# Fathom：面向卸载 KV Cache 稀疏解码的按查询读取深度方案

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-15 08:00
- AIHOT 分数：41
- AIHOT 链接：https://aihot.news/items/cmu5hmk750656roqodw7ehnh3
- 原文链接：https://arxiv.org/abs/2609.17652

## AI 摘要

Fathom 是一种按查询决定每个 key 通道读取位数的稀疏解码扫描方法，将 4-bit K cache 按通道主序存为 bit plane，查询通过反向注水分配位预算。

## 正文

When agentic sessions run to a million tokens with many sessions resident at once, the KV cache and the index that ranks it live in host memory, and the scan that ranks all n keys for a top-k step becomes the traffic that bounds decoding. We present Fathom, a key scan in which each query decides how many bits of each key channel to read. The 4-bit K cache is stored channel-major as bit planes, so a prefix of t planes is exactly the channel's t-bit quantizer, and the query spends its bit budget by reverse water-filling over the variance-weighted importance of its channels.

At one million tokens on Qwen3-8B a decode step is 1.67x faster in GPU time than with the 136-bit scans of Double Sparsity, Loki and SparQ r=32, and in the same GPU time as SparQ's 68-bit read (r=16) Fathom reads 18% fewer bytes with lower attention error on six of seven model and context settings. On RULER-style tasks every per-token scan matches exact top-k decoding, and on real coding-agent sessions Fathom reaches the step agreement of the most accurate 136-bit scan at 92 bits. The store is the 4-bit K copy a quantized serving stack already holds, and the method is not faster when the index is resident in GPU memory.