PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration 文章

ArXiv CS.CL2026-06-08NEWSen作者: Songhao Wu, Ang Lv, Xiao Feng, Yufei Zhang, Xun Zhang, Guojun Yin, Wei Lin, Rui Yan

PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration · 相关技术