Information-Density Driven Token Eviction: Dynamic KV-Cache Pruning for Extreme Resource-Constrained Small Language Models
International Journal of Scientific Research in Engineering and Management · 2026-06 · 10 (6)
DOI: 10.55041/ijsrem65313 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Scientific Research in Engineering and Management, 2026-06. Verfasst von Chinmay Kamble Chinmay Kamble.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Zitieren
APA
Kamble, C. K. C. (2026). Information-Density Driven Token Eviction: Dynamic KV-Cache Pruning for Extreme Resource-Constrained Small Language Models. International Journal of Scientific Research in Engineering and Management, 10(6). https://doi.org/10.55041/ijsrem65313
Vancouver
Kamble CKC. Information-Density Driven Token Eviction: Dynamic KV-Cache Pruning for Extreme Resource-Constrained Small Language Models. International Journal of Scientific Research in Engineering and Management. 2026;10(6). doi:10.55041/ijsrem65313
BibTeX
@article{Kamble2026,
author = {Kamble, Chinmay Kamble Chinmay},
title = {Information-Density Driven Token Eviction: Dynamic KV-Cache Pruning for Extreme Resource-Constrained Small Language Models},
journal = {International Journal of Scientific Research in Engineering and Management},
year = {2026},
volume = {10},
number = {6},
doi = {10.55041/ijsrem65313}
}
EUVIMED