Metraipolis › archive › dc_7b385a4ef77c
EvoCache: Accelerating Browser Large Language Model Delivery with Public Cache Anchors — arXiv:2611.04638
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04638
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:45:42.716Z
- SHA-256 of the archived text
bc6865bd5f5d503dd3881e12cfac0e2351c55029abf18ee609f245f023f61121- Stable URL of this page
https://metraipolis.com/documento/dc_7b385a4ef77c
How to cite
EvoCache: Accelerating Browser Large Language Model Delivery with Public Cache Anchors — arXiv:2611.04638 — arXiv (en), https://arxiv.org/abs/2611.04638 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b385a4ef77c (Metraipolis archive dc_7b385a4ef77c, sha256 bc6865bd5f5d503dd3881e12cfac0e2351c55029abf18ee609f245f023f61121)
BibTeX
@misc{dc7b385a4ef77c,
title = {EvoCache: Accelerating Browser Large Language Model Delivery with Public Cache Anchors — arXiv:2611.04638},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04638},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b385a4ef77c; sha256 bc6865bd5f5d503dd3881e12cfac0e2351c55029abf18ee609f245f023f61121},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04638. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Language Models (LLMs) can run directly in a browser, but first use typically requires downloading model files that are hundreds of MiB or even several GiB in size. The same LLM is often repackaged by different publishers; these files share substantial content, yet byte differences prevent whole-file caches from reusing them. We propose EvoCache, a browser-managed LLM delivery system. EvoCache uses public cache anchors that are stored in advance by the browser and independent of browsing history to reconstruct losslessly the publisher version requested by a site. A site specifies only the target, while the browser selects the anchor and performs reconstruction, keeping both hidden from the site. An audit of 1,000 public repositories finds that 61 of the 100 most popular LLMs are offered by multiple publishers and that 98.1% of overlapping versions cannot be reused by whole-file caching. Across 23 cross-publisher model-package pairs, EvoCache achieves a median traffic reduction of 77.3% and outperforms every comparator. Across 240 real end-to-end browser experiments, EvoCache reduces network traffic by 78.9% and page-ready time by 64.2% relative to ordinary full downloads. For cached data left by other sites, EvoCache also protects users' cross-site cache privacy by using the same return time for cache hits and misses. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2611.04638 — 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 2026-11-04T21:36:19.379Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).