# KVShare: An LLM Service System with Efficient and Effective Multi-Tenant KV Cache Reuse

arXiv: https://arxiv.org/abs/2503.16525 · HTML: https://mlsanity.com/paper/2503.16525/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Placed in

- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 14 of 14)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [Prompt Cache: Modular Attention Reuse for Low-Latency Inference](https://mlsanity.com/paper/2311.04934/) (2023)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [EPIC: Efficient Position-Independent Caching for Serving Large Language Models](https://mlsanity.com/paper/2410.15332/) (2024)

## Built on by (most cited first, 22 of 22)

- [LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference](https://mlsanity.com/paper/2510.09665/) (2025)
- [ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation](https://mlsanity.com/paper/2602.02579/) (2026)
- [MEPIC: Memory Efficient Position Independent Caching for LLM Serving](https://mlsanity.com/paper/2512.16822/) (2025)
- [VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference](https://mlsanity.com/paper/2512.12977/) (2025)
- [HYPIC: Accelerating Hybrid-Attention LLM Serving with Position-Independent Caching](https://mlsanity.com/paper/2607.01299/) (2026)
- [Category-Aware Semantic Caching for Heterogeneous LLM Workloads](https://mlsanity.com/paper/2510.26835/) (2025)
- [Towards Efficient Agents: A Co-Design of Inference Architecture and System](https://mlsanity.com/paper/2512.18337/) (2025)
- [OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism](https://mlsanity.com/paper/2603.14371/) (2026)
- [KV Cache Translation across Heterogeneous Large Language Models](https://mlsanity.com/paper/2607.28979/) (2026)
- [ShadowServe: Interference-Free KV Cache Fetching for Distributed Prefix Caching](https://mlsanity.com/paper/2509.16857/) (2025)
- [LinearKV: One Cached State Suffices for Position-Independent Caching in Hybrid LLMs](https://mlsanity.com/paper/2608.11231/) (2026)
- [Token-Budget-Aware Pool Routing for Cost-Efficient LLM Inference](https://mlsanity.com/paper/2604.09613/) (2026)
- [HijackKV: New Threat in Position-Independent KV Cache Reuse](https://mlsanity.com/paper/2607.19957/) (2026)
- [Burn-After-Use for Preventing Data Leakage through a Secure Multi-Tenant Architecture in Enterprise LLM](https://mlsanity.com/paper/2601.06627/) (2026)
- [Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving](https://mlsanity.com/paper/2604.08075/) (2026)
- [Contiguity, Not Importance: Budgeted Repair of Stale KV Caches After Document Edits](https://mlsanity.com/paper/2609.17983/) (2026)
- [HA-RAG: Hotness-Aware RAG Acceleration via Mixed Precision and Data Placement](https://mlsanity.com/paper/2510.20878/) (2025)
- [QCFuse: Query-Centric Cache Fusion for Efficient RAG Inference](https://mlsanity.com/paper/2604.08585/) (2026)
- [Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?](https://mlsanity.com/paper/2609.09768/) (2026)
- [RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse](https://mlsanity.com/paper/2609.33503/) (2026)
- [KVCMAS: Efficient KV cache Correction for Shared Context in Multi-Agent Systems](https://mlsanity.com/paper/2609.34060/) (2026)
- [ATTUNER: Recomputation-Free KV Cache Reuse via Query-Side Adaptation](https://mlsanity.com/paper/2609.36722/) (2026)

## Abstract (arXiv)

Recent advances in long-text understanding have pushed the context length of large language models (LLMs) up to one million tokens. It boosts LLMs's accuracy and reasoning capacity but causes exorbitant computational costs and unsatisfactory Time to First Token (TTFT). KV cache reuse, which reuses the exact same KV cache of prefixes and templates or shares similar ones but with extra selective recomputation, offers a promising way to tackle this issue. However, prior studies overlook the cross-request KV reuse and the attention deviations introduced by new tokens during the decoding stage. In this paper, we present a KV cache management module that shares the KV cache across requests under multi-tenant scenarios without sacrificing model accuracy. Our system, KVShare, enables accurate and efficient LLM serving by 1) a Dual-Stage High Deviation algorithm (DHD) that conditionally selects a small portion of KV cache to be recomputed during both prefill and decode phases, and 2) a cache-aware scheduler that prioritizes requests based on their KV cache hit rates and orchestrates continuous batching to achieve enhanced system efficiency and faster TTFT. Multi-task experiments conducted on models such as Qwen2.5-7B,Llama3.1-8B and Yi1.5-9B demonstrate that KVShare reduces TTFT by up to 9.39x and increases 1.2x of the throughput compared to the full KV recompute. Moreover, KVShare achieves 20.38% boost in terms of accuracy compared to SOTA methods.