cs.DCNov 10, 2026

Can KV Cache Be Reused Across Model Updates? A DeepSeek-V4-Flash Case Study

Authors: Zhikun Tao, Fangyong Jin, Junping Zhao

Organizations: Rank Computing

Abstract

Reusing key--value (KV) caches across language model updates could avoid repeated computation of shared context, but changes in model weights raise a fundamental question about what these caches preserve. We investigate direct cache reuse across four model updates, with a detailed study of DeepSeek-V4-Flash to Flash-0731. Our central finding is that caches can retain useful task information without faithfully reproducing the updated model's behavior. Retrieval accuracy varies substantially across updates, ranging from near-native performance to large losses. With source caches already available, reuse achieves median time-to-first-token speedups of 2.102.10--5.08×5.08\times on three longer-prefix QA benchmarks. To characterize the behavioral differences behind these outcomes, we introduce Functional Cache Divergence, which compares next-token distributions under reused and native caches. Direct KV cache reuse better preserves native model behavior in natural-text continuation, whereas compatibility degrades with increasing prefix length in single-token retrieval tasks. Answer-margin analyses help explain how correct retrieval decisions survive substantial internal state changes. Yet even agreement on the first generated token does not ensure agreement in answer content or stopping behavior. These findings establish task utility and fidelity to native inference as distinct criteria for evaluating cross-version KV cache reuse.

Figures & tables

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Positions Are Not Facts: The Mismatch Between KV Caches and Memory

    Sep 27, 2026Changhai Zhou, Yuhua Zhou, Shiyang Zhang +5Knowledge EditingKnowledge Conflicts in Language Models

  2. CacheReforge: Bounded Recovery for Stale KV Caches under Evolving Adapters

    Sep 25, 2026Yuhang Cao, Yanzhou Mu, Chunrong Fang +1KV-Cache ManagementKV-Cache Reuse

  3. KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints

    Sep 9, 2026Xi Shi, Mengxin Zheng, Qian LouKV CachingLLM Inference Acceleration