%0 Journal Article %1 journals/corr/abs-2403-09054 %A Adnan, Muhammad %A Arunkumar, Akhil %A Jain, Gaurav %A Nair, Prashant J. %A Soloveychik, Ilya %A Kamath, Purushotham %D 2024 %J CoRR %K dblp %T Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference. %U http://dblp.uni-trier.de/db/journals/corr/corr2403.html#abs-2403-09054 %V abs/2403.09054

@article{journals/corr/abs-2403-09054, added-at = {2024-04-05T00:00:00.000+0200}, author = {Adnan, Muhammad and Arunkumar, Akhil and Jain, Gaurav and Nair, Prashant J. and Soloveychik, Ilya and Kamath, Purushotham}, biburl = {https://www.bibsonomy.org/bibtex/2603af65adcd8ce4597eabd164513ab40/dblp}, ee = {https://doi.org/10.48550/arXiv.2403.09054}, interhash = {d3a5026718332029c46ae347278c9711}, intrahash = {603af65adcd8ce4597eabd164513ab40}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-08T22:44:57.000+0200}, title = {Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2403.html#abs-2403-09054}, volume = {abs/2403.09054}, year = 2024 }