The paper introduces Kwai Summary Attention V2, an improved version of the KSA architecture that compresses distant context into learnable summary tokens per chunk. It addresses bottlenecks of the original hybrid KSA‑Full design by allowing flexible KV cache compression across layers and reducing computation costs in full‑attention layers. The new approach treats summary tokens as both KV memory and sparse indexers, enhancing efficiency.
SGD-KV is a head‑aware framework for compressing key‑value caches in large language models. It uses a chunk‑summarization diagnostic task to identify attention heads that specialize in hierarchical information aggregation, allowing the KV cache budget to be allocated based on each head’s summarization score. Experiments on Qwen2.5‑7B‑1M and Qwen3‑32B show state‑of‑the‑art performance on up to 1M‑token contexts while cutting KV cache memory usage by up to 75%.
By Zeyu Liu, Woomin Song, Xuandi Fu, Sai Muralidhar Jayanthi, Vivek Govindan, Aram Galstyan, Sravan Babu Bodapati, Srikanth Ronanki
arXiv:2604. 24432v2 Announce Type: replace-cross Abstract: Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agentic intelligence and recommendation system.
By Chenglong Chu, Guorui Zhou, Guowang Zhang, Han Li, Hao Peng, Hongtao Cheng, Hui Wang, Jian Liang, Jiangxia Cao, Kun Gai, Lingzhi Zhou, Lu Ren, Qi Zhang, Ruiming Tang, Ruitao Wang, Xinchen Luo, Yi Su, Zhiyuan Liang, Ziqi Wang, Boyang Ding, Chengru Song, Dunju Zang, Jiao Ou, Jiaxin Deng, Jijun Shi, Jinghao Zhang, Junmin Chen, Lejian Ren, Minxuan Lv, Qianqian Wang, Qigen Hu, Shiyao Wang, Siyang Mao, Tao Wang, Xingmei Wang, Zhixin Ling, Ziming Li, Zixing Zhang
SGD-KV is a head‑aware framework that compresses key‑value caches in large language models by using a chunk‑summarization diagnostic task to identify attention heads that specialize in hierarchical information aggregation. It prioritizes these heads during compression, achieving state‑of‑the‑art performance on long‑context benchmarks with up to 1M tokens while cutting KV cache memory usage by as much as 75%. Experiments on Qwen2.5‑7B‑1M and Qwen3‑32B confirm that allocating cache budget based on summarization scores yields a superior efficiency‑accuracy trade‑off for long‑context inference.
arXiv:2607. 16213v1 Announce Type: new Abstract: Large Language Models (LLMs) generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length, creating a major bottleneck.
By Soumia Bouyahiaoui, Manel Kara laouar, Aicha Boutorh, Mohamed Hadj Ameur
arXiv:2606. 06467v1 Announce Type: cross Abstract: Long-context inference in modern LLMs is increasingly constrained by decoding efficiency, especially in reasoning-heavy settings where models generate long intermediate chains of thought.
By Yutao Sun, Yanqi Zhang, Li Dong, Jianyong Wang, Furu Wei
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
arXiv:2607. 06523v1 Announce Type: new Abstract: Long-context language model inference is increasingly limited by the memory bandwidth and capacity required to store key-value caches, yet existing compression methods often apply uniform budgets across layers or tokens and degrade retrieval when lexical cues and semantic states require different preservation.
By Anna Cordoba, Adam Puente Tercero, Nerea Angulo Hijo, Mar Linares Tercero, Julia Barrientos, Ainhoa Miranda, Jesus Olivera
arXiv:2607. 05399v1 Announce Type: cross Abstract: Large language model serving is increasingly limited by KV-cache growth under long-context workloads, yet existing KV-cache compression techniques are difficult to compare because they were evaluated on different models, tasks, budgets, and serving stacks.
By Nikita Agrawal, Ruben Mayer
CompKV introduces a compensation‑aware sparse attention framework for long‑context LLM inference. It partitions tokens into blocks and optimizes token selection to minimize the error introduced by block‑level mean compensation, using compact block‑level statistics. Experiments on RULER and LongBench‑Pro show CompKV outperforms other sparse baselines and achieves up to a 6.85× speedup over full attention.
By Zhen Huang, Ruizhe Yao, Danyi Liu, Xinrui Chen, Shuwei Li, Siru Zhong, Zijian Cao, Yushan Lai, Mingming Guo, Weijie Zheng, Haohuan Fu
arXiv:2610.06927v1 Announce Type: cross
Abstract: The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free r...
By Sara Abdali, Jongwoo Ko, Pashmina Cameron
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