PowerSlider: Exploiting Phase Asymmetry for LLM Serving under Demand Response

arXiv:2608.21719v1 Announce Type: cross Abstract: AI inference clusters are increasingly constrained by instantaneous power, not just energy: grid operators condition new capacity on demand response, imposing time-varying power caps. Existing LLM serving systems optimize a static energy objective or shed fixed priority tiers under load; either way, goodput collapses when the power envelope moves. An LLM pipeline is not a uniform load: compute-bound prefill loses throughput almost linearly with GPU frequency, memory-bound answer decode sustains it down to 0.57imes nominal, and reasoning's thinking phase couples KV-cache capacity to scheduling -- so a cap should be steered to where each watt costs the least performance. PowerSlider does so with a new Flex SLO contract that turns bounded user slack into an optimization constraint, prefill--think--answer disaggregation exposing per-stage frequency and KV control, and a Karush--Kuhn--Tucker (KKT) online solver re-solving within 7.7 ms of every cap change, backed by a consolidated fail-safe that power-gates drained instances when DVFS bottoms out on static power. On SGLang with production traces, sys{} sustains 78.3% online goodput at a 30% cap reduction versus 47.6% for the best of five baselines (1.64imes), holds latency-critical tails within 1.3imes of nominal (baselines: 2.3--6imes, up to 12imes), and delivers 92% mean goodput through a replayed CAISO grid-emergency day bottoming at 0.41imes (54% at the trough; every baseline below 7%).

Related

• XWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy Farms
• Power-Flexible AI Data Centers: A New Paradigm for Grid-Responsive Compute
• TokenPowerSandbox: Evidence-Gated CPU-First Screening for Energy-Aware LLM Serving
• VoltanaLLM: Energy-Efficient and SLO-Aware Disaggregated LLM Serving via Adaptive Frequency Control and State-Space Routing
• PALS: Power-Aware LLM Serving for Mixture-of-Experts Models

Source: arXiv cs.AI | 2026-09-01