# Stateful KV Cache Management for LLMs: Balancing Space, Time, Accuracy, and Positional Fidelity

arXiv: https://arxiv.org/abs/2511.04686 · HTML: https://mlsanity.com/paper/2511.04686/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 17 of its 21 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Placed in

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

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [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)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [Effective Long-Context Scaling of Foundation Models](https://mlsanity.com/paper/2309.16039/) (2023)

## Abstract (arXiv)

The Key-Value (KV) cache is integral to efficient autoregressive inference in large language models (LLMs), yet its unbounded growth in stateful multi-turn scenarios presents major challenges. This paper examines the interplay between KV cache management strategies, the architectural context limits of models like meta-llama/Meta-Llama-3-8b-instruct, and the often-overlooked integrity of positional encodings. Through empirical analysis using a stateful benchmarking framework, we show that LLM generation quality degrades sharply when the accumulated KV cache approaches or exceeds the model's trained context window (e.g., 8192 tokens for Llama 3), a failure mode distinct from GPU memory exhaustion. Common eviction strategies, even high-retention ones (e.g., 99% via AttentionTop), can worsen performance if they disrupt positional coherence. Because LLMs rely on consistent positional signals (e.g., RoPE), compacting a cache by removing non-contiguous tokens can scramble these signals and lead to degenerative outputs. We further show that simple strategies preserving contiguous context blocks (e.g., keeping an initial "gist") can yield more coherent generations than complex or positionally disruptive ones. We advocate for eviction techniques that respect architectural limits, preserve positional structure, and view "cache health" holistically beyond mere size.