TGV-KV: Text-Grounded KV Eviction for Vision-Language Models

摘要

Vision-Language Models (VLMs) inherit the auto-regressive generation paradigm and cache the keys and values (KV) of all previous tokens to accelerate inference, resulting in memory consumption that scales linearly with context length. This issue is particularly pronounced in VLMs due to substantial redundancy in the visual modality. Although KV cache eviction approaches can effectively reduce inference memory, they often incur significant performance degradation in VLMs, as most are designed for language models and overlook the inherent gap between text and vision. By systematically analyzing the modality gap in VLMs in this work, we argue that the importance of visual information should be grounded in textual guidance and accordingly propose a **T**ext-**G**rounded KV Eviction method for **V**LMs (**TGV-KV**). TGV-KV comprises three submodules: *(1) Text-Vision Budgeting (TVB)* assigns budget to each layer based on the mutual information interaction. *(2) Text-Weighted Ranking (TWR)* assesses the priority of text and ranks vision importance based on weighted text-image attention. *(3) Text-Prioritised Retention (TPR)* policy strategically preserves text KV to avoid acute information loss. We evaluate TGV-KV across five models with different sizes and architectures, showing that TGV-KV preserves 99.2\% accuracy on the VizWiz-VQA task with LLaVA-NeXT and boosts decode throughput by 52.6\% with an extreme retention budget of 5\%. Code will be released.