KiF: Accelerating Low-Batch LLM Inference Using In-Flash KV Cache
IEEE Computer Architecture Letters · 2026-01 · 25 (1) · 174-177
DOI: 10.1109/lca.2026.3689575 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Computer Architecture Letters, 2026-01. Verfasst von Haeeun Jung und 6 weiteren Autor:innen. Die Arbeit nennt 10 Literaturangaben. Gefördert von: Institute for Information & communications Technology Planning, Ministry of Science and ICT, South Korea, Republic of Korea.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Institute for Information & communications Technology Planning
- Ministry of Science and ICT, South Korea
- Republic of Korea
- Global Scholars Invitation Program
- Samsung Electronics Coompany
- ICT at Seoul National University
Zitieren
APA
Jung, H., Lee, J., Lee, S., Yun, H., Jeon, D., Kim, N. S., & Kim, J. (2026). KiF: Accelerating Low-Batch LLM Inference Using In-Flash KV Cache. IEEE Computer Architecture Letters, 25(1), 174-177. https://doi.org/10.1109/lca.2026.3689575
Vancouver
Jung H, Lee J, Lee S, Yun H, Jeon D, Kim NS, et al. KiF: Accelerating Low-Batch LLM Inference Using In-Flash KV Cache. IEEE Computer Architecture Letters. 2026;25(1):174-177. doi:10.1109/lca.2026.3689575
BibTeX
@article{Jung2026,
author = {Jung, Haeeun and Lee, Jaeyong and Lee, Sanggu and Yun, Huiwon and Jeon, Dongsuk and Kim, Nam Sung and Kim, Jihong},
title = {KiF: Accelerating Low-Batch LLM Inference Using In-Flash KV Cache},
journal = {IEEE Computer Architecture Letters},
year = {2026},
volume = {25},
number = {1},
pages = {174--177},
doi = {10.1109/lca.2026.3689575}
}
EUVIMED