English
Related papers

Related papers: ProxyKV: Cross-Model Proxy Pruning for Efficient L…

200 papers

The bottleneck associated with the key-value(KV) cache presents a significant challenge during the inference processes of large language models. While depth pruning accelerates inference, it requires extensive recovery training, which can…

Computation and Language · Computer Science 2024-09-18 Bo Lv , Quan Zhou , Xuanang Ding , Yan Wang , Zeming Ma

While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and…

Machine Learning · Computer Science 2026-04-21 Dongwon Jo , Jiwon Song , Yulhwa Kim , Jae-Joon Kim

Large language models have achieved notable success across various domains, yet efficient inference is still limited by the quadratic computation complexity of the attention mechanism. The inference consists of prefilling and decoding…

Computation and Language · Computer Science 2024-09-24 Junlin Lv , Yuan Feng , Xike Xie , Xin Jia , Qirong Peng , Guiming Xie

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

Artificial Intelligence · Computer Science 2025-05-27 Ahmet Caner Yüzügüler , Jiawei Zhuang , Lukas Cavigelli

The quadratic complexity of the attention mechanism and the substantial memory footprint of the Key-Value (KV) cache present severe computational and memory challenges for Large Language Models (LLMs) processing long contexts. Existing…

Machine Learning · Computer Science 2026-03-10 Dongfang Li , Zixuan Liu , Gang Lin , Baotian Hu , Min Zhang

Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens…

Computation and Language · Computer Science 2024-06-03 Sotiris Anagnostidis , Dario Pavllo , Luca Biggio , Lorenzo Noci , Aurelien Lucchi , Thomas Hofmann

Vision language models (VLMs) demonstrate strong capabilities in jointly processing visual and textual data. However, they often incur substantial computational overhead due to redundant visual information, particularly in long-form video…

Machine Learning · Computer Science 2025-04-25 Yudong Liu , Jingwei Sun , Yueqian Lin , Jingyang Zhang , Ming Yin , Qinsi Wang , Jianyi Zhang , Hai Li , Yiran Chen

Large language models (LLMs) support long-context inference but suffer from substantial memory and runtime overhead due to Key-Value (KV) Cache growth. Existing KV Cache eviction methods primarily rely on local attention weights, neglecting…

Computation and Language · Computer Science 2026-05-11 Tho Mai , Joo-Young Kim

The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank KV compression methods reduce this footprint by modifying model…

Computation and Language · Computer Science 2026-05-14 Shiyu Ji , Yixuan Wang , Yijun Liu , Qingfu Zhu , Wanxiang Che

Existing key-value (KV) cache compression methods for large language models (LLMs) often rely on token eviction, which risks losing critical local information in both long prefilling and decoding scenarios. When extrapolating beyond the…

Computation and Language · Computer Science 2026-01-30 Jushi Kai , Yixuan Wang , Boyi Zeng , Haoli Bai , Bo Jiang , Ziwei He , Zhouhan Lin

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

Visual token reduction lowers inference costs caused by extensive image features in large vision-language models (LVLMs). Unlike relevant studies that prune tokens in self-attention-only LVLMs, our work uniquely addresses…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Jewon Lee , Ki-Ung Song , Seungmin Yang , Donguk Lim , Jaeyeon Kim , Wooksu Shin , Bo-Kyeong Kim , Yong Jae Lee , Tae-Ho Kim

The quadratic complexity of attention mechanisms limits the efficiency of Large Language Models (LLMs) on long-text tasks. Recently, methods that dynamically estimate block importance have enabled efficient block sparse attention, leading…

Computation and Language · Computer Science 2026-04-01 Yixuan Wang , Huang He , Siqi Bao , Hua Wu , Haifeng Wang , Qingfu Zhu , Wanxiang Che

Large language models (LLMs) can now handle longer sequences of tokens, enabling complex tasks like book understanding and generating lengthy novels. However, the key-value (KV) cache required for LLMs consumes substantial memory as context…

Machine Learning · Computer Science 2024-11-13 Haojie Duanmu , Zhihang Yuan , Xiuhong Li , Jiangfei Duan , Xingcheng Zhang , Dahua Lin

Large Language Models (LLMs) have made significant strides in natural language processing and generation, yet their ability to handle long-context input remains constrained by the quadratic complexity of attention computation and…

Computation and Language · Computer Science 2025-06-16 Manlai Liang , Wanyi Huang , Mandi Liu , Huaijun Li , Jinlong Li

Autoregressive decoding in large language models (LLMs) requires caching a growing list of past key-value (KV) pairs, making long-context inference a memory-bound problem. While recent methods have explored quantizing the cache, evicting…

Computation and Language · Computer Science 2025-10-08 Harshil Vejendla

Large language models face significant computational and memory challenges when processing long contexts. During inference, efficient management of the key-value (KV) cache, which stores intermediate activations for autoregressive…

Computation and Language · Computer Science 2025-09-30 Yuxuan Zhu , Ali Falahati , David H. Yang , Mohammad Mohammadi Amiri

Despite the general capabilities of large pretrained language models, they consistently benefit from further adaptation to better achieve desired behaviors. However, tuning these models has become increasingly resource-intensive, or…

Computation and Language · Computer Science 2024-08-26 Alisa Liu , Xiaochuang Han , Yizhong Wang , Yulia Tsvetkov , Yejin Choi , Noah A. Smith

As modern LLMs support thousands to millions of tokens, KV caches grow to hundreds of gigabytes, stressing memory capacity and bandwidth. Existing solutions, such as KV cache pruning and offloading, alleviate these but underutilize hardware…

Performance · Computer Science 2026-04-21 Mao Lin , Xi Wang , Guilherme Cox , Dong Li , Hyeran Jeon

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