OJBKQ : Objective-Joint Babai–Klein-Based Quantization ∗
OJBKQ is proposed, a layer-wise PTQ method that formulates weight quantization as a joint optimization problem over activations and weights, yielding a multiple-right-hand-side box-constrained integer least squares (BILS) problem per layer.
Xinyu Wang, Ziyu Zhao, Peng Lu et al.
· 0 citations