method · first seen 4 Oct 2026
KV cache eviction
Also: KV eviction, key-value cache eviction
Discarding stored key-value cache entries during decoding to bound memory use in transformer inference.
Mentions per week
PapersCodeDiscussion
Rank 167 on 16 Nov 2026 · 8 mentions in 28 days · 8 independent groups · papers · first seen 6 weeks ago · acceleration +1.36
Earliest sources
- Mask-Guided KV Cache Eviction in Block Diffusion Language ModelsPapers · 4 Oct 2026 · Gleb Molodtsov, Ekaterina Alimaskina, Evgeny Uskov, Artur Zagitov, Aleksandr Bez…
- Monte Carlo Estimation for KV Cache EvictionPapers · 6 Oct 2026 · Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Wajih Hassan Raza, Atta Ul As…
- GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMsPapers · 10 Oct 2026 · Junjie Li, Jiong Lou, Jie Li
- TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language ModelsPapers · 13 Oct 2026 · Kai Liu, Anqi Li, Junxian Li, Zhixin Wang, Zhikai Chen, Renjing Pei, Yulun Zhang
- DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache EvictionPapers · 15 Oct 2026 · Aozhong Zhang, Selcuk Gurses, Yanxia Deng, Naigang Wang, Chi-Chun Liu, Davis Wer…
- Rethinking KV Cache Eviction for Agentic LLM ServingPapers · 30 Oct 2026 · Jiakun Fan, Han Meng, Yuxuan Xia, Hao Mark Chen, Dong Li, Dimitrios S. Nikolopou…
Latest sources
- AutoAssumption: Searching over Assumptions Discovers ML-Systems AlgorithmsPapers · 10 Nov 2026 · Igor Sadalski, Minghao Guo, Benjamin Jones, Wojciech Matusik
- Evolving Infra: Agent-Adaptive LLM Serving at ScalePapers · 9 Nov 2026 · Hao Kang, Weili Xu, Ziyang Li, Zheng Du, Hanchen Li, Tian Xia, Song Bian, Tushar…
- PACE: Keeping the Right Tokens in the KV Cache Is Not Enough for Long-Horizon LLM AgentsPapers · 6 Nov 2026 · Suman Chatterjee
- Intent-Aware Caching for Efficient LLM ServingPapers · 6 Nov 2026 · Kazi Hasan Ibn Arif, JinYi Yoon, Dimitrios S. Nikolopoulos, Hans Vandierendonck,…
- The Gating Mechanism of KV Cache EvictionPapers · 5 Nov 2026 · Hao Gu, Xintong Yang, Zhiwei Li, Lei Zhu, Jian Yang, Qiyuan Zhu, Dezhi Li, Jingy…
- EchoKV: Self-Corrective KV Cache Eviction via Iterative Query FeedbackPapers · 4 Nov 2026 · JianKun Zou, Tongtong Yuan
- Who Should Score the Cache? Mid-Depth Layers Are the Best Judges of KV-Cache EvictionPapers · 1 Nov 2026 · Ekaterina Seregina
- Rethinking KV Cache Eviction for Agentic LLM ServingPapers · 30 Oct 2026 · Jiakun Fan, Han Meng, Yuxuan Xia, Hao Mark Chen, Dong Li, Dimitrios S. Nikolopou…
- DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache EvictionPapers · 15 Oct 2026 · Aozhong Zhang, Selcuk Gurses, Yanxia Deng, Naigang Wang, Chi-Chun Liu, Davis Wer…
- TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language ModelsPapers · 13 Oct 2026 · Kai Liu, Anqi Li, Junxian Li, Zhixin Wang, Zhikai Chen, Renjing Pei, Yulun Zhang
- GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMsPapers · 10 Oct 2026 · Junjie Li, Jiong Lou, Jie Li
- Monte Carlo Estimation for KV Cache EvictionPapers · 6 Oct 2026 · Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Wajih Hassan Raza, Atta Ul As…