Metraipolis › archive › dc_1db3d464b211
ThermE: Predictive Management of Shared Thermal Headroom for Sustained LLM Inference on Thermally Constrained Edge SoCs — arXiv:2610.00267
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00267
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:30:28.981Z
- SHA-256 of the archived text
887668d098c77d1baeabd84c7f4f580b8fe9ad7ad26bd1b0b9c70d17807f4be0- Stable URL of this page
https://metraipolis.com/documento/dc_1db3d464b211
How to cite
ThermE: Predictive Management of Shared Thermal Headroom for Sustained LLM Inference on Thermally Constrained Edge SoCs — arXiv:2610.00267 — arXiv (en), https://arxiv.org/abs/2610.00267 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1db3d464b211 (Metraipolis archive dc_1db3d464b211, sha256 887668d098c77d1baeabd84c7f4f580b8fe9ad7ad26bd1b0b9c70d17807f4be0)
BibTeX
@misc{dc1db3d464b211,
title = {ThermE: Predictive Management of Shared Thermal Headroom for Sustained LLM Inference on Thermally Constrained Edge SoCs — arXiv:2610.00267},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00267},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1db3d464b211; sha256 887668d098c77d1baeabd84c7f4f580b8fe9ad7ad26bd1b0b9c70d17807f4be0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00267. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Compact edge system-on-chip (SoC) platforms increasingly run sustained LLM inference under thermal constraints, while their CPU, GPU, and RAM share a cooling path. Prefill and decode therefore consume shared, time-varying thermal headroom, yet vendor governors react only near hardware throttling thresholds without knowledge of request state or upcoming work. A control decision that improves current performance can thus consume headroom too quickly and degrade subsequent service. In this paper, we present ThermE, a runtime system that predicts and jointly manages shared thermal headroom for sustained LLM inference on edge SoCs. Its Fast LLM-to-Heat Compiler maps the model, requests, runtime state, and candidate actions to domain heats without executing LLMs. A partial differential equation (PDE)-constrained Headroom Predictor uses ThermPINN for offline thermal identification and a Reduced Headroom Predictor (RHP) for low-overhead online uncertainty-calibrated headroom forecasts. An Uncertainty-Aware Action Scheduler then selects actions that balance serving quality and future headroom. We implement ThermE atop vLLM and evaluate it across four LLM inference workloads. The results show that ThermE reduces TTFT and TPOT by 40.55% and 12.17%, respectively, relative to vLLM. It achieves a 5.70% SLO violation rate, compared with 12.30% for the strongest baseline, while its predictor obtains a 1.94 $^\circ$C MAE with 11.50 ms overhead. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-10-02 in eess.SY). Categorie arXiv: Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2610.00267 — 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 2026-10-07T12:03:07.602Z dalla pagina https://arxiv.org/catchup/eess.SY/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).