1
CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs
被ICML 2026接收为oral，提出一种兼顾成本与精度的三元量化新方法，为大模型高效部署提供突破。
arXiv:2606.26650v1 Announce Type: cross Abstract: In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing a…