论文arXiv 2611.149699 天前
XInfer系统开源:VLA推理成本降低,机器人有效容量提升3.75倍
本文由 AI 根据公开内容整理,可能有误,请以原文为准:Scaling VLA Serving Under Robotic Execution Constraints(arXiv 2611.14969)
核心内容
针对数百台VLA驱动机器人在真实环境部署面临的推理基础设施成本挑战,研究团队推出生产级服务系统XInfer。该系统已在实际产线部署,旨在解决大规模机器人舰队的高效服务问题。基于生产负载的评测显示,在严格物理执行约束下,XInfer在三款VLA模型上的有效机器人容量(ERC)达到当前最先进系统的1.26至3.75倍,显著降低了单位机器人的算力边际成本。
XInfer核心技术在于联合协调异构VLA计算与机器人动态响应需求。系统利用计算并行性提升GPU利用率,同时建立干扰管理机制以保护时间关键的机器人反馈回路,确保推理延迟满足物理执行安全阈值。该方案平衡了高吞吐推理与实时控制之间的矛盾,验证了在有限硬件资源下支撑大规模具身智能体并发运行的可行性,相关实现代码已在GitHub开源供社区复用。
关键看点
- 有效容量倍增:在生产衍生工作负载下,XInfer使三款VLA模型的有效机器人容量(ERC)达到SOTA系统的1.26-3.75倍
- 异构计算协同:联合调度异构VLA计算任务与机器人执行端的动态响应需求,最大化GPU资源利用率
- 实时干扰管理:在提升推理吞吐的同时主动管理计算干扰,严格保障时间关键的机器人反馈回路稳定性
- 生产级开源:系统已在数百台机器人真实环境中部署验证,完整实现代码于GitHub开源支持复现
工程与产业观察
VLA模型从单机验证迈向百台级舰队部署时,推理服务效率成为制约规模化落地的核心瓶颈。XInfer证明了通过系统层优化而非单纯堆叠算力,可在物理约束下大幅提升有效机器人容量。该成果为具身智能产业化提供了关键的中间件参考,表明软硬协同的推理服务架构是降低大规模部署成本的必经之路。
英文摘要 (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.
作者:Yue Zhang, Zicong Ye, Lufang Chen, Dance Yang, Mingyang Li, Zhenwei Duan, Michael Zhao, Ziye Deng, Starrick Liu, Ruizhi Chengze, YongHua Chen, SongAo Han, Yu Sun, Ran Yu, Xiaofan Li, Ruyi Gan, Hao Wan…
外部来源
本页事实对应的公开页面,以原文为准。(点击将离开本站)