LiteKV: A KV cache compression method for efficient inference on resource-constrained devices.
| Anthology ID: | DBLP:journals/ipm/ZhangI26 |
|---|---|
| Year: | 2026 |
| Venue: | Information Processing and Management |
| Pages: | 104889 |
| URL: | https://doi.org/10.1016/J.IPM.2026.104889 |
| DOI: | https://doi.org/10.1016/J.IPM.2026.104889 |
| DBLP: | journals/ipm/ZhangI26 |
| BibTeX: |
@article{zhang-2026-litekv,
author = {Zhipeng Zhang and
Dmitry Ilvovsky},
title = {{LiteKV: A KV cache compression method for efficient inference on resource-constrained devices}},
journal = {Information Processing and Management},
volume = {63},
number = {8},
pages = {104889},
year = {2026},
url = {https://doi.org/10.1016/J.IPM.2026.104889},
doi = {https://doi.org/10.1016/J.IPM.2026.104889}
}