# DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing

Source: [DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing](<https://www.sota2.com/research/paper/69e85bed7d0172140ec811de>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-07T05:00:04.653Z

Authors: Jinyu Guo, Zhihan Zhang, Jiehui Xie, Md. Tamim Iqbal, Dongshen Han, Lik-Hang Lee, Sung-Ho Bae, Jie Zou, Yang Yang, Chaoning Zhang

Published: 2026-04-21T11:33:24.000Z

## Abstract

The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing KV cache compression methods alleviate memory pressure, they often sacrifice generation quality and fail to address the high overhead of floating-point arithmetic. This paper introduces DASH-KV, an innovative acceleration framework that reformulates attention as approximate nearest-neighbor search via asymmetric deep hashing. Under this paradigm, we design an asymmetric encoding architecture that differentially maps queries and keys to account for their distinctions in precision and reuse characteristics. To balance efficiency and accuracy, we further introduce a dynamic mixed-precision mechanism that adaptively retains full-precision computation for critical tokens. Extensive experiments on LongBench demonstrate that DASH-KV significantly outperforms state-of-the-art baseline methods while matching the performance of full attention, all while reducing inference complexity from O(N^2) to linear O(N).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Long-context language understanding on LongBench (7-Metric Subset: NQ, HQ, QM, MN, GR, TQ, Avg)](<https://www.sota2.com/research/sota/long-context-language-understanding-on-longbench-7-metric-subset-nq-hq-qm-mn-gr-tq-avg.md>): Long-context Language Understanding; LongBench; NQ Score: 29.52.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.19351>)

[PDF](<https://arxiv.org/pdf/2604.19351.pdf>)
