huawei-csl/SINQ

Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method designed to make any Large Language Model smaller while preserving accuracy [ICML 2026]

4 best points · 1 comments · 1 Hacker News post · 635 GitHub stars · View on GitHub

Hacker News discussions

• Sinkhorn: Make LLMs even smaller through quantisation while maintaining accuracy (4 points, 1 comments, by ilitirit, 2025-10-04)