UniCache：面向统一多模态模型的 KV 缓存压缩框架
UniCache: Task- and Type-Aware KV Cache Compression for Unified Multimodal Models
一帮研究者做了个叫 UniCache 的免训练压缩框架，多模态模型缓存能压 5 倍，长上下文吞吐还能快 1.78 倍，做部署的可以看看。
UniCache 是一个无需训练的 KV 缓存压缩框架，针对统一多模态模型中理解、生成、编辑任务各自激活不同缓存类型的问题，通过离线校准为各任务分配差异化的压缩策略。实验显示，理解和编辑任务可实现 5 倍 KV 缓存压缩，生成任务为 2.5 倍，质量损失可忽略。在长上下文场景下，吞吐量最高提升 1.78 倍。
UniCache: Task- and Type-Aware KV Cache Compression for Unified Multimodal Models
Unified multimodal models combine understanding, generation, and editing within a single network, offering a promising foundation for versatile multimodal applications. However, growing multimodal contexts make KV cache storage and access increasingly costly. Existing KV cache compression methods are typically tailored to specific tasks and single-modality caches, while overlooking changes in cache importance across tasks and timesteps. However, in unified multimodal models, each task involves multiple KV cache types, and both their composition and dynamics differ across tasks. As a result, a single compression policy overlooks task- and type-specific requirements, leading to the loss of critical information and degraded quality across tasks. Based on these findings, we propose UniCache, a training-free framework for task- and type-aware KV cache compression. UniCache identifies the cache segments activated by each task and assigns suitable compression policies through offline calibration. It coordinates their parallel execution under a shared storage budget through attention-guided allocation and task-aware temporal scheduling. Experiments show that UniCache achieves $5\times$ KV cache compression for understanding and editing and $2.5\times$ for generation with negligible quality loss, while increasing throughput by up to $1.78\times$ in long-context settings, significantly improving the practicality of scaling unified multimodal models to longer context.
