AI RESEARCH
LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure
arXiv CS.AI
•
ArXi:2602.23036v2 Announce Type: replace-cross Large language model (LLM) serving infrastructures are undergoing a shift toward heterogeneity and disaggregation. Modern deployments increasingly integrate diverse accelerators and near-memory processing technologies, This paper presents LLMServingSim 2.0, a unified system-level simulator designed to make runtime-driven hardware-software interactions in heterogeneous and disaggregated LLM serving infrastructures explicit and analyzable.