AI.news
主页教程研究工具模型AI创业讨论新闻每日简报WIKI🚀 创业库★ 投稿
AI+医疗机器人教育金融能源健康娱乐思考

Enabling KV Caching of Shared Prefix for Diffusion Language Models

arxiv.org
分享

View PDF HTML (experimental)

Abstract:Key-value (KV) caching for shared prefixes is essential for high-throughput large language model (LLM) serving, but it faces critical challenges in emerging diffusion language models (DLMs). In DLMs, bidirectional attention means that updating any token dynamically alters the entire context and its corresponding KVs. Thus, existing caching techniques developed for LLMs, which assume that KVs remain invariant once computed, corrupt the shared prefix KVs. Our experiments show that applying these techniques to DLMs causes model accuracy to collapse to near zero.
To unlock high-throughput DLM serving, we propose bidirectional prefix caching, bicache, the first KV caching technique for shared prefixes in DLMs. bicache is designed based on key observations from our comprehensive analysis: shared prefix KVs remain stable and reusable in shallow layers, while the depth of shallow layers depends on the fraction of shared prefix tokens in each request. Thus, bicache dynamically identifies a safe layer depth for reusing shared prefix KVs and eliminates redundant computation. Evaluations demonstrate that bicache significantly improves serving throughput by 36.3%-98.3% compared to existing techniques without accuracy collapse (only 0-1.8% difference).

Submission history

From: Jaehoon Han [view email]
[v1] Tue, 26 May 2026 05:27:57 UTC (428 KB)