[2605.07985] Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation
View PDFHTML (experimental)Abstract:Selecting the optimal LLM inference configuration requires evaluation across hardware, serving engines, attention backends, and model architectures, since no single choice performs best across all workloads. Profile-based simulators are the standard tool, yet they hardcode their operation set to a specific ...