Yujeong Choi, John Kim 0001, Minsoo Rhu. Hera: A Heterogeneity-Aware Multi-Tenant Inference Server for Personalized Recommendations. In 34th International Conference on Parallel Architectures and Compilation Techniques, PACT 2025, Irvine, CA, USA, November 3-6, 2025. pages 320-332, IEEE, 2025. [doi]
Abstract is missing.