# PAGE: Partition-Aware Gated KV-Cache Eviction

arXiv: https://arxiv.org/abs/2609.22157 · HTML: https://mlsanity.com/paper/2609.22157/

## 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 24 of its 54 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution](https://mlsanity.com/paper/2510.00636/) (2025)
- [BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens](https://mlsanity.com/paper/2508.17196/) (2025)
- [Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction](https://mlsanity.com/paper/2601.17668/) (2026)
- [In-context KV-Cache Eviction for LLMs via Attention-Gate](https://mlsanity.com/paper/2410.12876/) (2024)
- [Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction](https://mlsanity.com/paper/2605.09649/) (2026)
- [EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving](https://mlsanity.com/paper/2512.14946/) (2025)
- [Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization](https://mlsanity.com/paper/2604.14853/) (2026)
- [Understanding the Physics of Key-Value Cache Compression for LLMs through Attention Dynamics](https://mlsanity.com/paper/2603.01426/) (2026)
- [MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference](https://mlsanity.com/paper/2606.01563/) (2026)
- [When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression](https://mlsanity.com/paper/2605.08234/) (2026)
- [A Simple Plug-in for Improving Eviction-Based KV Cache Compression](https://mlsanity.com/paper/2605.23258/) (2026)
- [Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV Eviction](https://mlsanity.com/paper/2605.18053/) (2026)
- [CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation](https://mlsanity.com/paper/2602.08686/) (2026)
- [CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2606.24467/) (2026)
- [Epiphany-Aware KV Cache Eviction Without the Attention Matrix](https://mlsanity.com/paper/2606.26472/) (2026)
- [UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference](https://mlsanity.com/paper/2603.18446/) (2026)
- [LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification](https://mlsanity.com/paper/2605.07315/) (2026)
- [From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs](https://mlsanity.com/paper/2606.09508/) (2026)
- [AnchorKV: Anchor-Residual KV Cache Compression](https://mlsanity.com/paper/2608.02901/) (2026)

## Abstract (arXiv)

KV-cache eviction can do more than compress. In long-context LLMs, keeping only some cached tokens sometimes matches or exceeds full-cache accuracy, because many redundant prefill tokens otherwise dilute attention away from the tokens that carry the answer. This benefit is not uniform, and evicting the wrong tokens can drop accuracy to zero on tasks that require precise retrieval, so the useful question is not only which tokens to keep but also whether to evict this input at all. We show that one label-free number computed from the prefill attention, the drop between early and late layers in how much attention heads agree on which tokens to read, predicts per input, before any decoding, which of the two cases an input falls under. We build this into PAGE (Partition-Aware Gated Eviction), a wrapper that runs any SnapKV-style evictor when the drop is large and keeps the full cache when it is small, with no training, labels, or fine-tuning. PAGE is a safety mechanism rather than a compressor, so we measure it by the failures it prevents. It cuts the harm rate on capacity-bound inputs from 0.75 to 0.026, and on multi-key retrieval with Mistral-7B plain SnapKV falls from 99% to 0% as the budget shrinks, while PAGE holds it at 89%. Elsewhere, it passes the base evictor through unchanged, which is the intended behaviour and is what we observe in 8 of 16 cells. Code is available at https://anonymous.4open.science/r/PAGE-018239.