# PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving

arXiv: https://arxiv.org/abs/2603.23049 · HTML: https://mlsanity.com/paper/2603.23049/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 33 of its 49 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)
- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 30 of 33)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (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)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference](https://mlsanity.com/paper/2510.09665/) (2025)
- [RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation](https://mlsanity.com/paper/2404.12457/) (2024)
- [Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting](https://mlsanity.com/paper/2407.08223/) (2024)
- [MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs](https://mlsanity.com/paper/2411.11217/) (2024)
- [TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text](https://mlsanity.com/paper/2410.07590/) (2024)
- [HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference](https://mlsanity.com/paper/2411.01433/) (2024)
- [A Survey on Inference Optimization Techniques for Mixture of Experts Models](https://mlsanity.com/paper/2412.14219/) (2024)
- [KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider](https://mlsanity.com/paper/2506.02634/) (2025)
- [Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.15734/) (2025)
- [BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching](https://mlsanity.com/paper/2412.03594/) (2024)
- [Strata: Hierarchical Context Caching for Long Context Language Model Serving](https://mlsanity.com/paper/2508.18572/) (2025)

## Built on by (most cited first, 4 of 4)

- [Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?](https://mlsanity.com/paper/2605.27494/) (2026)
- [Building py-kvcache: A Performance Characterization of External KV Caching for vLLM with NVMe SSDs](https://mlsanity.com/paper/2609.11744/) (2026)
- [Prefix Sharing Is a Sorting Problem](https://mlsanity.com/paper/2609.13692/) (2026)
- [TempoKV: Timely Staging of LLM KV Caches for Memory-Semantic Flash](https://mlsanity.com/paper/2609.35065/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) systems enhance the performance of large language models (LLMs) by incorporating supplementary retrieved documents, enabling more accurate and context-aware responses. However, integrating these external documents often results in very long input sequences, which significantly increases computation costs during the prefill stage, where key-value (KV) representations for all input tokens are generated. This latency bottleneck becomes especially pronounced under high-throughput serving scenarios. KV-cache reuse offers a promising solution by storing previously computed KV states for shared input prefixes, thereby avoiding redundant computation across requests that contain overlapping context. Yet, the effectiveness of cache reuse is often limited by three practical challenges: low cache hit rates due to naive eviction policies, high CPU-GPU data transfer overhead, and slow SSD I/O when caches spill to storage. To address these issues, we propose PCR, a system designed to maximize KV-cache reuse efficiency through intelligent prefetching and pipelined data movement. Specifically, PCR introduces three key techniques: (1) a prefix-tree caching structure with a look-ahead LRU replacement policy that uses pending requests in the scheduler queue to improve cache hit ratios; (2) layer-wise overlapping that pipelines KV-cache loading and GPU computation across CUDA streams to hide communication latency; and (3) queue-based prefetching that proactively loads relevant KV caches from SSD into DRAM before they are needed. Extensive experiments show that PCR outperforms existing KV-cache reuse methods, achieving up to a 2.47x speedup in terms of average TTFT.