PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers
This work introduces PrismQuant, a quantizer-aware rotation framework that aligns the leading activation eigenspace with the constant group subspace of asymmetric grouped INT4, and formulate rotation design as a Ky Fan trace maximization and derive a closed-form solution that is provably optimal for this alignment obje...
Yan-Long Chen, Yi-Ning Chen, Song Zhang et al.
· 0 citations