024-03-05 Xuanlei Zhao , Bin Jia , Haotian Zhou , Ziming Liu , Shenggan Cheng , Yang You

Major challenges in LLMs inference remain frequent memory bandwidth bottlenecks, computational redundancy, and inefficiencies in long-sequence processing. To address these issues, we propose LLM-CoOpt, a comprehensive algorithmhardware…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-11 Jie Kong , Wei Wang , Jiehan Zhou , Chen Yu

Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, inference over extended contexts is bottlenecked by the Key-Value (KV) cache, whose memory…

Computation and Language · Computer Science 2026-05-21 Seonghwan Choi , Beomseok Kang , Dongwon Jo , Jae-Joon Kim

Transformer-based large language models face severe scalability challenges in long-context generation due to the computational and memory costs of full-context attention. Under practical computation and memory constraints, many…

Computation and Language · Computer Science 2026-05-13 Xianpeng Shang , Jiang Li , Zehua Duo , Qianyi Cai , Xiangdong Su

The increasing size of the Key-Value (KV) cache during the Large Language Models long-context inference is the main obstacle for its balance between the deployment cost and task accuracy. To reduce the KV cache size in such scenarios, most…

Machine Learning · Computer Science 2025-07-25 Manlai Liang , JiaMing Zhang , Xiong Li , Jinlong Li