MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models
英文标题：MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models
arXiv:2607.22586v1 Announce Type: new Abstract: Key-Value (KV) caching is essential for efficient inference in multimodal large language models (MLLMs), yet its memory footprint grows linearly with context length and becomes a major bottleneck due to the large number of visual tokens. Recent prefil
打开原文相关 2.4 · 机会 0
2.1 KB
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2607.22586v1 Announce Type: new Abstract: Key-Value (KV) caching is essential for efficient inference in multimodal large language models (MLLMs), yet its memory footprint grows linearly with context length and becomes a major bottleneck due to the large number of visual tokens. Recent prefil
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×