English
Related papers

Related papers: CompilerKV: Risk-Adaptive KV Compression via Offli…

200 papers

Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks, yet deploying them on mobile, embedded, and edge devices remains particularly challenging. On-device LLM inference is…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Sayed Pedram Haeri Boroujeni , Niloufar Mehrabi , Patrick Woods , Gabriel Hillesheim , Abolfazl Razi

The linear growth of Key-Value (KV) cache remains a bottleneck for multi-turn LLM deployment. Existing KV cache compression methods often fail to account for the structural properties of multi-turn dialogues, relying on heuristic eviction…

Computation and Language · Computer Science 2026-01-30 Hong Chen , Xiang Liu , Bo Wang , Yuxuan Fan , Yuanlin Chu , Zongluo Li , Xiaowen Chu , Xuming Hu

Sub-token routing provides a finer compression axis for transformer efficiency than the coarse units used in most prior work, such as tokens, pages, heads, or layers. In this paper, we study routing within a token representation itself in…

Machine Learning · Computer Science 2026-05-07 Wei Jiang , Wei Wang

Scaling large language models to long contexts is challenging due to the quadratic computational cost of full attention. Mitigation approaches include KV-cache selection or compression techniques. We instead provide an effective and…

Machine Learning · Computer Science 2026-04-24 Yuzhen Mao , Michael Y. Li , Emily B. Fox

KV cache growth is a major bottleneck for long-context inference in large language models. Existing methods are often dominated by binary eviction or representation approximation, which may underutilize tokens that are not critical for…

Machine Learning · Computer Science 2026-05-25 Yuping Lin , Jiayuan Ding , Yue Xing , Pengfei He , Jiliang Tang , Subhabrata Mukherjee

Retrieval-Augmented Generation (RAG) enhances coding tasks by incorporating retrieved code examples into prompts. However, lengthy prompts, often exceeding tens of thousands of tokens, introduce challenges related to limited context windows…

Software Engineering · Computer Science 2026-04-13 Pengfei He , Shaowei Wang , Tse-Hsun Chen

Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality content generation with substantially fewer decoding steps. However, existing VAR models suffer from significant attention complexity and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Ziran Qin , Youru Lv , Mingbao Lin , Hang Guo , Zeren Zhang , Danping Zou , Weiyao Lin

Efficient state restoration in multi-turn conversations with large language models (LLMs) remains a critical challenge, primarily due to the overhead of recomputing or loading full key-value (KV) caches for all historical tokens. To address…

Computation and Language · Computer Science 2025-08-27 Junyi Wen , Junyuan Liang , Zicong Hong , Wuhui Chen , Ting Cai , Zibin Zheng

Speculative decoding accelerates LLM inference, but SOTA hidden-state-based drafters suffer from long-range decay: draft accuracy degrades as the speculative step increases. Existing work attributes this decay to train-inference mismatch…

Computation and Language · Computer Science 2026-05-12 Tianyu Liu , Yuhao Shen , Xinyi Hu , Baolin Zhang , Hengxin Zhang , Jun Dai , Jun Zhang , Shuang Ge , Lei Chen , Yue Li , MingCheng Wan

The large size of the KV cache has become a major bottleneck for serving LLMs with increasing context lengths. In response, many KV cache compression methods, such as token dropping and quantization, have been proposed. However, almost all…

Hardware Architecture · Computer Science 2026-05-19 Jiayi Yao , Samuel Shen , Kuntai Du , Shaoting Feng , Dongjoo Seo , Rui Zhang , Yuyang Huang , Yuhan Liu , Shan Lu , Junchen Jiang

Graphical user interface (GUI) agents built on vision-language models have emerged as a promising approach to automate human-computer workflows. However, they also face the inefficiency challenge as they process long sequences of…

Computation and Language · Computer Science 2025-10-02 Kung-Hsiang Huang , Haoyi Qiu , Yutong Dai , Caiming Xiong , Chien-Sheng Wu

The increasing input sequence length in Large Language Models (LLMs) puts significant pressure on key-value (KV) cache storage, making efficient inference challenging. Explicitly distinguishing attention behavior into our self-defined…

Computation and Language · Computer Science 2025-08-25 Mengjie Li , William J. Song

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

Large language models (LLMs) have shown strong performance across diverse tasks, but their inference with long input contexts is bottlenecked by memory size and bandwidth. The Key-Value (KV) cache size grows linearly with sequence length…

Machine Learning · Computer Science 2026-05-12 Junkai Zhang , Hang Guo , Luca Benini , Yawei Li

Under modern test-time compute and agentic paradigms, language models process ever-longer sequences. Efficient text generation with transformer architectures is increasingly constrained by the Key-Value cache memory footprint and bandwidth.…

Large language models (LLMs) are widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant deployment challenges, primarily due to the KV cache whose size…

Machine Learning · Computer Science 2026-03-10 Guangda Liu , Chengwei Li , Zhenyu Ning , Jing Lin , Yiwu Yao , Danning Ke , Minyi Guo , Jieru Zhao

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

Cross-layer key-value (KV) compression has been found to be effective in efficient inference of large language models (LLMs). Although they reduce the memory consumption of the KV cache, such methods usually introduce non-negligible…

Computation and Language · Computer Science 2026-04-16 You Wu , Ziheng Chen , Yizhen Zhang , Haoyi Wu , Chengting Yu , Yuchi Xu , Wenbo Su , Bo Zheng , Kewei Tu

Large Language Models (LLMs) are increasingly deployed in multi-turn conversational applications, where the management of the Key-Value (KV) Cache presents a significant bottleneck. The linear growth of the KV Cache with dialogue history…

Computation and Language · Computer Science 2025-10-09 Xiang Liu , Hong Chen , Xuming Hu , Xiaowen Chu

Large language models (LLMs) inference relies heavily on KV-caches to accelerate autoregressive decoding, but the resulting memory footprint grows rapidly with sequence length, posing significant efficiency challenges. Current KV-cache…

Databases · Computer Science 2025-09-04 Chenxia Tang , Jianchun Liu , Hongli Xu , Liusheng Huang
‹ Prev 1 8 9 10 Next ›