Metraipolis › archive › dc_2a47fb129ffb

EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints — arXiv:2608.15502

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.15502
License (as archived): CC0-1.0
Archived: 2026-10-18T17:20:10.734Z
SHA-256 of the archived text: a05871013c20f100d9507b592cb648873c3cab5c8464651add3550ac368b7c69
Stable URL of this page: https://metraipolis.com/documento/dc_2a47fb129ffb

How to cite

EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints — arXiv:2608.15502 — arXiv (en), https://arxiv.org/abs/2608.15502 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a47fb129ffb (Metraipolis archive dc_2a47fb129ffb, sha256 a05871013c20f100d9507b592cb648873c3cab5c8464651add3550ac368b7c69)

BibTeX

@misc{dc2a47fb129ffb,
  title = {EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints — arXiv:2608.15502},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15502},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a47fb129ffb; sha256 a05871013c20f100d9507b592cb648873c3cab5c8464651add3550ac368b7c69},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15502. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action (VLA) models have emerged as a promising foundation for Embodied AI, but their high inference cost poses significant challenges for deployment in robotic systems. In practice, on-device inference is constrained by limited compute capacity and energy budgets, struggling to simultaneously satisfy real-time control and energy efficiency requirements. Alternatively, offloading the inference workload to an edge server is susceptible to fluctuations in system conditions, introducing unpredictable latency risks. Device-edge co-inference offers a promising solution, but systematic research tailored to VLA models remains scarce, particularly a unified co-inference framework that jointly addresses real-time constraints and system-level energy efficiency. Thus, we propose EcoVLA, an adaptive device-edge co-inference framework for VLA models that maximizes system energy efficiency under real-time constraints. EcoVLA first introduces a unified stage-level abstraction over different VLA paradigms, establishing an architecture-agnostic co-inference design space. It then formulates a joint device-edge-network latency and energy prediction model to enable rapid runtime evaluation of candidate co-inference schemes. Building on this, EcoVLA continuously selects the energy-optimal scheme satisfying real-time constraints with millisecond-level overhead, adapting to runtime variations in network and system states. Furthermore, EcoVLA incorporates a lightweight transmission mechanism for inter-stage intermediate tensors to reduce the communication overhead incurred by cross-device collaboration. Experimental results across VLA models show that EcoVLA improves system energy efficiency by up to 236% over existing co-inference approaches under a 20 Hz action output frequency constraint, while consistently maintaining SLO satisfaction under dynamic network and edge workload conditions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.15502 — 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 2026-10-18T16:29:13.806Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).