In this paper, we show how to run pi0-level multi-view VLA at 30Hz frame rate and at most 480Hz trajectory frequency using a single consumer GPU. This enables dynamic and real-time tasks that were previously believed to be unattainable by large VLA models. To achieve it, we introduce a bag of strategies to eliminate the overheads in model inference. The real-world experiment shows that the pi0 policy with our strategy achieves a 100% success rate in grasping a falling pen task. Based on the results, we further propose a full streaming inference framework for real-time robot control of VLA. Code is available at https://github.com/Dexmal/realtime-vla.
Cite
@article{arxiv.2510.26742,
title = {Running VLAs at Real-time Speed},
author = {Yunchao Ma and Yizhuang Zhou and Yunhuan Yang and Tiancai Wang and Haoqiang Fan},
journal= {arXiv preprint arXiv:2510.26742},
year = {2025}
}
Comments
Code is available at https://github.com/Dexmal/realtime-vla