Metraipolis › archive › dc_516a71407330

Cloud, Edge, or Split? Profiling Onboard and Split Vision-Language Model Deployment for Drone AI — arXiv:2609.25415

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25415
License (as archived)
CC0-1.0
Archived
2026-10-08T14:37:19.446Z
SHA-256 of the archived text
8a15c92e89d2b81d1a3fc20a05d6f7e49f73aab5771a4a29a3e0010bf13d7b6b
Stable URL of this page
https://metraipolis.com/documento/dc_516a71407330

How to cite

Cloud, Edge, or Split? Profiling Onboard and Split Vision-Language Model Deployment for Drone AI — arXiv:2609.25415 — arXiv (en), https://arxiv.org/abs/2609.25415 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_516a71407330 (Metraipolis archive dc_516a71407330, sha256 8a15c92e89d2b81d1a3fc20a05d6f7e49f73aab5771a4a29a3e0010bf13d7b6b)
BibTeX
@misc{dc516a71407330,
  title = {Cloud, Edge, or Split? Profiling Onboard and Split Vision-Language Model Deployment for Drone AI — arXiv:2609.25415},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25415},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_516a71407330; sha256 8a15c92e89d2b81d1a3fc20a05d6f7e49f73aab5771a4a29a3e0010bf13d7b6b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25415. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language Models (VLMs) enable edge devices like unmanned aerial vehicles (UAVs) to interpret visual observations and reason about complex environments using natural-language instructions. However, their practical deployment remains challenging as onboard inference is constrained by limited computational, memory, and energy resources, whereas cloud-based inference introduces communication latency, bandwidth overhead, and dependence on network connectivity. To address these limitations, split computing offers a promising alternative by partitioning VLM inference between the resource-constrained UAVs and more capable remote servers. However, the performance trade-offs among fully onboard, cloud-based, and split-computing architectures for lightweight VLMs have not yet been systematically profiled. This paper benchmarks these three deployment paradigms using SmolVLM-256M as a representative lightweight VLM. We quantify their inference latency, computational resource utilization, communication overhead, and energy consumption across varying image resolutions and network conditions. Our results show that no deployment strategy is universally optimal; instead, the preferred strategy depends on the interaction between network conditions and input image resolution.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-23 in cs.DC).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2609.25415 — 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 2026-10-08T13:47:35.182Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).