Request-Level Energy Attribution for Batched LLM Serving

arXiv:2605.21427v1 Announce Type: new Abstract: Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and

arXiv:2603.25498v1 Announce Type: new Abstract: As the Web transitions from static retrieval to generative interaction, the escalating environmental footprint of Large Language

arXiv:2608.08382v1 Announce Type: new Abstract: As LLM inference shifts to multi-tenant GPU clusters, co-batching improves throughput but obscures per-tenant usage and limits

arXiv:2609.03716v1 Announce Type: new Abstract: Data centers are increasingly optimized by artificial intelligence and, at the same time, increasingly loaded by it. The literature

arXiv:2604.00053v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly used in domain-specific applications, including climate change and environmental

<p>The conventional view holds that edge‑LLM runtimes are limited by static, rule‑of‑thumb scaling of compute and memory, leaving most of the device’s power budget unused. QEIL v2

arXiv:2605.00254v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) architectures have turned LLM serving into a cluster-scale workload in which communication consumes a

<p>Data centers will drive 40% of electricity demand growth through the end of the decade, according to Goldman Sachs. Most conversations about fixing that focus on chips,