SpecCache: Speculative KV Cache Reuse for Efficient RAG Serving
Zijian Wen, Tao Zhang University of Science and Technology of China, Shuangwu Chen, Shenghao Ye University of Science and Technology of China, Yu Guo University of Science and Technology of China, Qirui Chen University of Science and Technology of China, Jingxian Shuai, Yunpeng Hou 等 10 位作者
原文摘要
Retrieval-Augmented Generation (RAG) significantly enhances LLMs but faces high prefill latency during long-context processing. While KV cache reuse can mitigate this, current methods relying on shallow features or static heuristics often fail to identify critical tokens for recomputation, resulting in generation quality degradation.We have an insight that KV deviations are more pronounced in deep layers.However, directly extracting deep-layer features from the target model is computationally prohibitive. Crucially, we find that the deep-layer features of a lightweight speculative model exhibit strong consistency with the target model in the selection of critical tokens for recomputation.In light of these insights, we propose SpecCache, which employs deep-layer hidden-state norms from a speculative model as a proxy to guide the critical token selection for target large model.Experiments demonstrate that SpecCache outperforms state-of-the-art (SOTA) baselines. Compared to full KV recomputation, it reduces time-to-first-token (TTFT) by 2.17-3.95\times and increases inference throughput by 2.7-5.2\times, with negligible degradation in generation quality relative to full recomputation.
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表