UniCache: Task- and Type-Aware KV Cache Compression for Unified Multimodal Models

arXiv:2609.32831v1 Announce Type: new Abstract: 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 5imes KV cache compression for understanding and editing and 2.5imes for generation with negligible quality loss, while increasing throughput by up to 1.78imes in long-context settings, significantly improving the practicality of scaling unified multimodal models to longer context.

Source: arXiv cs.LG | 2026-09-29