Metraipolis › archive › dc_dfd0648c7963

Efficient Vision-Language-Action Management and Serving for Robot Factories — arXiv:2609.12075

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.12075
License (as archived): CC0-1.0
Archived: 2026-10-16T03:08:33.138Z
SHA-256 of the archived text: 75de6d61039ce7b6d3243e45f30e67c79f5ccdd8c44399607c4be5fa5e98da59
Stable URL of this page: https://metraipolis.com/documento/dc_dfd0648c7963

How to cite

Efficient Vision-Language-Action Management and Serving for Robot Factories — arXiv:2609.12075 — arXiv (en), https://arxiv.org/abs/2609.12075 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dfd0648c7963 (Metraipolis archive dc_dfd0648c7963, sha256 75de6d61039ce7b6d3243e45f30e67c79f5ccdd8c44399607c4be5fa5e98da59)

BibTeX

@misc{dcdfd0648c7963,
  title = {Efficient Vision-Language-Action Management and Serving for Robot Factories — arXiv:2609.12075},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12075},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dfd0648c7963; sha256 75de6d61039ce7b6d3243e45f30e67c79f5ccdd8c44399607c4be5fa5e98da59},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12075. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action (VLA) models show high robotic manipulation capabilities via a two-stage design: a Vision-Language Model (VLM) stage followed by an Action Diffusion Transformer (ADiT) stage. Since robots must meet strict Service-Level Objectives (SLOs) for safety, VLA inference is inherently latency-critical. Meeting these SLOs requires high-end GPUs, yet weight, cost, and power constraints preclude integrating such GPUs on-robot. Prior works offload VLA inference to edge servers that serve many robots on VLA models. However, current VLA systems lack support for multi-request, multi-model execution on a multi-GPU server under SLOs, while existing serving systems for multi-stage models are optimized for throughput and stage disaggregation across separate GPUs, which are ill-suited for the millisecond-scale stages of VLA models. We design Robion, the first VLA serving and management system for multi-robot, multi-model requests on multi-GPU edge servers that meets SLOs. Our serving engine disaggregates the VLM and ADiT stages within a GPU via two streams, dynamically restricting the SMs on VLM stream so ADiT always finds SMs to run alongside it, and co-locates multiple models by sharing these streams across them, prioritizing requests by least remaining SLO time. Our management engine enables flexible model placements on multi-GPU servers, and integrates an intelligent traffic controller that maximizes per-model batching under the chosen placement while bounding each GPU's load to meet SLOs. For individual models, Robion serves on average 6.7$\times$ and 1.5$\times$ higher robot load within 98% SLO attainment over vLLM-Omni, the most widely used multi-stage serving system, and Monolithic, which runs VLM and ADiT as a single pipeline, respectively. In a large-scale experiment of serving 8 different models on a 4-GPU server, Robion can serve up to 64 robots within 98% SLO attainment.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-14 in cs.DC).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Hardware Architecture (cs.AR); Machine Learning (cs.LG); Performance (cs.PF); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.12075 — 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 2026-10-16T03:03:05.072Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).