English
Related papers

Related papers: Meta-Soft: Leveraging Composable Meta-Tokens for C…

200 papers

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

While Key-Value (KV) cache compression is essential for efficient LLM inference, current evaluations disproportionately focus on sparse retrieval tasks, potentially masking the degradation of High-Density Reasoning where Chain-of-Thought…

Computation and Language · Computer Science 2026-05-13 Xiang Liu , Zhenheng Tang , Hong Chen , Peijie Dong , Zeyu Li , Xiuze Zhou , Bo Li , Xuming Hu , Xiaowen Chu

Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows. However, hosting these models is cost-prohibitive mainly due to the…

Computation and Language · Computer Science 2024-08-09 Yilong Chen , Guoxia Wang , Junyuan Shang , Shiyao Cui , Zhenyu Zhang , Tingwen Liu , Shuohuan Wang , Yu Sun , Dianhai Yu , Hua Wu

Large Language Models (LLMs) require significant GPU memory when processing long texts, with the key value (KV) cache consuming up to 70\% of total memory during inference. Although existing compression methods reduce memory by evaluating…

Computation and Language · Computer Science 2025-10-15 Xiang Liu , Zhenheng Tang , Peijie Dong , Zeyu Li , Yue Liu , Bo Li , Xuming Hu , Xiaowen Chu

Large language models (LLMs) often incorporate multiple text chunks in their inputs to provide the necessary contexts. To speed up the prefill of the long LLM inputs, one can pre-compute the KV cache of a text and re-use the KV cache when…

Machine Learning · Computer Science 2025-04-07 Jiayi Yao , Hanchen Li , Yuhan Liu , Siddhant Ray , Yihua Cheng , Qizheng Zhang , Kuntai Du , Shan Lu , Junchen Jiang

As large language models (LLMs) continue to advance, the demand for higher quality and faster processing of long contexts across various applications is growing. KV cache is widely adopted as it stores previously generated key and value…

Computation and Language · Computer Science 2025-02-28 Yingxin Li , Ye Li , Yuan Meng , Xinzhu Ma , Zihan Geng , Shutao Xia , Zhi Wang

While Large Language Models (LLMs) can theoretically support extensive context windows, their actual deployment is constrained by the linear growth of Key-Value (KV) cache memory. Prevailing compression strategies mitigate this through…

Artificial Intelligence · Computer Science 2026-02-03 Aryan Sood , Tanvi Sharma , Vansh Agrawal

Large Language Models (LLMs) encounter significant challenges in long-sequence inference due to computational inefficiency and redundant processing, driving interest in context compression techniques. Existing methods often rely on token…

Computation and Language · Computer Science 2025-05-22 Huanxuan Liao , Wen Hu , Yao Xu , Shizhu He , Jun Zhao , Kang Liu

The Key-Value (KV) cache is integral to efficient autoregressive inference in large language models (LLMs), yet its unbounded growth in stateful multi-turn scenarios presents major challenges. This paper examines the interplay between KV…

Machine Learning · Computer Science 2025-11-10 Pratik Poudel

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

Efficient long-context inference is critical as large language models (LLMs) adopt context windows of ranging from 128K to 1M tokens. However, the growing key-value (KV) cache and the high computational complexity of attention create…

Computation and Language · Computer Science 2025-03-13 Guangtao Wang , Shubhangi Upasani , Chen Wu , Darshan Gandhi , Jonathan Li , Changran Hu , Bo Li , Urmish Thakker

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

We describe KVLink, an approach for efficient key-value (KV) cache reuse in large language models (LLMs). In many LLM applications, different inputs can share overlapping context, such as the same retrieved document appearing in multiple…

Computation and Language · Computer Science 2025-11-11 Jingbo Yang , Bairu Hou , Wei Wei , Yujia Bao , Shiyu Chang

The growing memory footprint of the Key-Value (KV) cache poses a severe scalability bottleneck for long-context Large Language Model (LLM) inference. While KV cache eviction has emerged as an effective solution by discarding less critical…

Computation and Language · Computer Science 2025-10-28 Jinhan Chen , Jianchun Liu , Hongli Xu , Xianjun Gao , Shilong Wang

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

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

Recent large language model applications, such as Retrieval-Augmented Generation and chatbots, have led to an increased need to process longer input contexts. However, this requirement is hampered by inherent limitations. Architecturally,…

Artificial Intelligence · Computer Science 2024-08-14 Giulio Corallo , Paolo Papotti

Existing KV cache compression methods generally operate on discrete tokens or non-semantic chunks. However, such approaches often lead to semantic fragmentation, where linguistically coherent units are disrupted, causing irreversible…

Computation and Language · Computer Science 2026-03-17 Shunlong Wu , Hai Lin , Shaoshen Chen , Tingwei Lu , Yongqin Zeng , Shaoxiong Zhan , Hai-Tao Zheng , Hong-Gee Kim

Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Payal Fofadiya , Sunil Tiwari

The expanding long-context capabilities of large language models are constrained by a significant memory bottleneck: the key-value (KV) cache required for autoregressive generation. This bottleneck is substantial; for instance, a…

Computation and Language · Computer Science 2026-04-20 Yuxuan Zhu , David H. Yang , Mohammad Mohammadi Amiri , Keerthiram Murugesan , Tejaswini Pedapati , Pin-Yu Chen