Book
Open access
Sep 2026
Cerium: A Multi-GPU Framework for Terabyte-Scale Encrypted Inference
Cerium is a multi-GPU framework for large-scale FHE inference that combines a domain-specific language, an optimizing compiler, and a runtime system to automatically generate optimized GPU kernels, compress plaintext data, manage terabyte-scale memory footprints, and optimize multi-GPU communication.
Siddharth Jayashankar, Joshua Kim, Michael B. Sullivan et al.
· Proceedings of the ACM SIGOP... · 0 citations