# MatKV: Trading Compute for Flash Storage in LLM Inference

arXiv: https://arxiv.org/abs/2512.22195 · HTML: https://mlsanity.com/paper/2512.22195/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 26 of its 49 references that are in the map.
- First posted on arXiv 20 Dec 2025.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 26 of 26)

- [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)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [Prompt Cache: Modular Attention Reuse for Low-Latency Inference](https://mlsanity.com/paper/2311.04934/) (2023)
- [InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management](https://mlsanity.com/paper/2406.19707/) (2024)
- [A Survey on Efficient Inference for Large Language Models](https://mlsanity.com/paper/2404.14294/) (2024)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [MiniCache: KV Cache Compression in Depth Dimension for Large Language Models](https://mlsanity.com/paper/2405.14366/) (2024)
- [RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation](https://mlsanity.com/paper/2404.12457/) (2024)
- [CRAG -- Comprehensive RAG Benchmark](https://mlsanity.com/paper/2406.04744/) (2024)
- [TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text](https://mlsanity.com/paper/2410.07590/) (2024)
- [D'ej`aVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving](https://mlsanity.com/paper/2403.01876/) (2024)
- [LLM Inference Serving: Survey of Recent Advances and Opportunities](https://mlsanity.com/paper/2407.12391/) (2024)
- [RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression](https://mlsanity.com/paper/2502.14051/) (2025)
- [Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks](https://mlsanity.com/paper/2412.15605/) (2024)
- [LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management](https://mlsanity.com/paper/2410.00428/) (2024)

## Built on by (most cited first, 2 of 2)

- [Can I Buy Your KV Cache?](https://mlsanity.com/paper/2606.13361/) (2026)
- [TempoKV: Timely Staging of LLM KV Caches for Memory-Semantic Flash](https://mlsanity.com/paper/2609.35065/) (2026)

## Abstract (arXiv)

We observe two major trends in LLM-based generative AI: (1) inference is becoming the dominant factor in terms of cost and power consumption, surpassing training, and (2) retrieval augmented generation (RAG) is becoming prevalent. When processing long inputs in RAG, the prefill phase of computing the key-value vectors of input text is energy-intensive and time-consuming even with high-end GPUs. Thus, it is crucial to make the prefill phase in RAG inference efficient. To address this issue, we propose MatKV, a scheme that precomputes the key-value vectors (KVs) of RAG objects (e.g., documents), materializes them in inexpensive but fast and power-efficient flash storage, and reuses them at inference time instead of recomputing the KVs using costly and power-inefficient GPU. Experimental results using Hugging Face's Transformers library across state-of-the-art GPUs and flash memory SSDs confirm that, compared to full KV computation on GPUs, MatKV reduces both inference time and power consumption by half for RAG workloads, without severely impacting accuracy in the question-answering task. Furthermore, we demonstrate that MatKV enables additional optimizations in two ways. First, a GPU can decode text while simultaneously loading the materialized KVs for the next instance, reducing load latency. Second, since decoding speed is less sensitive to GPU performance than KV computation, low-end GPUs can be leveraged for decoding without significantly compromising speed once the materialized KVs are loaded into GPU memory. These findings underscore MatKV's potential to make large-scale generative AI applications more cost-effective, power-efficient, and accessible across a wider range of tasks and hardware environments.