Please log in to take part in the discussion (add own reviews or comments).
Cite this publication
More citation styles
- please select -
%0 Journal Article
%1 journals/corr/abs-2402-18096
%A Yang, June Yong
%A Kim, Byeongwook
%A Bae, Jeongin
%A Kwon, Beomseok
%A Park, Gunho
%A Yang, Eunho
%A Kwon, Se Jung
%A Lee, Dongsoo
%D 2024
%J CoRR
%K dblp
%T No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization.
%U http://dblp.uni-trier.de/db/journals/corr/corr2402.html#abs-2402-18096
%V abs/2402.18096
@article{journals/corr/abs-2402-18096,
added-at = {2024-03-26T00:00:00.000+0100},
author = {Yang, June Yong and Kim, Byeongwook and Bae, Jeongin and Kwon, Beomseok and Park, Gunho and Yang, Eunho and Kwon, Se Jung and Lee, Dongsoo},
biburl = {https://www.bibsonomy.org/bibtex/2efc88f02a90f713b52603edeba7b8927/dblp},
ee = {https://doi.org/10.48550/arXiv.2402.18096},
interhash = {91bb6f409019e586d3bf6b42970a35ec},
intrahash = {efc88f02a90f713b52603edeba7b8927},
journal = {CoRR},
keywords = {dblp},
timestamp = {2024-04-08T23:33:23.000+0200},
title = {No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization.},
url = {http://dblp.uni-trier.de/db/journals/corr/corr2402.html#abs-2402-18096},
volume = {abs/2402.18096},
year = 2024
}