@article{heraaheterogeneityawaremultitenant, title = {Hera: A Heterogeneity-Aware Multi-Tenant Inference Server for Personalized Recommendations}, author = {Yujeong Choi and John Kim and Minsoo Rhu}, year = {2023}, eprint = {2302.11750}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2302.11750v1}, }