# FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache Management

arXiv: https://arxiv.org/abs/2511.00868 · HTML: https://mlsanity.com/paper/2511.00868/

## Key facts

- Cited by 5 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 27 of its 28 references that are in the map.
- First posted on arXiv 2 Nov 2025.

## Placed in

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

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads](https://mlsanity.com/paper/2410.10819/) (2024)
- [L-Eval: Instituting Standardized Evaluation for Long Context Language Models](https://mlsanity.com/paper/2307.11088/) (2023)
- [QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving](https://mlsanity.com/paper/2405.04532/) (2024)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [Qwen2.5-1M Technical Report](https://mlsanity.com/paper/2501.15383/) (2025)
- [LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs](https://mlsanity.com/paper/2408.07055/) (2024)
- [LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference](https://mlsanity.com/paper/2510.09665/) (2025)
- [From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models](https://mlsanity.com/paper/2310.08825/) (2023)
- [MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs](https://mlsanity.com/paper/2411.11217/) (2024)
- [LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs](https://mlsanity.com/paper/2409.02076/) (2024)
- [LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention](https://mlsanity.com/paper/2502.14866/) (2025)
- [NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM Inference](https://mlsanity.com/paper/2411.01142/) (2024)
- [Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMs](https://mlsanity.com/paper/2503.00979/) (2025)

## Built on by (most cited first, 5 of 5)

- [An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference](https://mlsanity.com/paper/2605.07719/) (2026)
- [SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference](https://mlsanity.com/paper/2605.18856/) (2026)
- [Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding](https://mlsanity.com/paper/2606.30389/) (2026)
- [Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics](https://mlsanity.com/paper/2606.01502/) (2026)
- [WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds](https://mlsanity.com/paper/2610.02713/) (2026)

## Abstract (arXiv)

Large Language Model (LLM) serving is increasingly constrained by the growing size of the key-value (KV) cache, which scales with both context length and generation length. Prior work shows that attention is dominated by a small subset of critical tokens, yet existing systems struggle to exploit this efficiently without degrading accuracy, especially in long generation. We make a key observation: the temporal stability of these critical tokens varies significantly across KV heads: some heads consistently focus on the same tokens, while others shift frequently. Building on this insight, we introduce FlexiCache, a hierarchical KV-cache management system that leverages the temporal stability of KV heads to reduce GPU memory usage and computation overhead, while preserving model accuracy. FlexiCache classifies KV heads as stable or unstable: it retains all KV-cache pages from unstable heads in GPU memory, whereas for stable heads, it keeps only the top-K pages on the GPU and offloads the rest to host memory. By exploiting temporal stability, FlexiCache performs periodic reranking for stable heads to fetch newly promoted top pages. Implemented atop vLLM, FlexiCache reduces GPU memory footprint for long-context requests by up to 70%, improves offline serving throughput by 1.38-1.55x, and lowers online token latency by 1.6-2.1x, all while maintaining accuracy in long-context, long-generation scenarios.