Metraipolis › archive › dc_b593ae186e59

PELM: Power Efficient On-Device LLM Inference with Speculative Decoding and Dynamic Voltage Frequency Scaling — arXiv:2609.09662

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.09662
License (as archived)
CC0-1.0
Archived
2026-10-16T07:53:36.135Z
SHA-256 of the archived text
d426b8d6e43599a5bd697dc2b1624c9e8ef811cf4760e242b11a2a3fef5f3623
Stable URL of this page
https://metraipolis.com/documento/dc_b593ae186e59

How to cite

PELM: Power Efficient On-Device LLM Inference with Speculative Decoding and Dynamic Voltage Frequency Scaling — arXiv:2609.09662 — arXiv (en), https://arxiv.org/abs/2609.09662 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b593ae186e59 (Metraipolis archive dc_b593ae186e59, sha256 d426b8d6e43599a5bd697dc2b1624c9e8ef811cf4760e242b11a2a3fef5f3623)
BibTeX
@misc{dcb593ae186e59,
  title = {PELM: Power Efficient On-Device LLM Inference with Speculative Decoding and Dynamic Voltage Frequency Scaling — arXiv:2609.09662},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09662},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b593ae186e59; sha256 d426b8d6e43599a5bd697dc2b1624c9e8ef811cf4760e242b11a2a3fef5f3623},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09662. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deploying Large Language Models (LLMs) directly on mobile platforms at the edge is gaining traction due to a myriad of benefits, such as increased privacy, personalization, and reduced latency. However, LLMs have heavy computational requirements, which are difficult for resource-constrained mobile and edge platforms to fulfill. In addition to limited compute resources, mobile and edge systems often have a compact form factor and lack physical mechanisms to dissipate heat generated from high processor usage rates (e.g., fans) to prevent throttling and reduced processing power, which LLMs can easily cause. To mitigate these effects, prior works have proposed various power governing strategies, such as dynamic voltage and frequency scaling (DVFS), for reducing power and heat generation for heavy computational tasks on mobile platforms. Recently, DVFS methods tailored for mobile LLMs have also been proposed. However, these methods mostly focus on optimizing hardware parameters and processor frequencies, and they fall short under some thermally constrained scenarios. Drawing from recent advances in machine learning, we identify and take advantage of the key insight that not all tokens require full-depth inference to maintain high-quality generation. Motivated by this, we present PELM, a solution that augments traditional DVFS processor frequency tuning with two additional workload-specific knobs: 1) speculative decoding and 2) variable verification depth to expand the optimization space to multiple dimensions for more power efficient on-device LLM inference. In extensive evaluations across hardware platforms and datasets, PELM demonstrates superior performance compared to state-of-the-art power governing methods, with up to 23.1% speedup and 52.4% reduction in energy consumption, while maintaining comparable task performance. The source code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CL).
Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL); Operating Systems (cs.OS); Performance (cs.PF).
Pagina del lavoro: https://arxiv.org/abs/2609.09662 — 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 2026-10-16T07:24:00.954Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).