English
Related papers

Related papers: Compressing KV Cache for Long-Context LLM Inferenc…

200 papers

Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similarity search, but key…

Computation and Language · Computer Science 2025-03-10 Giulio Corallo , Orion Weller , Fabio Petroni , Paolo Papotti

Recent advances in Large Language Models (LLMs) have highlighted the critical importance of extending context length, yet the quadratic complexity of attention mechanisms poses significant challenges for efficient long-context modeling. KV…

Computation and Language · Computer Science 2025-11-07 Wanyun Cui , Mingwei Xu

Recent large vision-language models (LVLMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet the resulting key-value (KV) cache expansion creates a critical memory bottleneck that fundamentally limits…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Xuyang Liu , Xiyan Gui , Yuchao Zhang , Linfeng Zhang

Long-context language modeling is increasingly constrained by the Key-Value (KV) cache, whose memory and decode-time access costs scale linearly with the prefix length. This bottleneck has motivated a range of context-compression methods,…

Machine Learning · Computer Science 2026-05-13 Yoav Gelberg , Yam Eitan , Michael Bronstein , Yarin Gal , Haggai Maron

Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Xihao Chen , Yangyang Guo , Roger Zimmermann

Long-context Large Language Models (LLMs) face significant memory bottlenecks during inference due to the linear growth of key-value (KV) cache with sequence length. While individual optimization techniques like KV cache quantization,…

Machine Learning · Computer Science 2025-12-02 Sai Gokhale , Devleena Das , Rajeev Patwari , Ashish Sirasao , Elliott Delaye

Modern large language models (LLMs) extend context lengths to millions of tokens, enabling coherent, personalized responses grounded in long conversational history. However, the Key-Value (KV) cache grows linearly with the extended dialogue…

Computation and Language · Computer Science 2026-05-21 Minsoo Kim , Arnav Kundu , Han-Byul Kim , Richa Dixit , Minsik Cho

Long-context LLMs demand accurate inference at low latency, yet decoding becomes primarily constrained by KV cache as context grows. Prior pruning methods are largely context-agnostic: their token selection ignores step-wise relevance and…

Artificial Intelligence · Computer Science 2026-02-25 Chao Fei , Guozhong Li , Chenxi Liu , Panos Kalnis

We introduce KV-Fold, a simple, training-free long-context inference protocol that treats the key-value (KV) cache as the accumulator in a left fold over sequence chunks. At each step, the model processes the next chunk conditioned on the…

Machine Learning · Computer Science 2026-05-13 Alireza Nadali , Patrick Cooper , Ashutosh Trivedi , Alvaro Velasquez

Recent advancements in Large Language Models (LLMs) have spurred interest in numerous applications requiring robust long-range capabilities, essential for processing extensive input contexts and continuously generating extended outputs. As…

Machine Learning · Computer Science 2025-07-22 Dachuan Shi , Yonggan Fu , Xiangchi Yuan , Zhongzhi Yu , Haoran You , Sixu Li , Xin Dong , Jan Kautz , Pavlo Molchanov , Yingyan , Lin

KV cache compression is critical for efficient long-context LLM inference. Approaches that reduce the per-pair footprint -- quantization and low-rank decomposition -- are orthogonal to those that reduce the sequence length of the cache.…

Machine Learning · Computer Science 2026-03-31 Bo Jiang , Sian Jin

Large language models (LLMs) represent a groundbreaking advancement in the domain of natural language processing due to their impressive reasoning abilities. Recently, there has been considerable interest in increasing the context lengths…

Machine Learning · Computer Science 2024-11-11 Utkarsh Saxena , Gobinda Saha , Sakshi Choudhary , Kaushik Roy

Long-context inference in decoder-only language models is costly because long prompts are processed during Prefill, cached at every layer, and repeatedly attended to during autoregressive Decode. We introduce \emph{Shallow Prefill, dEEp…

Artificial Intelligence · Computer Science 2026-05-08 Jungsuk Oh , Hyeseo Jeon , Hyunjune Ji , Kyongmin Kong , Jay-Yoon Lee

Long-running agentic tasks, such as deep research, require multi-hop reasoning over information distributed across multiple webpages and documents. In such tasks, the LLM context is dominated by tokens from external retrieval, causing…

Artificial Intelligence · Computer Science 2026-03-03 Sanjay Kariyappa , G. Edward Suh

Large Language Models capable of handling extended contexts are in high demand, yet their inference remains challenging due to substantial Key-Value cache size and high memory bandwidth requirements. Previous research has demonstrated that…

Machine Learning · Computer Science 2025-10-29 Junlin Mu , Hantao Huang , Jihang Zhang , Minghui Yu , Tao Wang , Yidong Li

Large language models have revolutionized data processing in numerous domains, with their ability to handle extended context reasoning receiving notable recognition. To speed up inference, maintaining a key-value (KV) cache memory is…

Computation and Language · Computer Science 2024-10-22 Zhen Yang , J. N. Han , Kan Wu , Ruobing Xie , An Wang , Xingwu Sun , Zhanhui Kang

Long Chain-of-Thought (CoT) reasoning has significantly advanced the capabilities of Large Language Models (LLMs), but this progress is accompanied by substantial memory and latency overhead from the extensive Key-Value (KV) cache. Although…

Machine Learning · Computer Science 2025-12-23 Tao Zhang , Ziqian Zeng , Hao Peng , Huiping Zhuang , Cen Chen

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

The impressive capabilities of Large Language Models (LLMs) come at the cost of substantial computational resources during deployment. While KV Cache can significantly reduce recomputation during inference, it also introduces additional…

Computation and Language · Computer Science 2025-05-19 Yi Su , Yuechi Zhou , Quantong Qiu , Juntao Li , Qingrong Xia , Ping Li , Xinyu Duan , Zhefeng Wang , Min Zhang

Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agentic intelligence and recommendation system. However, the…