English
Related papers

Related papers: SPHERICAL KV: Angle-Domain Attention and Rate-Dist…

200 papers

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

Long-context inference increasingly operates over CPU-resident KV caches, either because decoding-time KV states exceed GPU memory capacity or because disaggregated prefill-decode systems place KV data in host memory. Although block-sparse…

Machine Learning · Computer Science 2026-05-11 Feiyu Yao , Zhixiong Niu , Xiaqing Li , Yongqiang Xiong , Juan Fang , Qian Wang

Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference. Current KV cache eviction methods typically rely on instantaneous heuristic metrics, implicitly assuming that score magnitudes are…

Machine Learning · Computer Science 2026-02-10 Ziyao Tang , Pengkun Jiao , Xinhang Chen , Wei Liu , Shiyong Li , Jingjing Chen

Transformer-based large language models (LLMs) use the key-value (KV) cache to significantly accelerate inference by storing the key and value embeddings of past tokens. However, this cache consumes significant GPU memory. In this work, we…

The KV cache in self-attention has emerged as a major bottleneck in long-context and large-batch inference for LLMs. Existing approaches often treat sparsity prediction and compression as separate modules, relying on auxiliary index…

Machine Learning · Computer Science 2026-03-17 Xu Yang , Jiapeng Zhang , Dongyang Zhao , Guo Chen , Zhuo Tang

Current hierarchical attention methods, such as NSA and InfLLMv2, select the top-k relevant key-value (KV) blocks based on coarse attention scores and subsequently apply fine-grained softmax attention on the selected tokens. However, the…

Computation and Language · Computer Science 2026-05-19 Yuxiang Huang , Nuno M. T. Gonçalves , Federico Alvetreti , Lei Li , Xu Han , Edoardo M. Ponti , André F. T. Martins , Marcos V. Treviso

Efficient inference is critical for long-context language models, where attention computation and KV-cache access dominate the cost. Recent work RAT+, introduces a recurrence-augmented attention backbone that enables flexible dilated…

Machine Learning · Computer Science 2026-05-28 Xiuying Wei , Caglar Gulcehre

Large Audio-Language Models (LALMs) have set new benchmarks in speech processing, yet their deployment is hindered by the memory footprint of the Key-Value (KV) cache during long-context inference. While general KV cache compression…

Sound · Computer Science 2026-04-09 Yuxuan Wang , Peize He , Xiyan Gui , Xiaoqian Liu , Junhao He , Xuyang Liu , Zichen Wen , Xuming Hu , Linfeng Zhang

Large Language Models (LLMs) suffer inference-time memory bottlenecks dominated by the attention Key-Value (KV) cache, which scales with model size and context length. While KV-cache quantization alleviates this cost, bit allocation between…

Machine Learning · Computer Science 2026-05-12 Mohsen Hariri , Alan Luo , Weicong Chen , Shaochen Zhong , Tianyi Zhang , Qifan Wang , Xia Hu , Xiaotian Han , Vipin Chaudhary

The key-value (KV) cache in transformer models is a critical component for efficient decoding or inference, yet its memory demands scale poorly with sequence length, posing a major challenge for scalable deployment of large language models.…

Computation and Language · Computer Science 2025-06-06 Vinay Joshi , Pratik Prabhanjan Brahma , Zicheng Liu , Emad Barsoum

The quadratic complexity of attention mechanisms poses a critical bottleneck for large language models processing long contexts. While dynamic sparse attention methods offer input-adaptive efficiency, they face fundamental trade-offs:…

Computation and Language · Computer Science 2026-02-06 Siran Liu , Guoxia Wang , Sa Wang , Jinle Zeng , HaoYang Xie , Siyu Lou , JiaBin Yang , DianHai Yu , Haifeng Wang , Chao Yang

In long-context decoding for LLMs and LMMs, attention becomes increasingly memory-bound because each decoding step must load a large amount of KV-cache data from GPU memory. Existing acceleration strategies often trade efficiency for…

Machine Learning · Computer Science 2026-04-21 Junnan Liu , Xinyan Liu , Peifeng Gao , Zhaobo Qi , Beichen Zhang , Weigang Zhang , Antoni Bert Chen

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

Machine Learning · Computer Science 2025-05-28 Ted Zadouri , Hubert Strauss , Tri Dao

Visual Autoregressive (VAR) models have recently demonstrated impressive image generation quality while maintaining low latency. However, they suffer from severe KV-cache memory constraints, often requiring gigabytes of memory per generated…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jonathan Cederlund , Axel Berg , Durmus Alp Emre Acar , Chuteng Zhou , Pontus Giselsson

Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintain performance. Existing methods use random linear hashing to…

Computation and Language · Computer Science 2025-10-10 Wenhao Li , Yuxin Zhang , Gen Luo , Haiyuan Wan , Ziyang Gong , Fei Chao , Rongrong Ji

Disaggregated inference has become an essential framework that separates the prefill (P) and decode (D) stages in large language model inference to improve throughput. However, the KV cache transfer faces significant delays between prefill…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-08 Weiqing Li , Guochao Jiang , Xiangyong Ding , Zhangcheng Tao , Chuzhan Hao , Chenfeng Xu , Yuewei Zhang , Hao Wang

Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but their inference cost is dominated by decoding, where each new token must attend to the entire…

Computation and Language · Computer Science 2026-05-05 Hossein Entezari Zarch , Lei Gao , Chaoyi Jiang , Murali Annavaram

Long-form video question answering (VQA) overwhelms current vision-language models (VLMs) because attention and key-value (KV) caches grow with runtime, forcing either expensive inference or near-sighted sliding windows. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Shrenik Patel , Daivik Patel

Efficient long-sequence generation is a critical challenge for Large Language Models. While recent sparse decoding methods improve efficiency, they suffer from KV cache misalignment, where approximation errors accumulate and degrade…

Computation and Language · Computer Science 2025-06-06 Yutao Sun , Tianzhu Ye , Li Dong , Yuqing Xia , Jian Chen , Yizhao Gao , Shijie Cao , Jianyong Wang , Furu Wei

Reasoning large language models exhibit complex reasoning behaviors via extended chain-of-thought generation that are highly fragile to information loss during decoding, creating critical challenges for KV cache compression. Existing…

Computation and Language · Computer Science 2026-05-28 Wenjie Du , Li Jiang , Keda Tao , Xue Liu , Huan Wang