Salmani, Mehran, Ghafouri, Saeid, Sanaee, Alireza, Razavi, Kamran, Mühlhäuser, Max, Doyle, Joseph, Jamshidi, Pooyan, and Sharifi, Mohsen. Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems. Retrieved from https://par.nsf.gov/biblio/10443138. EuroMLSys '23: Proceedings of the 3rd Workshop on Machine Learning and Systems . Web. doi:10.1145/3578356.3592578.

Salmani, Mehran, Ghafouri, Saeid, Sanaee, Alireza, Razavi, Kamran, Mühlhäuser, Max, Doyle, Joseph, Jamshidi, Pooyan, & Sharifi, Mohsen. Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems. EuroMLSys '23: Proceedings of the 3rd Workshop on Machine Learning and Systems, (). Retrieved from https://par.nsf.gov/biblio/10443138. https://doi.org/10.1145/3578356.3592578

Salmani, Mehran, Ghafouri, Saeid, Sanaee, Alireza, Razavi, Kamran, Mühlhäuser, Max, Doyle, Joseph, Jamshidi, Pooyan, and Sharifi, Mohsen. "Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems". EuroMLSys '23: Proceedings of the 3rd Workshop on Machine Learning and Systems (). Country unknown/Code not available. https://doi.org/10.1145/3578356.3592578. https://par.nsf.gov/biblio/10443138.

@article{osti_10443138,
place = {Country unknown/Code not available}, title = {Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems}, url = {https://par.nsf.gov/biblio/10443138}, DOI = {10.1145/3578356.3592578}, abstractNote = {}, journal = {EuroMLSys '23: Proceedings of the 3rd Workshop on Machine Learning and Systems}, author = {Salmani, Mehran and Ghafouri, Saeid and Sanaee, Alireza and Razavi, Kamran and Mühlhäuser, Max and Doyle, Joseph and Jamshidi, Pooyan and Sharifi, Mohsen}, }