Compositional Performance Modeling of LLM Inference Clusters with Hierarchical KV Caching

Abstract

Design-space exploration of LLM inference clusters requires predicting how hardware and serving policies interact with hierarchical key-value (KV) caching. Isolated operation profiles alone do not determine cluster latency: reuse changes computational demand, while KV location, capacity, and contention govern execution order. We present a compositional discrete-event simulator based on separating local service costs from shared resource and KV availability. Compute and transfer models calibrated on one-prefill/one-decode (1P-1D) deployments are reused across compatible workers, enabling policy and topology comparisons without per-configuration latency fitting. Validation against SGLang covers Qwen3-8B and Qwen3-32B on 1P-1D and 3P-1D clusters. Mean request end-to-end latency error is 1.34% for question answering and 6.36% for captured coding sessions, measured as mean absolute percentage error. CPU simulation reduces replay turnaround by 15.33 times on average; real replay includes prescribed arrival gaps. Measured session-affinity and simulated retention studies demonstrate how the framework guides policy selection by predicting the joint effects on computation, latency, and KV occupancy.