# FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration

arXiv: https://arxiv.org/abs/2502.01068 · HTML: https://mlsanity.com/paper/2502.01068/

## Key facts

- Cited by 14 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 23 of its 34 references that are in the map.
- First posted on arXiv 3 Feb 2025.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [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)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention](https://mlsanity.com/paper/2407.02490/) (2024)
- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference](https://mlsanity.com/paper/2407.11550/) (2024)
- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference](https://mlsanity.com/paper/2405.12532/) (2024)
- [No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization](https://mlsanity.com/paper/2402.18096/) (2024)
- [Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning](https://mlsanity.com/paper/2410.19258/) (2024)
- [Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction](https://mlsanity.com/paper/2409.17422/) (2024)

## Built on by (most cited first, 14 of 14)

- [FreqKV: Key-Value Compression in Frequency Domain for Context Window Extension](https://mlsanity.com/paper/2505.00570/) (2025)
- [CSV-Decode: Certifiable Sub-Vocabulary Decoding for Efficient Large Language Model Inference](https://mlsanity.com/paper/2511.21702/) (2025)
- [A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges](https://mlsanity.com/paper/2507.21117/) (2025)
- [Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference](https://mlsanity.com/paper/2601.07667/) (2026)
- [Information-Aware KV Cache Compression for Long Reasoning](https://mlsanity.com/paper/2606.26875/) (2026)
- [Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection](https://mlsanity.com/paper/2602.03216/) (2026)
- [UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference](https://mlsanity.com/paper/2603.18446/) (2026)
- [DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression](https://mlsanity.com/paper/2607.06523/) (2026)
- [SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models](https://mlsanity.com/paper/2604.16883/) (2026)
- [FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference](https://mlsanity.com/paper/2607.06519/) (2026)
- [SALT: Salience-Aware Lexical Trie for Long-Context Compression](https://mlsanity.com/paper/2607.17486/) (2026)
- [Parser Transitions Already Reveal Structural Responsibility: KV Persistence for Structured Generation](https://mlsanity.com/paper/2608.28276/) (2026)
- [CONDUIT: A Unified Residual-Stream Restoration Framework for KV Cache Reuse in Vision-Language Models](https://mlsanity.com/paper/2609.05821/) (2026)
- [TPBench: A Turning-Point Benchmark for Dialogue Compression](https://mlsanity.com/paper/2610.02736/) (2026)

## Abstract (arXiv)

While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and decoding stages. Recent works that compress KV caches with prefill acceleration reduce this cost but inadvertently tie the prefill compute reduction to the decoding KV budget. This coupling arises from overlooking the layer-dependent variation of critical context, often leading to accuracy degradation. To address this issue, we introduce FastKV, a KV cache compression framework designed to reduce latency in both prefill and decoding by leveraging the stabilization of token importance in later layers. FastKV performs full-context computation until a Token-Selective Propagation (TSP) layer, which forwards only the most informative tokens to subsequent layers. From these propagated tokens, FastKV independently selects salient KV entries for caching, thereby decoupling KV budget from the prefill compute reduction based on the TSP decision. This independent control of the TSP rate and KV retention rate enables flexible optimization of efficiency and accuracy. Experimental results show that FastKV achieves speedups of up to 1.82× in prefill and 2.87× in decoding compared to the full-context baseline, while matching the accuracy of the decoding-only baselines. Our code is available at https://github.com/dongwonjo/FastKV.