Jun 2026
Energy-Aware Scheduling for Serverless LLM Serving on Shared GPUs
Festina is presented, a profiling-guided, power-aware control plane to minimize cluster-wide energy for serverless LLM serving and performs energy-aware workload consolidation to reduce GPUs'static power consumption via SLO-aware migration.
Tianyu Wang, Gourav Rattihalli, A. Dhakal et al.
· arXiv.org · 0 citations