Model-Preserving Adaptive Rounding 事件

Model-Preserving Adaptive Rounding arXiv:2505.22988v3 Announce Type: replace-cross Abstract: The goal of quantization is to produce a compressed model whose output distribution is as close to the original model's as possible. To do this tractably, most quantization algorithms minimize the immediate activation error of each layer as a proxy for the end-to-end error. However, this ignores the effect of future layers, making it a poor proxy. In this work, we introduce Yet Another Quantization Algo