# AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model Serving

arXiv: https://arxiv.org/abs/2509.00105 · HTML: https://mlsanity.com/paper/2509.00105/

## Key facts

- Cited by 4 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 11 of its 16 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Placed in

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

## Builds on (most cited first, 11 of 11)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention](https://mlsanity.com/paper/2403.19708/) (2024)
- [LongCoder: A Long-Range Pre-trained Language Model for Code Completion](https://mlsanity.com/paper/2306.14893/) (2023)

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

- [EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving](https://mlsanity.com/paper/2512.14946/) (2025)
- [SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling](https://mlsanity.com/paper/2607.08565/) (2026)
- [OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services](https://mlsanity.com/paper/2602.20595/) (2026)
- [FinCacheServe: Dependency-Consistent Answer Reuse for Cost-Efficient RAG Serving over Mutable Enterprise Documents](https://mlsanity.com/paper/2607.26076/) (2026)

## Abstract (arXiv)

Large language model (LLM) applications often reuse previously processed context, such as chat history and documents, which introduces significant redundant computation. Existing LLM serving systems address such redundant computation by storing the KV caches of processed context and loading the corresponding KV cache when a new request reuses the context. Further, as these LLM applications scale, the total size of KV caches becomes excessively large and requires both DRAM and SSD for full storage. However, prior work that stores KV caches in DRAM and SSD suffers from high loading delays, as most KV cache hits come from SSD, which is slow to load. To increase the KV cache hit rate on DRAM, we identify lossy KV cache compression as a promising approach. We design a lossy compression system that decides the compression algorithm, compression rate and device placement for each KV cache entry to maximise DRAM hits and minimise loading delay without significantly degrading generation quality. Compared to various static compression baselines across three tasks, our system AdaptCache achieves 1.43--2.4 x delay savings at the same quality and 6--55% quality improvements at the same delay.