# KVFetch: Temporal Prefetching for the Missing Half of KV Cache Compression

arXiv: https://arxiv.org/abs/2610.08811 · HTML: https://mlsanity.com/paper/2610.08811/

## 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 18 of its 28 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Placed in

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

## Builds on (most cited first, 18 of 18)

- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [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)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference](https://mlsanity.com/paper/2407.11550/) (2024)
- [InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory](https://mlsanity.com/paper/2402.04617/) (2024)
- [GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM](https://mlsanity.com/paper/2403.05527/) (2024)
- [Transformers are Multi-State RNNs](https://mlsanity.com/paper/2401.06104/) (2024)
- [Learning to Evict from Key-Value Cache](https://mlsanity.com/paper/2602.10238/) (2026)
- [OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2510.07651/) (2025)
- [IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference](https://mlsanity.com/paper/2605.25475/) (2026)
- [MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference](https://mlsanity.com/paper/2606.01563/) (2026)
- [Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective](https://mlsanity.com/paper/2604.25975/) (2026)
- [SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2606.04511/) (2026)
- [FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention](https://mlsanity.com/paper/2606.09079/) (2026)
- [CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2606.24467/) (2026)

## Abstract (arXiv)

As context windows scale to tens or hundreds of thousands of tokens, KV cache compression has become essential for efficient LLM inference. Existing methods fall into three families: score-based eviction, summary compensation, and offload-and-recall. Yet all three decide what to keep or recall by content relevance to the current query. We show this shared design is structurally incomplete. A cache supports two access modes: associative lookup by content and sequential traversal by position; current compressors implement only the first. The gap matters in practice: retrieval-augmented generation, code completion, and structured-data extraction all require the model to reproduce identifiers, field values, or code tokens verbatim from the context. Under compression, content-based eviction retains the head of such a sequence but discards its continuation, causing verbatim copying to break irreversibly midway, a failure we call sequential forgetting. This failure resists better scoring, larger budgets, summary compensation, and dynamic re-scoring; it is the dominant source of remaining quality loss under compression. We propose KVFetch, a training-free, drop-in framework that opens a temporal recall channel for any score-based compressor. It demotes evicted candidates to a quantized cold tier, detects active copying through a monotone read pointer, and prefetches positional successors into fixed-size hot-tier slots without increasing attention cost. On RULER-16K under an iso-budget control, KVFetch recovers verbatim copying from 0.8 to 78.4 and raises the 13-task average by +8.4, with gains concentrating on tasks that require sequential access. On LongBench, where no task requires sequential access, the channel remains dormant and imposes no cost.