VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration

29 October 2024

Papers citing "VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration"

7 / 7 papers shown

Title
MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention Yucheng Li Huiqiang Jiang Chengruidong Zhang Qianhui Wu Xufang Luo ... Amir H. Abdi Dongsheng Li Jianfeng Gao Yi Yang Lili Qiu 33 1 0 22 Apr 2025
AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference Kai Huang Hao Zou Bochen Wang Ye Xi Zhen Xie Hao Wang VLM 49 0 0 31 Mar 2025
Beyond Intermediate States: Explaining Visual Redundancy through Language Dingchen Yang Bowen Cao Anran Zhang Weibo Gu Winston Hu Guang Chen VLM 79 0 0 26 Mar 2025
AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding Xiao Wang Qingyi Si Jianlong Wu Shiyu Zhu Zheng Lin Liqiang Nie VLM 83 3 0 16 Mar 2025
Slim attention: cut your context memory in half without loss of accuracy -- K-cache is all you need for MHA Nils Graef Andrew Wasielewski 40 1 0 07 Mar 2025
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs Zeliang Zhang Yifan Zhu Susan Liang Zhiyuan Wang Jiani Liu ... Mingjie Zhao Chenliang Xu Kun Wan Wentian Zhao Wentian Zhao VLM MQ 43 0 0 15 Feb 2025
ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding Xiao Wang Qingyi Si Jianlong Wu Shiyu Zhu Zheng Lin Liqiang Nie VLM 82 6 0 29 Dec 2024