%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 }