# Dynamic Flow, Static Graph: KV Cache Reuse for Efficient LLM Serving on Mobile NPUs

arXiv: https://arxiv.org/abs/2609.34727 · HTML: https://mlsanity.com/paper/2609.34727/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

- Efficient LLM inference and serving / [Serving systems and request scheduling](https://mlsanity.com/inference/serving-systems-and-request-scheduling/)

## Builds on (most cited first, 27 of 27)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [Prompt Cache: Modular Attention Reuse for Low-Latency Inference](https://mlsanity.com/paper/2311.04934/) (2023)
- [CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion](https://mlsanity.com/paper/2405.16444/) (2024)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [LLM in a flash: Efficient Large Language Model Inference with Limited Memory](https://mlsanity.com/paper/2312.11514/) (2023)
- [LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference](https://mlsanity.com/paper/2510.09665/) (2025)
- [PowerInfer-2: Fast Large Language Model Inference on a Smartphone](https://mlsanity.com/paper/2406.06282/) (2024)
- [ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition](https://mlsanity.com/paper/2402.15220/) (2024)
- [Fast On-device LLM Inference with NPUs](https://mlsanity.com/paper/2407.05858/) (2024)
- [T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge](https://mlsanity.com/paper/2407.00088/) (2024)
- [Strata: Hierarchical Context Caching for Long Context Language Model Serving](https://mlsanity.com/paper/2508.18572/) (2025)
- [Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference](https://mlsanity.com/paper/2501.14794/) (2025)
- [SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobile](https://mlsanity.com/paper/2404.13528/) (2024)
- [MobileRAG: A Fast, Memory-Efficient, and Energy-Efficient Method for On-Device RAG](https://mlsanity.com/paper/2507.01079/) (2025)
- [Scaling LLM Test-Time Compute with Mobile NPU on Smartphones](https://mlsanity.com/paper/2509.23324/) (2025)
- [MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile Devices](https://mlsanity.com/paper/2506.10443/) (2025)
- [MicroNN: An On-device Disk-resident Updatable Vector Database](https://mlsanity.com/paper/2504.05573/) (2025)
- [Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking](https://mlsanity.com/paper/2410.19274/) (2024)
- [T-MAN: Enabling End-to-End Low-Bit LLM Inference on NPUs via Unified Table Lookup](https://mlsanity.com/paper/2511.11248/) (2025)
- [ClawMobile: Rethinking Smartphone-Native Agentic Systems](https://mlsanity.com/paper/2602.22942/) (2026)
- [SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference](https://mlsanity.com/paper/2604.21231/) (2026)

## Abstract (arXiv)

On-device large language model (LLM) serving is a cornerstone of local-first personal intelligence, offering users data sovereignty, strong privacy guarantees, and freedom from cloud API latency and cost. Although KV caching is widely used to reduce latency in long-context inference, existing designs were primarily optimized for cloud GPUs with dynamic execution environments and abundant memory bandwidth. These architectural assumptions do not hold on mobile NPUs, where computation graphs must be statically compiled and both memory capacity and I/O bandwidth are severely constrained. In this work, we present a compute-storage co-design for mobile-centric prefix and non-prefix KV reuse. We first propose an intra-graph mechanism that maps selective KV recomputation onto static NPU graphs, reconciling algorithmic dynamicity with NPU staticity. We further develop an inter-graph scheduler to optimize chunk merging and minimize padding with dynamic programming. To address mobile bandwidth limitations, we introduce a hierarchical KV manager featuring a tree-hash-semantic hybrid structure, along with cost-aware prefetching and eviction policies. We also build a two-dimensional pipeline that overlaps KV loading, rerotation, and storage with NPU execution, hiding data-movement latency. Experiments across representative on-device workloads and LLMs show that our design reduces time-to-first-token (TTFT) by 40-60% compared with no reuse and prefix-only caching.