English
Related papers

Related papers: UNIQUE: Universal Top-k Sparse Attention for Train…

200 papers

Transformer-based large language models (LLMs) demonstrate impressive potential in various practical applications. However, long context inference poses a significant challenge due to the enormous memory requirements of the key-value (KV)…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-03 Bo Jiang , Taolue Yang , Youyuan Liu , Chengming Zhang , Xubin He , Sian Jin

With the advancements in long-context inference capabilities of large language models (LLMs), the KV cache has become one of the foundational components. However, its substantial GPU memory consumption makes KV cache compression a key…

Computation and Language · Computer Science 2025-03-28 Youhui Zuo , Sibo Wei , Chen Zhang , Zhuorui Liu , Wenpeng Lu , Dawei Song

Serving long-context LLMs is costly because attention computation grows linearly with context length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to the key-value (KV) cache of critical tokens. However, with…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Qihui Zhou , Peiqi Yin , Pengfei Zuo , James Cheng

Large language models (LLMs) are essential in natural language processing but often struggle with inference speed and computational efficiency, limiting real-time deployment. The key-value (KV) cache mechanism reduces computational overhead…

Computation and Language · Computer Science 2024-10-31 Junqi Zhao , Zhijin Fang , Shu Li , Shaohui Yang , Shichao He

The deployment of long-context Large Language Models (LLMs) poses significant challenges due to the intense computational cost of self-attention and the substantial memory overhead of the Key-Value Cache (KV Cache). In this paper, we…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-21 Haoxuan Wang , Chen Wang

With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key-value (KV) cache expands with the sequence length, the…

Machine Learning · Computer Science 2025-04-29 Hanshi Sun , Li-Wen Chang , Wenlei Bao , Size Zheng , Ningxin Zheng , Xin Liu , Harry Dong , Yuejie Chi , Beidi Chen

Transformer-based models are the foundation of modern machine learning, but their execution, particularly during autoregressive decoding in large language models (LLMs), places significant pressure on memory systems due to frequent memory…

Computation and Language · Computer Science 2026-05-13 Zehao Fan , Garrett Gagnon , Zhenyu Liu , Liu Liu

The quadratic computational complexity of the attention mechanism in current Large Language Models (LLMs) renders inference with long contexts prohibitively expensive. To address this challenge, various approaches aim to retain critical…

Computation and Language · Computer Science 2024-12-09 Hongyin Tang , Di Xiu , Lanrui Wang , Xiurui Geng , Jingang Wang , Xunliang Cai

Efficiently processing long sequences with Transformer models usually requires splitting the computations across accelerators via context parallelism. The dominant approaches in this family of methods, such as Ring Attention or DeepSpeed…

Machine Learning · Computer Science 2026-02-25 Ravi Ghadia , Maksim Abraham , Sergei Vorobyov , Max Ryabinin

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

Long-context decoding in LLMs is IO-bound: each token re-reads an ever-growing KV cache. Prior accelerations cut bytes via compression, which lowers fidelity, or selection/eviction, which restricts what remains accessible, and both can…

Machine Learning · Computer Science 2026-04-02 Jinghan Yao , Sam Adé Jacobs , Walid Krichene , Masahiro Tanaka , Dhabaleswar K Panda

The Transformer architecture has significantly advanced natural language processing (NLP) and has been foundational in developing large language models (LLMs) such as LLaMA and OPT, which have come to dominate a broad range of NLP tasks.…

Artificial Intelligence · Computer Science 2024-03-27 Youpeng Zhao , Di Wu , Jun Wang

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

Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional methods selectively evict less important KV cache entries, which…

Machine Learning · Computer Science 2025-12-01 Yuxuan Tian , Zihan Wang , Yebo Peng , Aomufei Yuan , Zhiming Wang , Bairen Yi , Xin Liu , Yong Cui , Tong Yang

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

Generative reasoning with large language models (LLMs) often involves long decoding sequences, leading to substantial memory and latency overheads from accumulating key-value (KV) caches. While existing KV compression methods primarily…

Machine Learning · Computer Science 2025-12-16 Hui Zeng , Daming Zhao , Pengfei Yang , WenXuan Hou , Tianyang Zheng , Hui Li , Weiye Ji , Jidong Zhai

Self-attention dominates the computational and memory cost of long-context LLM inference across both prefill and decode phases. To address this challenge, we introduce Sketch&Walk Attention, a training-free sparse attention method that…

Machine Learning · Computer Science 2026-02-10 Hoang Anh Duy Le , Sahil Joshi , Zeyu Yang , Zhaozhuo Xu , Anshumali Shrivastava

Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the efficient processing of video sequences that are usually…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Xuan Zhang , Cunxiao Du , Sicheng Yu , Jiawei Wu , Fengzhuo Zhang , Wei Gao , Qian Liu

Large Language Models (LLMs), while demonstrating remarkable capabilities across various applications, present significant challenges during inference due to their substantial model size, especially when deployed on edge devices. Activation…

Machine Learning · Computer Science 2025-04-29 Zhenyu Zhang , Zechun Liu , Yuandong Tian , Harshit Khaitan , Zhangyang Wang , Steven Li

KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness. However, current methods have three unsolved issues:…

Machine Learning · Computer Science 2025-11-21 Xing Li , Zeyu Xing , Yiming Li , Linping Qu , Hui-Ling Zhen , Wulong Liu , Yiwu Yao , Sinno Jialin Pan , Mingxuan Yuan