A Go-based LLM serving control plane that models token-aware scheduling, request lifecycle, streaming metrics, prefix cache, and KV block pressure around mock inference backends.

🏆[ICML 2026 Spotlight] Official implementation of "DecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions"

A datacenter-scale simulation framework for energy- and SLO-aware LLM inference serving — non-invasive extension of CloudSim Plus

A curated map of AFD, PD disaggregation, KV-cache systems, MoE serving, and re-aggregation baselines for LLM serving.