English
Related papers

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

200 papers

The quadratic complexity of Multimodal Large Language Models (MLLMs) with respect to context length poses significant computational and memory challenges, hindering their real-world deployment. In the paper, we devise a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Yuhang Han , Xuyang Liu , Zihan Zhang , Pengxiang Ding , Junjie Chen , Donglin Wang , Honggang Chen , Qingsen Yan , Siteng Huang

Multimodal Large Language Models (MLLMs) have advanced unified reasoning over text, images, and videos, but their inference is hindered by the rapid growth of key-value (KV) caches. Each visual input expands into thousands of tokens,…

Artificial Intelligence · Computer Science 2026-04-08 Bowen Zeng , Feiyang Ren , Jun Zhang , Xiaoling Gu , Ke Chen , Lidan Shou , Huan Li

KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mechanism to detect or…

Machine Learning · Computer Science 2026-05-21 Dean Calver

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

Prefix caching is a key optimization in Large Language Model (LLM) serving, reusing attention Key-Value (KV) states across requests with shared prompt prefixes to reduce expensive prefill computation. However, its benefit depends critically…

Machine Learning · Computer Science 2026-05-20 Shaoke Fang , Ziang Li , Wenfei Wu , Jiatong Ji , Qingsong Liu , Ruizhi Pu

Generating long sequences of tokens given a long-context input is a very compute-intensive inference scenario for large language models (LLMs). One prominent inference speed-up approach is to construct a smaller key-value (KV) cache,…

Computation and Language · Computer Science 2025-03-04 Fangyuan Xu , Tanya Goyal , Eunsol Choi

Large language models (LLMs) are often used for infilling tasks, which involve predicting or generating missing information in a given text. These tasks typically require multiple interactions with similar context. To reduce the computation…

Computation and Language · Computer Science 2025-05-30 Tianyu Guo , Hande Dong , Yichong Leng , Feng Liu , Cheater Lin , Nong Xiao , Xianwei Zhang

Transformer-based large language models (LLMs) have already achieved remarkable results on long-text tasks, but the limited GPU memory (VRAM) resources struggle to accommodate the linearly growing demand for key-value (KV) cache as the…

Computation and Language · Computer Science 2025-03-21 Shibo Jie , Yehui Tang , Kai Han , Zhi-Hong Deng , Jing Han

Large Language Models (LLMs) have gained popularity in recent years, driving up the demand for inference. LLM inference is composed of two phases with distinct characteristics: a compute-bound prefill phase followed by a memory-bound decode…

Hardware Architecture · Computer Science 2025-10-10 Hengrui Zhang , Pratyush Patel , August Ning , David Wentzlaff

The increasing size of the Key-Value (KV) cache during the Large Language Models long-context inference is the main obstacle for its balance between the deployment cost and task accuracy. To reduce the KV cache size in such scenarios, most…

Machine Learning · Computer Science 2025-07-25 Manlai Liang , JiaMing Zhang , Xiong Li , Jinlong Li

Large Language models (LLMs) have become a research hotspot. To accelerate the inference of LLMs, storing computed caches in memory has become the standard technique. However, as the inference length increases, growing KV caches might lead…

Computation and Language · Computer Science 2024-12-13 Meizhi Zhong , Xikai Liu , Chen Zhang , Yikun Lei , Yan Gao , Yao Hu , Kehai Chen , Min Zhang

This work studies how to adaptively recompute key-value (KV) caches for diffusion large language models (DLMs) to maximize prediction accuracy while minimizing decoding latency. Prior methods' decoders recompute QKV for all tokens at every…

Computation and Language · Computer Science 2025-12-30 Quan Nguyen-Tri , Mukul Ranjan , Zhiqiang Shen

Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token-oriented methods, such as pruning and skipping, have shown great promise in reducing inference…

Computation and Language · Computer Science 2026-02-03 Zimeng Wu , Donghao Wang , Chaozhe Jin , Jiaxin Chen , Yunhong Wang

Video large language models (VideoLLMs) show strong capability in video understanding, yet long-context inference is still dominated by massive redundant visual tokens in the prefill stage. We revisit token compression for VideoLLMs under a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Xinying Lin , Xuyang Liu , Yiyu Wang , Teng Ma , Wenqi Ren

Visual token pruning is a promising approach for reducing the computational cost of vision-language models (VLMs), and existing methods often rely on early pruning decisions to improve efficiency. While effective on coarse-grained reasoning…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Chen Qian , Xinran Yu , Danyang Li , Guoxuan Chi , Zheng Yang , Qiang Ma , Xin Miao

The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing KV cache compression methods alleviate memory pressure, they…

Computation and Language · Computer Science 2026-05-06 Jinyu Guo , Zhihan Zhang , Jiehui Xie , Md. Tamim Iqbal , Dongshen Han , Lik-Hang Lee , Sung-Ho Bae , Jie Zou , Yang Yang , Chaoning Zhang

Vision-Language Models (VLMs) have demonstrated strong capabilities in multimodal understanding and generation tasks. However, their application to long video understanding remains hindered by the quadratic complexity of standard attention…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Letian Kang , Shixian Luo , Yiqiang Li , Yuxin Yin , Shenxuan Zhou , Xiaoyang Yu , Jin Yang , Yong Wu

Speculative decoding is a widely adopted technique for accelerating inference in large language models (LLMs), yet its application to vision-language models (VLMs) remains underexplored, with existing methods achieving only modest speedups…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Jialiang Kang , Han Shu , Wenshuo Li , Yingjie Zhai , Xinghao Chen

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Computation and Language · Computer Science 2024-01-04 Coleman Hooper , Sehoon Kim , Hiva Mohammadzadeh , Hasan Genc , Kurt Keutzer , Amir Gholami , Sophia Shao

As Large Language Models (LLMs) scale to longer context windows, the computational cost of attention mechanisms, which traditionally grows quadratically with input length, presents a critical challenge for real-time and memory-constrained…

Computation and Language · Computer Science 2024-12-10 James Vo