Metraipolis › archive › dc_14cf15fd449a

AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing — arXiv:2610.00465

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00465
License (as archived)
CC0-1.0
Archived
2026-10-06T17:48:06.729Z
SHA-256 of the archived text
2885067fd65d02c9003820a72ddc89b27aed8e1d39d884b4fef39d1b757f5427
Stable URL of this page
https://metraipolis.com/documento/dc_14cf15fd449a

How to cite

AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing — arXiv:2610.00465 — arXiv (en), https://arxiv.org/abs/2610.00465 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_14cf15fd449a (Metraipolis archive dc_14cf15fd449a, sha256 2885067fd65d02c9003820a72ddc89b27aed8e1d39d884b4fef39d1b757f5427)
BibTeX
@misc{dc14cf15fd449a,
  title = {AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing — arXiv:2610.00465},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00465},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_14cf15fd449a; sha256 2885067fd65d02c9003820a72ddc89b27aed8e1d39d884b4fef39d1b757f5427},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00465. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Next-generation large language models (LLMs) are expanding from the cloud to ubiquitous edge devices. However, edge devices typically either lack the memory to store increasingly large LLM weights or, even with enough memory, spend unaffordable energy on loading the weights. This raises our question: can an edge device run an LLM without storing or loading its weights, but receive them over the air and consume them on the fly? Inspired by wireless broadcasting, we present AIR-LLM, an LLM inference architecture for edge devices, which is composed of: (i) a central radio (e.g., 5G base stations) that broadcasts the LLM weights into the air, and (ii) the edge user that receives the weights and completes the general matrix-vector multiplication (GEMV) of LLM inference directly in the radio frequency (RF) domain using RF mixers. To further shorten the airtime, AIR-LLM exploits MIMO spatial multiplexing and proposes an energy-efficient precoder-postcoder pair on the edge to calibrate its own wireless channel. Since the central radio stays user-unaware, AIR-LLM is user-scalable so that one broadcast serves unlimited users within its coverage. We implement AIR-LLM on the NVIDIA Sionna ray-traced channels of two real-world urban scenes and the profiling of a real RF mixer. With a WikiText-2 perplexity degradation of 4.0% on LLaMA-3.1-8B, AIR-LLM saves the energy by 157.7x/40.4x against the FP16 and weight-only quantization baselines; with 20 users, its airtime is 104.1x/26.0x shorter, respectively.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-10-02 in math.IT).
Categorie arXiv: Information Theory (cs.IT) ; Emerging Technologies (cs.ET); Machine Learning (cs.LG); Signal Processing (eess.SP); Applied Physics (physics.app-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.00465 — 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 2026-10-06T16:13:30.416Z dalla pagina https://arxiv.org/catchup/math.IT/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).