EUVIMEDEUVIMED entdecken
Crossref

Prompt Caching on Flash: Achieving Memory-Class Latency for LLM Inference

Joohee Lee, Kwangjin Ko, Taeho Hwang, Woosuk Chung, Hoshik Kim, Donguk Moon

IEEE Computer Architecture Letters · 2026-07 · 25 (2) · 295-298

DOI: 10.1109/lca.2026.3711675 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Computer Architecture Letters, 2026-07. Verfasst von Joohee Lee und 5 weiteren Autor:innen. Die Arbeit nennt 5 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Zitieren

APA

Lee, J., Ko, K., Hwang, T., Chung, W., Kim, H., & Moon, D. (2026). Prompt Caching on Flash: Achieving Memory-Class Latency for LLM Inference. IEEE Computer Architecture Letters, 25(2), 295-298. https://doi.org/10.1109/lca.2026.3711675

Vancouver

Lee J, Ko K, Hwang T, Chung W, Kim H, Moon D. Prompt Caching on Flash: Achieving Memory-Class Latency for LLM Inference. IEEE Computer Architecture Letters. 2026;25(2):295-298. doi:10.1109/lca.2026.3711675

BibTeX
@article{Lee2026,
  author = {Lee, Joohee and Ko, Kwangjin and Hwang, Taeho and Chung, Woosuk and Kim, Hoshik and Moon, Donguk},
  title = {Prompt Caching on Flash: Achieving Memory-Class Latency for LLM Inference},
  journal = {IEEE Computer Architecture Letters},
  year = {2026},
  volume = {25},
  number = {2},
  pages = {295--298},
  doi = {10.1109/lca.2026.3711675}
}
Kostenlos starten →