ARKV: Adaptive and Resource-Efficient KV Cache Management Under Limited Memory Budget for Long-Context Inference in LLMs

2026 IEEE 26th International Symposium on Cluster, Cloud and Internet Computing (CCGrid) 2026

View at publisher
Authors: Jianlong Lei, Shashikant Ilager
DOI: 10.1109/ccgrid68966.2026.00015
Cited by: 1
References: 10

Publication details

Journal / source
2026 IEEE 26th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)
Publisher
IEEE
Pages
54–63
Publication date
1 May 2026