%0 Journal Article %1 journals/corr/abs-2402-07033 %A Kamahori, Keisuke %A Gu, Yile %A Zhu, Kan %A Kasikci, Baris %D 2024 %J CoRR %K dblp %T Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models. %U http://dblp.uni-trier.de/db/journals/corr/corr2402.html#abs-2402-07033 %V abs/2402.07033

@article{journals/corr/abs-2402-07033, added-at = {2024-02-16T00:00:00.000+0100}, author = {Kamahori, Keisuke and Gu, Yile and Zhu, Kan and Kasikci, Baris}, biburl = {https://www.bibsonomy.org/bibtex/2fccac477130b4b410171a0e2968687a2/dblp}, ee = {https://doi.org/10.48550/arXiv.2402.07033}, interhash = {9d34479cdf2b13088e110ed1113e1c37}, intrahash = {fccac477130b4b410171a0e2968687a2}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-08T22:54:11.000+0200}, title = {Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2402.html#abs-2402-07033}, volume = {abs/2402.07033}, year = 2024 }