2 papers
cs.LG2026
A Simple Plug-in for Improving Eviction-Based KV Cache Compression
Yuping Lin, Jiayuan Ding, Yue Xing +3
KV cache growth is a major bottleneck for long-context inference in large language models. Existing methods are often dominated by binary eviction or representation approximation,…
cs.LG2026
ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier Detection
Debajyoti Datta, Trishala Neeraj, Bibek Paudel +2
Long-context inference is constrained by KV-cache memory, which grows linearly with sequence length; KV-cache compression therefore hinges on reliably selecting which past tokens t…