English
Related papers

Related papers: Spotlight Attention: Towards Efficient LLM Generat…

200 papers

Large Language Models (LLMs) exhibit enhanced capabilities by Chain-of-Thought reasoning. However, the extended reasoning sequences introduce significant GPU memory overhead due to increased key-value (KV) cache. Existing KV cache…

Machine Learning · Computer Science 2025-10-16 Haoyue Zhang , Hualei Zhang , Xiaosong Ma , Jie Zhang , Song Guo

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…

Machine Learning · Computer Science 2024-10-07 Rongzhi Zhang , Kuang Wang , Liyuan Liu , Shuohang Wang , Hao Cheng , Chao Zhang , Yelong Shen

Recent large language models (LLMs) with enormous model sizes use many GPUs to meet memory capacity requirements incurring substantial costs for token generation. To provide cost-effective LLM inference with relaxed latency constraints,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-03 Sanghyeon Lee , Hongbeen Kim , Soojin Hwang , Guseul Heo , Minwoo Noh , Jaehyuk Huh

Video Large Language Models (Video-LLMs) excel at understanding videos in-context, provided they have full access to the video when answering queries. However, these models face challenges in streaming scenarios where hour-long videos must…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Vaggelis Dorovatas , Soroush Seifi , Gunshi Gupta , Rahaf Aljundi

We present an approximate attention mechanism named HyperAttention to address the computational challenges posed by the growing complexity of long contexts used in Large Language Models (LLMs). Recent work suggests that in the worst-case…

Machine Learning · Computer Science 2023-12-04 Insu Han , Rajesh Jayaram , Amin Karbasi , Vahab Mirrokni , David P. Woodruff , Amir Zandieh

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-06 Dimitrios Kafetzis , Ramin Khalili , Iordanis Koutsopoulos

The attention operator remains a critical performance bottleneck in large language models (LLMs), particularly for long-context scenarios. While FlashAttention is the most widely used and effective GPU-aware acceleration algorithm, it must…

Recent reasoning large language models (LLMs) excel in complex tasks but encounter significant computational and memory challenges due to long sequence lengths. KV cache compression has emerged as an effective approach to greatly enhance…

Computation and Language · Computer Science 2025-12-02 Mengqi Liao , Lu Wang , Chaoyun Zhang , Zekai Shen , Xiaowei Mao , Si Qin , Qingwei Lin , Saravan Rajmohan , Dongmei Zhang , Huaiyu Wan

Key--value (KV) caching enables fast autoregressive decoding but at long contexts becomes a dominant bottleneck in High Bandwidth Memory (HBM) capacity and bandwidth. A common mitigation is to compress cached keys and values by projecting…

Vision-language models (VLMs) have shown remarkable success across various multi-modal tasks, yet large VLMs encounter significant efficiency challenges due to processing numerous visual tokens. A promising approach to accelerating large…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Wangbo Zhao , Yizeng Han , Jiasheng Tang , Zhikai Li , Yibing Song , Kai Wang , Zhangyang Wang , Yang You

The transformer's context window is vital for tasks such as few-shot learning and conditional generation as it preserves previous tokens for active memory. However, as the context lengths increase, the computational costs grow…

Computation and Language · Computer Science 2025-04-01 Jeffrey Willette , Heejun Lee , Youngwan Lee , Myeongjae Jeon , Sung Ju Hwang

Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A…

Computation and Language · Computer Science 2026-05-26 Xintong Yang , Hao Gu , Binxing Xu , Lujun Li , Bei Liu , Jiacheng Liu , Qiyuan Zhu , Sirui Han , Yike Guo

Scaling inference for large language models (LLMs) is increasingly constrained by limited GPU memory, especially due to growing key-value (KV) caches required for long-context generation. While existing approaches offload KV caches to CPU…

Machine Learning · Computer Science 2025-07-08 Weishu Deng , Yujie Yang , Peiran Du , Lingfeng Xiang , Zhen Lin , Chen Zhong , Song Jiang , Hui Lu , Jia Rao

KV cache stores key and value states from previous tokens to avoid re-computation, yet it demands substantial storage space, especially for long sequences. Adaptive KV cache compression seeks to discern the saliency of tokens, preserving…

Machine Learning · Computer Science 2024-05-24 Yefei He , Luoming Zhang , Weijia Wu , Jing Liu , Hong Zhou , Bohan Zhuang

Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughput and latency while keeping costs manageable. The Key-Value…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-23 Jiale Xu , Rui Zhang , Cong Guo , Weiming Hu , Zihan Liu , Feiyang Wu , Yu Feng , Shixuan Sun , Changxu Shao , Yuhong Guo , Junping Zhao , Ke Zhang , Minyi Guo , Jingwen Leng

Serving large language models (LLMs) efficiently remains challenging due to the high memory and latency overhead of key-value (KV) cache access during autoregressive decoding. We present \textbf{TinyServe}, a lightweight and extensible…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-17 Dong Liu , Yanxuan Yu

Compressing the KV cache is a required step to deploy large language models on edge devices. Current quantization methods compress storage but fail to reduce bandwidth as attention calculation requires dequantizing keys from INT4/INT8 to…

Machine Learning · Computer Science 2026-01-16 Aryan Karmore

Key-Value (KV) cache remains a major bottleneck for deploying Large Language Models (LLMs) in long-generation tasks. Prior work often applies uniform compression across both prefill and decoding caches, but compressing the prefill cache…

Artificial Intelligence · Computer Science 2026-05-29 Soumyadeep Jana , Sagar Nishad , Sanasam Ranbir Singh

The high memory demands of the Key-Value (KV) Cache during the inference of Large Language Models (LLMs) severely restrict their deployment in resource-constrained platforms. Quantization can effectively alleviate the memory pressure caused…

Machine Learning · Computer Science 2026-02-03 Fei Li , Song Liu , Weiguo Wu , Shiqiang Nie , Jinyu Wang

Large language models (LLMs) with extended context windows have become increasingly prevalent for tackling complex tasks. However, the substantial Key-Value (KV) cache required for long-context LLMs poses significant deployment challenges.…

Computation and Language · Computer Science 2025-06-16 Jie Hu , Shengnan Wang , Yutong He , Ping Gong , Jiawei Yi , Juncheng Zhang , Youhui Bai , Renhai Chen , Gong Zhang , Cheng Li , Kun Yuan