Zean Han

Ruihan Lin, Zezhen Ding, Zean Han et al.

Large Language Models (LLMs) are rapidly becoming critical infrastructure for enterprise applications, driving unprecedented demand for GPU-based inference services. A key operational challenge arises from the two-phase nature of LLM inference: a compute-intensive \emph{prefill} phase that processes user input, followed by a memory-bound \emph{decode} phase that generates output tokens. When these phases share GPU resources, prefill tasks throttle the processing speed of concurrent decodes, creating state-dependent contention. This contention is further complicated by workload heterogeneity, as different applications exhibit vastly different input and output lengths. We develop a stochastic control framework for scheduling heterogeneous LLM workloads across large GPU clusters. We formulate LLM inference as a multiclass many-server queueing network with state-dependent service rates, grounded in empirical iteration-time measurements. We analyze the fluid approximation of this system and solve steady-state linear programs that characterize optimal resource allocation. We design gate-and-route policies that regulate prefill admission and decode routing, and prove that they are asymptotically optimal in the many-GPU limit under both bundled and separate token-pricing schemes. We further extend the framework to incorporate Service Level Indicators (SLIs) such as latency and fairness, providing a general approach to constrained scheduling. Numerical experiments calibrated to empirical iteration-time data demonstrate that our policies outperform standard serving heuristics.

Zean Han, Ruihan Lin, Zezhen Ding et al.

We study offline-to-online learning in linear contextual bandits with biased offline regression data: the offline parameter need not match the online one, so history should not be treated as a single warm start. We model directional transfer with a shift certificate $(M_{\mathrm{shift}},ρ)$ and offline ridge estimation, yielding a geometry-aware confidence region for the online parameter rather than an isotropic radius. We propose \emph{Ellipsoidal-MINUCB}, which combines a standard online branch with an offline-informed pooled branch and uses offline information only when it tightens uncertainty. With high probability, regret is bounded by the minimum of a standard SupLinUCB-style fallback and a pooled term that separates statistical width from a certificate-weighted shift penalty. Under a simple alignment condition, the pooled term further simplifies to a rate governed by an effective dimension induced by the offline geometry. We also show that a purely Euclidean (scalar) shift bound, by itself, does not determine which feature directions are transferable. Beyond this fixed certificate, we show how to learn a data-driven certificate from data at finitely many refresh times and establish a high-probability regret bound for Ellipsoidal-MINUCB with epoch-wise learned certificates. Experiments match the main prediction: gains are strongest at intermediate horizons when offline coverage and transferability align, while the method otherwise tracks the safe online baseline.