Metraipolis › archive › dc_cc87b3638f65
HeatCache: Thermal-aware Energy-efficient LLM Inference Scheduling for Chassis-level Liquid Cooling in Sustainable Edge Server Rooms — arXiv:2609.12449
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12449
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:08:36.969Z
- SHA-256 of the archived text
499adb113f13c4f4c6e72881210d1b9c3938a0cd51dafc9bb4dcf4f26aaa0382- Stable URL of this page
https://metraipolis.com/documento/dc_cc87b3638f65
How to cite
HeatCache: Thermal-aware Energy-efficient LLM Inference Scheduling for Chassis-level Liquid Cooling in Sustainable Edge Server Rooms — arXiv:2609.12449 — arXiv (en), https://arxiv.org/abs/2609.12449 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc87b3638f65 (Metraipolis archive dc_cc87b3638f65, sha256 499adb113f13c4f4c6e72881210d1b9c3938a0cd51dafc9bb4dcf4f26aaa0382)
BibTeX
@misc{dccc87b3638f65,
title = {HeatCache: Thermal-aware Energy-efficient LLM Inference Scheduling for Chassis-level Liquid Cooling in Sustainable Edge Server Rooms — arXiv:2609.12449},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12449},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc87b3638f65; sha256 499adb113f13c4f4c6e72881210d1b9c3938a0cd51dafc9bb4dcf4f26aaa0382},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12449. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM inference is increasingly deployed at institution-scale edges to meet service requirements. However, multi-GPU inference consumes a large amount of electricity and produces substantial heat. To improve sustainability, operators and regulations often demand raising the ambient setpoint to reduce cooling electricity. This can increase thermal throttling and hardware aging, leading to Service-Level Objective violations. In this paper, we present HeatCache, a thermal-aware, energy-efficient LLM inference scheduler for commercial chassis-level AIO liquid-cooled GPUs at sustainable ambient temperatures. HeatCache treats AIO loops as a temporary heat buffer, measured by heat budget and schedules requests to minimize energy subject to thermal safety and SLO constraints, based on an electrical-informed heat-demand estimation from HeatiTS. We implement HeatCache atop vLLM and show that it reduces computing energy by up to 18.0%, decreases thermal-throttle exposure by 81.7%, and maintains SLO violation rates below 0.9% even up to $48~^{\circ}\mathrm{C}$.
Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-14 in cs.DC).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Performance (cs.PF); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.12449 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T03:03:05.087Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).