HiLLM: Heterogeneous CPU–GPU Inference for Interactive MoE LLM Serving on Local Systems

Publication
2026 59th IEEE/ACM International Symposium on Microarchitecture (MICRO)
Insu Choi
Insu Choi
Ph.D. Candidate · AI Accelerators & Computer Architecture

My research interests include AI/ML, AI accelerators and memory reliability.