arXiv · 2611.09973
ReelCache: An Efficient KV Cache Compression and Management System for Multi-Round Video Generation
Abstract
Autoregressive video diffusion models produce large KV caches during multi-round video generation. Keeping all these KV chunks would consume substantial memory, while rebuilding discarded caches would significantly delay video chunk generation. This paper presents ReelCache, a KV cache compression system for efficient multi-round, long video generation. ReelCache combines an intra-chunk compressor with an inter-chunk cache manager. The compressor applies low-rank decomposition across channels and video coding to the resulting coefficients, predicting the decomposition rank per transformer layer online to meet retained-energy targets. The cache manager shares basis directions across consecutive chunks and organizes chunk states in a tree, allowing generation branches to share historical state while supporting restoration for resume, rewind, and fork. Experiments across five video generation models show that ReelCache reduces KV storage by 14.46-21.13x relative to baselines and accelerates next-chunk generation by 1.25-3.36x, with less than 1% drop in six representative VBench metrics. GitHub: https://github.com/Tianyu9748/ReelCache
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Tianyu Wang, Daiyang Yu, Zhiwei Ren, Junbo Li, Jitian Zhang, Longfei Shangguan. 2026-10-31. ReelCache: An Efficient KV Cache Compression and Management System for Multi-Round Video Generation. https://arxiv.org/abs/2611.09973
Cite the original work for its findings. Save a collection to share your selection of sources.