Product-Aware Deterministic Rounding for Quantized Matrix Multiplication
Scalar rounding decisions interact through matrix multiplication. We study deterministic product-aware rounding after scales, clipping bounds, and grids are fixed, with each active scalar choosing between adjacent levels.
By Piyush Sao, Narasinga Miniskar, Pedro Valero-Lara, Keita Teranishi, Sudip SealarXiv cs.LG
Read the full story
Originally published by arXiv cs.LG on Sep 30, 2026.
Comments
Sign in to join the discussion.