SOURCE-LINKED INTELLIGENCE

Phase-Decoupled, Model-Calibrated Power Control for Disaggregated LLM Serving

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Datacenter GPU power is the binding constraint on LLM serving capacity, and production serving has shifted to prefill/decode (PD) disaggregation. Deploying NVIDIA's Max-Q inference profile on a disaggregated B200 system, we found its realized gain modest (+8.6% tokens/J), model-dependent, and carrying a mean end-to-end latency cost (+5.2%) that throughput-only evaluation does not surface; the profile also applies one setting to prefill and decode GPUs that operate in opposite hardware regimes. We hypothesize that the optimal power setting is a property of the deployed (model, quantization, eng

Read original source ↗ Open in workspace

recordType

paper

region

Global