1
GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries
提出GaugeQuant方法,利用LLM对称性在线学习量化最优基,提升大模型压缩效率。
arXiv:2607.20757v1 Announce Type: new Abstract: Transformers are known to have internal continuous symmetries that leave outputs invariant, while modi…