Can I read PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration on EtoBox?

PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration by Wu, Songhao; Lv, Ang; Feng, Xiao; Zhang, Yufei; Zhang, Xun; Yin, Guojun; Lin, Wei; Yan, Rui is a scholarly article available to read on EtoBox.

What is PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration about?

The KV cache in large language models is a dominant factor in memory usage, limiting their broader applicability. Quantizing the cache to lower bit widths is an effective way to reduce computational costs; however, previous methods struggle with quantizing key vectors due to outliers, resulting in excessive overhead. We propose a novel quantization approach called PolarQuant, which efficiently addresses the outlier challenge. We observe that outliers typically appear in only one of two dimensions, which are rotated together by a specific angle when rotary position embeddings are applied. When represented as two-dimensional vectors, these dimensions exhibit well-structured patterns, with radii and angles smoothly distributed in polar coordinates. This alleviates the challenge of outliers on per-channel quantization, making them well-suited for quantization. Thus, PolarQuant divides key vectors into groups of two-dimensional sub-vectors, encoding them as the corresponding quantized radius and the polar angle, rather than quantizing original key vectors directly. PolarQuant achieves the superior efficiency in KV cache quantization and accelerates the decoding process by turning the qu

Author

Wu, Songhao; Lv, Ang; Feng, Xiao; Zhang, Yufei; Zhang, Xun; Yin, Guojun; Lin, Wei; Yan, Rui

Published

2025

Language

EN