# KVarN：方差归一化的KV-Cache量化方法可缓解推理任务中的误差累积

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-02 08:00
- AIHOT 分数：68
- AIHOT 链接：https://aihot.virxact.com/items/cmpy8j6nn02r5slaxrn2t6raa
- 原文链接：https://arxiv.org/abs/2606.03458

## AI 摘要

KVarN是一种免校准的KV-cache量化方法，通过Hadamard旋转结合双标度方差归一化，同时对K和V矩阵的两个轴进行归一化，以修复异常token尺度误差，大幅减少自回归解码中量化误差随时间步的累积。在2-bit精度下，KVarN在MATH500、AIME24和HumanEval等生成基准上达到新的SOTA。该方法的vLLM实现已在GitHub开源。

## 正文

Test-time scaling is a powerful approach to obtain better reasoning in large language models, but it becomes memory-bottlenecked during long-horizon decoding, as the KV-cache grows. KV-cache quantization can help improve this, but current methods are evaluated under prefill-like settings and errors behave differently under autoregressive decoding. We show that in the latter regime, quantization errors accumulate across timesteps, driven primarily by incorrect token scales. We introduce KVarN, a calibration-free KV-cache quantizer that applies a Hadamard rotation followed by a dual-scaling variance normalization across both axes of the K and V matrices. We find that this combination fixes outlying token-scale errors and substantially reduces error accumulation over existing baselines. KVarN establishes a new state-of-theart for KV-cache quantization on generative benchmarks, including MATH500, AIME24 and HumanEval, at 2-bit precision. A vLLM implementation of the KVarN method is available at https://github.com/huawei-csl/KVarN