The paper investigates when attention maps can be compressed beyond simple sparsity, arguing that large weights alone do not guarantee compressibility. It introduces metrics such as global score gaps and weighted sums of omitted values to determine token retention for a target mass, and presents a retrieval–aggregation model to predict the impact of truncation. Based on these insights, the authors propose CertKV, a training‑free compressor that allocates a tail‑summary slot per head and distributes remaining slots according to value dispersion, achieving strong performance across several benchmarks.
By Chiwun Yang, Xiaoyu Li
The paper addresses the challenge of long input contexts in Retrieval-Augmented Generation (RAG) systems, where concatenating many retrieved chunks increases prefill workload and time to first token (TTFT). It proposes a dual strategy: fine‑tuning the model to be aware of KV cache concatenation and selectively recomputing only part of the KV caches. Experiments on the RULER benchmark show that for a 124k‑token input, this combined method boosts the RULER score by 9.7 points over a baseline that recomputes caches only, while cutting TTFT by 80% compared with full attention.
By Fumihiko Tachibana, Daisuke Miyashita, Jun Deguchi
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: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
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. Existing methods primarily improve which original KV pairs are retained.
arXiv:2607. 06519v1 Announce Type: new Abstract: Long-context LLM inference is increasingly limited by the memory and bandwidth cost of KV caches, yet aggressive compression can remove the layer-specific evidence needed for retrieval and multi-step reasoning.
By Anna C\'ordoba, Adam Puente Tercero, Nerea Angulo Hijo, Mar Linares Tercero, Julia Barrientos, Ainhoa Miranda, Jes\'us Olivera
arXiv:2610.02953v1 Announce Type: new
Abstract: Long-context LLM serving is increasingly bottlenecked by KV-cache memory, especially in resource-constrained scenarios. Among existing KV-cache compres...
By Zihan Teng, Jiayu Zhao, Wentao Ren, Minhao Fan, Tianrui Ma, Song Chen, Weichen Liu
arXiv:2609.36835v1 Announce Type: new
Abstract: Long-context large language model inference is bottlenecked by KV caches that grow linearly with sequence length. This burden is especially severe for...
By Zheyu Shen, Guanhua Wang, Dezhan Tu, Mengchi Zhang, Yanjia Li, Adnan Aziz, Chunqiang Tang, Ang Li
The paper introduces GRKV, a training‑free method for compressing the key‑value cache in long‑context large language models. GRKV uses ridge‑regression to redistribute information from evicted tokens to retained ones, aiming to minimize the difference between compressed‑cache and full‑cache attention outputs. Experiments on LongBench and RULER show that GRKV improves overall performance with minimal overhead compared to other merging methods.
By Junjie Peng, You Wu, Haoyi Wu, Jialong Han, Xiaohua Xie, Kewei Tu, Jianhuang Lai
Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs.
arXiv:2609.30738v1 Announce Type: new
Abstract: KV cache eviction methods such as SnapKV and PyramidKV rank tokens solely by mean attention over a small observation window. We study a unified score,...
By Tianfang Xie, Wei Zhu
EchoPress is a training‑free method for pruning key‑value caches in large language models. It approximates the reconstruction attention used by KVzip by leveraging queries and keys from standard prefill, reconstructing only the first chunk to calibrate importance scores for the rest of the context. Experiments on LongBench and RULER with Qwen3‑8B and Llama‑3.1‑8B‑Instruct show that EchoPress matches KVzip’s task accuracy across eviction ratios from 50% to 90%, while reducing compression overhead by 1.7–19.6× and total prefill time by up to 2.9×.
By Jiawei Lin, Saibo Geng, Thomas Bourgeat