# Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention

arXiv: https://arxiv.org/abs/2403.19708 · HTML: https://mlsanity.com/paper/2403.19708/

## Key facts

- Cited by 163 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 41 of its 56 references that are in the map.
- First posted on arXiv 23 Mar 2024.

## Placed in

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

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [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)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [ERNIE: Enhanced Language Representation with Informative Entities](https://mlsanity.com/paper/1905.07129/) (2019)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time](https://mlsanity.com/paper/2305.17118/) (2023)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning](https://mlsanity.com/paper/2104.07857/) (2021)
- [PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU](https://mlsanity.com/paper/2312.12456/) (2023)

## Built on by (most cited first, 30 of 163)

- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Reducing Transformer Key-Value Cache Size with Cross-Layer Attention](https://mlsanity.com/paper/2405.12981/) (2024)
- [A Survey on Large Language Model Acceleration based on KV Cache Management](https://mlsanity.com/paper/2412.19442/) (2024)
- [LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference](https://mlsanity.com/paper/2510.09665/) (2025)
- [Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption](https://mlsanity.com/paper/2407.18003/) (2024)
- [A Comprehensive Survey of Foundation Models in Medicine](https://mlsanity.com/paper/2406.10729/) (2024)
- [KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows](https://mlsanity.com/paper/2507.07400/) (2025)
- [LLM Inference Serving: Survey of Recent Advances and Opportunities](https://mlsanity.com/paper/2407.12391/) (2024)
- [KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider](https://mlsanity.com/paper/2506.02634/) (2025)
- [The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective](https://mlsanity.com/paper/2506.04301/) (2025)
- [Fast State Restoration in LLM Serving with HCache](https://mlsanity.com/paper/2410.05004/) (2024)
- [BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching](https://mlsanity.com/paper/2412.03594/) (2024)
- [Marconi: Prefix Caching for the Era of Hybrid LLMs](https://mlsanity.com/paper/2411.19379/) (2024)
- [TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms](https://mlsanity.com/paper/2501.02600/) (2025)
- [P/D-Serve: Serving Disaggregated Large Language Model at Scale](https://mlsanity.com/paper/2408.08147/) (2024)
- [Strata: Hierarchical Context Caching for Long Context Language Model Serving](https://mlsanity.com/paper/2508.18572/) (2025)
- [Compute Or Load KV Cache? Why Not Both?](https://mlsanity.com/paper/2410.03065/) (2024)
- [SocialMind: LLM-based Proactive AR Social Assistive System with Human-like Perception for In-situ Live Interactions](https://mlsanity.com/paper/2412.04036/) (2024)
- [Jenga: Effective Memory Management for Serving LLM with Heterogeneity](https://mlsanity.com/paper/2503.18292/) (2025)
- [InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference](https://mlsanity.com/paper/2409.04992/) (2024)
- [KVComm: Enabling Efficient LLM Communication through Selective KV Sharing](https://mlsanity.com/paper/2510.03346/) (2025)
- [Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution](https://mlsanity.com/paper/2406.00059/) (2024)
- [METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation](https://mlsanity.com/paper/2412.10543/) (2024)
- [Taming the Titans: A Survey of Efficient LLM Inference Serving](https://mlsanity.com/paper/2504.19720/) (2025)
- [TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications](https://mlsanity.com/paper/2510.18586/) (2025)
- [TraceLab: Characterizing Coding Agent Workloads for LLM Serving](https://mlsanity.com/paper/2606.30560/) (2026)
- [vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving](https://mlsanity.com/paper/2407.15309/) (2024)
- [DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference](https://mlsanity.com/paper/2602.21548/) (2026)
- [Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation](https://mlsanity.com/paper/2503.20552/) (2025)
- [CONCUR: High-Throughput Agentic Batch Inference of LLM via Congestion-Based Concurrency Control](https://mlsanity.com/paper/2601.22705/) (2026)

## Abstract (arXiv)

Interacting with humans through multi-turn conversations is a fundamental feature of large language models (LLMs). However, existing LLM serving engines executing multi-turn conversations are inefficient due to the need to repeatedly compute the key-value (KV) caches of historical tokens, incurring high serving costs. To address the problem, this paper proposes CachedAttention, a new attention mechanism that enables reuse of KV caches across multi-turn conversations, significantly reducing the repetitive computation overheads. CachedAttention maintains a hierarchical KV caching system that leverages cost-effective memory/storage mediums to save KV caches for all requests. To reduce KV cache access overheads from slow mediums, CachedAttention employs layer-wise pre-loading and asynchronous saving schemes to overlap the KV cache access with the GPU computation. To ensure that the KV caches to be accessed are placed in the fastest hierarchy, CachedAttention employs scheduler-aware fetching and eviction schemes to consciously place the KV caches in different layers based on the hints from the inference job scheduler. To avoid the invalidation of the saved KV caches incurred by context window overflow, CachedAttention enables the saved KV caches to remain valid via decoupling the positional encoding and effectively truncating the KV caches. Extensive experimental results demonstrate that CachedAttention significantly decreases the time to the first token (TTFT) by up to 87%, improves the prompt prefilling throughput by up to 7.8× for multi-turn conversations, and reduces the end-to-end inference cost by up to 70%.