English
Related papers

Related papers: Shallow Prefill, Deep Decoding: Efficient Long-Con…

200 papers

Autoregressive large language models (LLMs) have made remarkable progress in various natural language generation tasks. However, they incur high computation cost and latency resulting from the autoregressive token-by-token generation. To…

Computation and Language · Computer Science 2023-07-07 Luciano Del Corro , Allie Del Giorno , Sahaj Agarwal , Bin Yu , Ahmed Awadallah , Subhabrata Mukherjee

Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…

Machine Learning · Computer Science 2026-04-20 Chuangtao Chen , Grace Li Zhang , Xunzhao Yin , Cheng Zhuo , Bing Li , Ulf Schlichtmann

Language models handle increasingly long contexts for tasks such as book summarization, but this leads to growing memory costs for the key-value (KV) cache. Many prior works have proposed ways of discarding KVs from memory, but their…

Computation and Language · Computer Science 2025-06-23 Adithya Bhaskar , Alexander Wettig , Tianyu Gao , Yihe Dong , Danqi Chen

Long-context Multimodal Large Language Models (MLLMs) demand substantial computational resources for inference as the growth of their multimodal Key-Value (KV) cache, in response to increasing input lengths, challenges memory and time…

Computation and Language · Computer Science 2024-06-27 Zhongwei Wan , Ziang Wu , Che Liu , Jinfa Huang , Zhihong Zhu , Peng Jin , Longyue Wang , Li Yuan

Multimodal latent reasoning has emerged as a promising paradigm that replaces explicit Chain-of-Thought (CoT) decoding with implicit feature propagation, simultaneously enhancing representation informativeness and reducing inference…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Yudong Han , Yong Wang , Zaiquan Yang , Zhen Qu , Liyuan Pan , Xiangxiang Chu

The widespread of Large Language Models (LLMs) marks a significant milestone in generative AI. Nevertheless, the increasing context length and batch size in offline LLM inference escalate the memory requirement of the key-value (KV) cache,…

Hardware Architecture · Computer Science 2024-09-10 Xiurui Pan , Endian Li , Qiao Li , Shengwen Liang , Yizhou Shan , Ke Zhou , Yingwei Luo , Xiaolin Wang , Jie Zhang

The key-value (KV) cache is a major bottleneck in long-context inference, where memory and computation grow with sequence length. Existing KV eviction methods reduce this cost but typically degrade performance relative to full-cache…

Machine Learning · Computer Science 2026-05-12 Ngoc Bui , Hieu Trung Nguyen , Arman Cohan , Rex Ying

KV caches, typically used only to speed up autoregressive decoding, encode contextual information that can be reused for downstream tasks at no extra cost. We propose treating the KV cache as a lightweight representation, eliminating the…

Computation and Language · Computer Science 2026-01-29 Zeyu Xing , Xing Li , Hui-Ling Zhen , Mingxuan Yuan , Sinno Jialin Pan

The Key-Value (KV) cache in generative large language models (LLMs) introduces substantial memory overhead. Existing works mitigate this burden by offloading or compressing the KV cache. However, loading the entire cache incurs significant…

Computation and Language · Computer Science 2025-05-28 Dingyu Yao , Bowen Shen , Zheng Lin , Wei Liu , Jian Luan , Bin Wang , Weiping Wang

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-16 Ziyi Zhang , Ziheng Jiang , Chengquan Jiang , Menghan Yu , Size Zheng , Haibin Lin , Henry Hoffmann , Xin Liu

Large language models and large multimodal models (LLMs and LMMs) deliver strong generative performance but suffer from slow decoding, a problem that becomes more severe when handling visual inputs, whose sequences typically contain many…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Zihua Wang , Ruibo Li , Haozhe Du , Joey Tianyi Zhou , Yu Zhang , Xu Yang

Supporting long-context LLMs is challenging due to the substantial memory demands of the key-value (KV) cache. Existing offloading systems store the full cache in host memory and selectively fetch critical entries during decoding, but this…

Computation and Language · Computer Science 2026-05-19 Jian Lin , Jiazhi Mi , Zicong Hong , Haodong Wang , Qianli Liu , Haodyue Zhang , Peng Li , Song Guo

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

The Key-Value (KV) cache reading latency increases significantly with context lengths, hindering the efficiency of long-context LLM inference. To address this, previous works propose retaining a small fraction of KV cache based on token…

Databases · Computer Science 2025-09-18 Dongwei Wang , Zijie Liu , Song Wang , Yuxin Ren , Jianing Deng , Jingtong Hu , Tianlong Chen , Huanrui Yang

In this paper, we introduce LightVLM, a simple but effective method that can be seamlessly deployed upon existing Vision-Language Models (VLMs) to greatly accelerate the inference process in a training-free manner. We divide the inference…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Lianyu Hu , Fanhua Shang , Wei Feng , Liang Wan

Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long context inputs, but this comes at the cost of increased computational resources and latency. Our research introduces a novel approach for the long…

Computation and Language · Computer Science 2024-09-27 Zhenmei Shi , Yifei Ming , Xuan-Phi Nguyen , Yingyu Liang , Shafiq Joty

Efficient long-context inference in Large Language Models (LLMs) is severely constrained by the Key-Value (KV) cache memory wall, yet existing pruning methods force a choice between low-latency heuristics that sacrifice precision and…

Machine Learning · Computer Science 2026-05-19 Junjie Li , Jiong Lou , Jie Li

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

Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is enlarged. However, the batch size is limited by some…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-03-19 Jiaao He , Jidong Zhai

Multimodal Large Language Models face severe challenges in computational efficiency and memory consumption due to the substantial expansion of the visual KV cache when processing long visual contexts. Existing KV cache compression methods…

Machine Learning · Computer Science 2026-05-07 Sihao Liu , YuFan Xiong , Zhonghua Jiang , Zhaode Wang , chengfei lv Shengyu Zhang