QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models

arXiv:2310.08041v2 Announce Type: replace-cross
Abstract: Large Language Models (LLMs) excel in NLP, but their demands hinder their widespread deployment. While Quantization-Aware Training (QAT) offers a solution, its extensive training costs make Post-Training Quantization (PTQ) a more practical approach for LLMs. In existing studies, activation outliers in particular channels are identified as the bottleneck to PTQ accuracy. They propose to transform the magnitudes from activations to weights, which however offers limited alleviation or suffers from unstable gradients, resulting in a severe …

abstract arxiv costs cs.ai cs.cl cs.lg deployment excel hinder language language models large language large language models llms low nlp outliers practical quantization solution studies training training costs type