Request-Level Energy Attribution for Batched LLM Serving

본문 미리보기

arXiv:2608.00026v1 Announce Type: new Abstract: Batched LLM serving improves throughput but complicates energy accounting. GPU power telemetry is aggregate, whereas sustainability reporting, chargeback, and workload analysis often require request-level energy charges. Existing inference-energy benchmarks report model-, phase-, or token-level energy, and recent carbon-accounting work motivates Shapley fairness conceptually. Neither provides measured request-level ground truth, so how far the acc