The paper investigates how temporal aggregation of token scores during decoding-time KV cache compression affects eviction decisions. It shows that using an exponential‑moving‑average (EMA) aggregation keeps ranking changes minimal for many scorer variants, while others like KeyDiff or recency significantly alter rankings and degrade performance. Building on this, the authors propose InertiaKV and its lazy variant, which achieve 1.34–1.46× faster decoding than full refresh, and also evaluate a score‑free approach that slightly improves quality while eliminating further scoring.
NestedKV is a training‑free key‑only KV cache compression technique for long‑context language models that uses global, block‑level, and sliding‑window key anchors to score tokens via multi‑time‑scale cosine anomaly. It combines these rankings with a head‑adaptive outer learner and surprise‑gated token routing, requiring no model modification or additional training. Experiments on Qwen3 and Llama‑3.2 across benchmarks such as RULER, LongBench, and MMLU‑Pro show that NestedKV outperforms existing methods when the retained cache is small, achieving up to 19‑point gains on RULER and LongBench at a 75% retention rate.
By Hong Chen, Xiang Liu, Yubo Gao, Yuxuan Fan, Bo Wang, Yuanlin Chu, Yuanguo Lin, Xuming Hu
arXiv:2607. 15498v1 Announce Type: cross Abstract: The key-value (KV) cache is the main memory bottleneck in long-context large language model (LLM) inference.
By Shahrzad Esmat, Dhawal Shah, Ali Jannesari
arXiv:2608.23843v1 Announce Type: new
Abstract: Long-context inference in large language models (LLMs) is increasingly limited by the memory required for the key-value (KV) cache. KV cache compressio...
By Zizhong Wang, Jieying Wang, Zhao Zhang, Jiajia Li
arXiv:2602. 10238v2 Announce Type: replace-cross Abstract: The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache.
By Luca Moschella, Laura Manduchi, Ozan Sener
arXiv:2608. 05326v1 Announce Type: new Abstract: Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache.
By Ayushman Garg, Akshita Gupta, Shaswata Bhattacharya, Abhishek Gupta, Sandeep Kumar, Manoj Kumar
The paper argues that evaluating continual knowledge‑updating methods solely at a final checkpoint and a single adapter rank can be misleading. By fixing a periodic hierarchy and comparing it to cumulative replay on a 24‑month Wikidata stream, the authors show that the apparent best method changes depending on the evaluation month, replay LoRA rank, and query formulation. They recommend reporting performance trajectories and capacity sweeps, and only declaring a robust winner when the ranking remains stable across the evaluation region.
By Heejin Choi
arXiv:2607. 05061v1 Announce Type: new Abstract: Key-value (KV) cache growth is a major bottleneck in autoregressive decoding, as memory and bandwidth scale linearly with context length.
By Lukas Hauzenberger, Niklas Schmidinger, Anamaria-Roberta Hartl, David Stap, Thomas Schmied, Sebastian B\"ock, G\"unter Klambauer, Sepp Hochreiter
The paper investigates KV‑cache eviction strategies for sparse‑attention models, showing that selecting the largest attention weights is nearly optimal—closing only a median 2–5 % of the gap to full attention. It further demonstrates that differences in performance between eviction methods largely stem from memory usage, with the new training‑free ContourKV allocator outperforming state‑of‑the‑art methods in most pairwise comparisons while matching their byte‑efficiency.
By Jack Shi, Jerry Gu
arXiv:2608. 01247v1 Announce Type: cross Abstract: Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse under tight budgets.
By Changwoo Baek, Seungjun Shin, Kyeongbo Kong
arXiv:2605. 25475v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference.
By Xintong Yang, Hao Gu, Binxing Xu, Lujun Li, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Yike Guo, Sirui Han
arXiv:2607. 11942v1 Announce Type: cross Abstract: KV-cache compression methods are predominantly evaluated with the query appended to the context before compression -- a query-aware protocol.
By Daming Luo, Christy Liang, Junyu Xuan