SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLM. (arXiv:2312.03788v1 [cs.LG]) Show more
http://arxiv.org/abs/2312.03788 #arXiv #NLProc
QOTO: Question Others to Teach Ourselves An inclusive, Academic Freedom, instance All cultures welcome. Hate speech and harassment strictly forbidden.
