ZipLLM: Efficient LLM Storage via Model-Aware Synergistic Data Deduplication and Compression · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2505.06252/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTZipLLM: Efficient LLM Storage via Model-Aware Synergistic Data Deduplication and Compression — mentioned by SirMadamhttps://news.ycombinator.com/item?id=48638119urn:hackerpapers:mention:2505.06252:48638119Mon, 22 Jun 2026 23:44:55 GMT<p>SOTA LLM specific compression achieves around ~54%! https://arxiv.org/abs/2505.06252v3</p><p><a href="https://hackerpaper.kaipfister.de/p/2505.06252/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.DB