arXiv:2608. 07747v1 Announce Type: new Abstract: We study how to share a single conserved capacity budget across many locations and two service classes when demand is uneven, time-varying, and can exceed supply.
arXiv:2607. 16891v1 Announce Type: cross Abstract: A truckload carrier must accept or reject each load tender within seconds.
The paper argues that large language model (LLM) providers, constrained by compute, often degrade service during congestion by routing queries to smaller models, cutting reasoning effort, or truncating context. It shows that this practice misrepresents costs because degraded answers can fail, leading to retries that inflate traffic or churn that erodes lifetime value. By modeling inference allocation with newsvendor, retry, and queueing frameworks, the authors derive a ‘shadow price of intelligence’ that quantifies the marginal value of each query, revealing that throttling under congestion acts as a demand lever rather than a cost lever.
arXiv:2606. 10472v1 Announce Type: cross Abstract: Dynamic multi-resource allocation is a central problem in shared computing environments, where users' demands arrive sequentially and resources must be distributed fairly without knowledge of future demands.
The paper proposes a method for routing requests to a fixed pool of quantized Mixture-of-Experts (MoE) instances, aiming to maximize throughput while respecting a quality‑degradation budget. It introduces Fragility‑Weighted Perplexity (FWP) as a request‑specific risk metric derived from prompt tokens, and uses a window‑level linear program to compute a reduced‑reward score that aligns with the LP optimum. Experiments on Qwen prompts show that FWP‑based allocation improves throughput by 2.5% over request‑agnostic mixing and static configurations.
arXiv:2607. 26788v1 Announce Type: cross Abstract: Clustered federated learning benefits from organizing heterogeneous participants into coalitions that train coalition-specific models, but such clustering is sustainable only if participants prefer their assigned coalition and the required transfers are affordable.
arXiv:2607. 08565v1 Announce Type: cross Abstract: LLM scheduling is critical to serving, yet it remains unclear how well existing designs fit agentic serving--with LLM requests issued by agents instead of humans.
arXiv:2606. 27743v1 Announce Type: cross Abstract: Large Language Models (LLMs) inference is typically deployed under a static resource assumption, where models execute a fixed computational graph regardless of the runtime environment.
arXiv:2606. 17081v1 Announce Type: cross Abstract: Disaggregated inference architectures physically separate prefill and decode phases onto distinct GPU pools, creating competing "agents" that share a fixed hardware budget.
arXiv:2505.02796v3 Announce Type: replace-cross Abstract: We study budget pacing in repeated first-price auctions when an advertiser's private-value distributions change over time and the stationary...
arXiv:2606. 15555v1 Announce Type: cross Abstract: In large language model (LLM) serving, each request accumulates persistent graphics processing unit (GPU) memory during service as its key-value cache grows with every generated token.
arXiv:2607. 04206v1 Announce Type: cross Abstract: Diffusion language models (dLLMs) generate text by iteratively denoising a masked response and can commit multiple output positions per model invocation.
arXiv:2607. 05272v1 Announce Type: cross Abstract: Inference serving systems must balance throughput and latency under bursty, heterogeneous workloads, yet the industry standard remains static batching policies that require manual tuning and cannot adapt to shifting traffic.