# RelayAttention for Efficient Large Language Model Serving with Long System Prompts

arXiv: https://arxiv.org/abs/2402.14808 · HTML: https://mlsanity.com/paper/2402.14808/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 22 Feb 2024.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction](https://mlsanity.com/paper/2005.12833/) (2020)
- [Prompt Cache: Modular Attention Reuse for Low-Latency Inference](https://mlsanity.com/paper/2311.04934/) (2023)
- [Online normalizer calculation for softmax](https://mlsanity.com/paper/1805.02867/) (2018)
- [Self-attention Does Not Need O(n2) Memory](https://mlsanity.com/paper/2112.05682/) (2021)
- [Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Data](https://mlsanity.com/paper/2001.05295/) (2020)
- [Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence](https://mlsanity.com/paper/2306.07075/) (2023)

## Built on by (most cited first, 13 of 13)

- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [Twilight: Adaptive Attention Sparsity with Hierarchical Top-p Pruning](https://mlsanity.com/paper/2502.02770/) (2025)
- [Queue management for slo-oriented large language model serving](https://mlsanity.com/paper/2407.00047/) (2024)
- [BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching](https://mlsanity.com/paper/2412.03594/) (2024)
- [DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference](https://mlsanity.com/paper/2404.00242/) (2024)
- [Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)](https://mlsanity.com/paper/2505.21091/) (2025)
- [Accurate KV Cache Quantization with Outlier Tokens Tracing](https://mlsanity.com/paper/2505.10938/) (2025)
- [PAT: Accelerating LLM Decoding via Prefix-Aware Attention with Resource Efficient Multi-Tile Kernel](https://mlsanity.com/paper/2511.22333/) (2025)
- [xGR: Efficient Generative Recommendation Serving at Scale](https://mlsanity.com/paper/2512.11529/) (2025)
- [CaliDrop: KV Cache Compression with Calibration](https://mlsanity.com/paper/2507.19906/) (2025)
- [Enabling KV Caching of Shared Prefix for Diffusion Language Models](https://mlsanity.com/paper/2606.07571/) (2026)
- [Crossflow: Prefill-Decode Elasticity for Agentic LLM Serving](https://mlsanity.com/paper/2609.27085/) (2026)
- [TyphoonMLA: A Mixed Naive-Absorb MLA Kernel For Shared Prefix](https://mlsanity.com/paper/2509.21081/) (2025)

## Abstract (arXiv)

A practical large language model (LLM) service may involve a long system prompt, which specifies the instructions, examples, and knowledge documents of the task and is reused across requests. However, the long system prompt causes throughput/latency bottlenecks as the cost of generating the next token grows w.r.t. the sequence length. This paper aims to improve the efficiency of LLM services that involve long system prompts. Our key observation is that handling these system prompts requires heavily redundant memory accesses in existing causal attention computation algorithms. Specifically, for batched requests, the cached hidden states (ie, key-value pairs) of system prompts are transferred from off-chip DRAM to on-chip SRAM multiple times, each corresponding to an individual request. To eliminate such a redundancy, we propose RelayAttention, an attention algorithm that allows reading these hidden states from DRAM exactly once for a batch of input tokens. RelayAttention is a free lunch: it maintains the generation quality while requiring no model retraining, as it is based on a mathematical reformulation of causal attention. We have observed significant performance improvements to a production-level system, vLLM, through integration with RelayAttention. The improvements are even more profound with longer system prompts.