single mention ยท software implementation
ModelOpt AutoQuantize
ModelOpt AutoQuantize is a sensitivity-constrained mixed-precision search that replaces hand-authored layer rules for choosing quantization formats.1 For each quantizable module and candidate format it estimates a sensitivity from the quantization-induced output error weighted by the squared task-loss gradient, then assigns formats minimizing total sensitivity subject to a target effective bitwidth budget.2,3
How this definition was written
Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.
to replace hand-authored layer rules with a sensitivity- constrained mixed-precision search
โ NVIDIA Nemotron 3.5 Super and Lightning Technical Reportmin {๐๐} โ๏ธ ๐ ๐๐(๐๐)s.t. โ๏ธ ๐ ๐๐๐(๐๐)โค ยฏ๐
โ NVIDIA Nemotron 3.5 Super and Lightning Technical Report๐ is the target effective bitwidth
โ NVIDIA Nemotron 3.5 Super and Lightning Technical Report
Also called ModelOpt AutoQuantize (AutoQuant).
Filed under software implementation โบ kernel & quantization library