cs.RONov 11, 2026

Scaling VLA Serving Under Robotic Execution Constraints

Authors: Yue Zhang, Zicong Ye, Lufang Chen, Dance Yang, Mingyang Li, Zhenwei Duan, Michael Zhao, Ziye Deng, 

Abstract

Vision-language-action (VLA) models have emerged as a promising paradigm for general-purpose robotic manipulation. In our production setting, hundreds of VLA-powered robots are already operating in real-world environments, creating an immediate need for efficient fleet serving. We present XInfer, a production-deployed VLA serving system designed to reduce the inference infrastructure cost of large-scale robotic deployments. XInfer jointly coordinates heterogeneous VLA computation with the evolving response requirements of robotic execution. By exploiting computational parallelism while managing interference, XInfer improves GPU efficiency while protecting time-critical robotic feedback. We evaluate XInfer across three VLA models using production-derived workloads, achieving 1.26-3.75 times the effective robot capacity (ERC) of state-of-the-art systems under physical-execution constraints. Our implementation is publicly available at https://github.com/X-Square-Robot/xinfer.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Efficient Vision-Language-Action Management and Serving for Robot Factories

    Sep 10, 2026Dionysios Adamopoulos, Nattapol Chanpaisit, Basel Fakhri +1Edge ComputingEfficient VLA Inference

  2. vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models

    Jun 6, 2026Khanh D. Nguyen, Hung T. Ho, Chinh T. Nguyen +5AI Accelerator InferenceEfficient VLM Inference