Metraipolis › archive › dc_989653aba7c9
NanoKV: High-Ratio KV Cache Compression for Autoregressive Video Generation — arXiv:2611.06377
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06377
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:30:03.416Z
- SHA-256 of the archived text
f6b6d8ab012fe3ddae1edb72ccfc2e4abc9665947c59c9d51193fe5e335e8746- Stable URL of this page
https://metraipolis.com/documento/dc_989653aba7c9
How to cite
NanoKV: High-Ratio KV Cache Compression for Autoregressive Video Generation — arXiv:2611.06377 — arXiv (en), https://arxiv.org/abs/2611.06377 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_989653aba7c9 (Metraipolis archive dc_989653aba7c9, sha256 f6b6d8ab012fe3ddae1edb72ccfc2e4abc9665947c59c9d51193fe5e335e8746)
BibTeX
@misc{dc989653aba7c9,
title = {NanoKV: High-Ratio KV Cache Compression for Autoregressive Video Generation — arXiv:2611.06377},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06377},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_989653aba7c9; sha256 f6b6d8ab012fe3ddae1edb72ccfc2e4abc9665947c59c9d51193fe5e335e8746},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06377. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Autoregressive video models rely on historical key-value (KV) caches to preserve scene consistency over extended rollouts, making KV storage and repeated attention over history a growing memory and computational bottleneck. Aggressive compression can degrade generation quality, while reconstructing full-dimensional KV leaves attention computation largely unchanged. We introduce NanoKV, a frozen-backbone framework for generation-aware high-ratio KV compression. NanoKV exploits redundancy across tokens and attention heads by storing shared content in cluster centers and encoding joint head-channel residuals into low-bit coefficients. Crucially, NanoKV uses different fitting objectives for Keys and Values according to their distinct roles in attention: Key decoders are optimized to preserve downstream block outputs, whereas Value encoders and decoders are fitted for faithful reconstruction through the deployed quantization path. Building on the same compressed representation, the optional NanoKV-Fast variant reuses the stored coefficients for mixed-dimensional attention, reducing computation without modifying the video backbone. Across three autoregressive video backbones, NanoKV consistently improves the quality-storage trade-off. On HY-WorldPlay, NanoKV achieves $26.09\times$ effective KV compression, nearly twice that of KVTC, while improving PSNR by 1.0 dB. NanoKV-Fast retains $20.53\times$ effective compression and achieves an approximately $1.15\times$ end-to-end speedup over KVTC. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.06377 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-05T18:19:49.057Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).