# 超越 LLM Serving：面向具身 AI 系统设计的 Vision-Language-Action 工作负载表征

> 原文链接：https://robotics.hellobike.com/papers/2026-10-04-2610-05062
> 频道：papers | 更新日期：2026-10-04 | 标签：arxiv, cs.RO
> 核心摘要：本文针对VLA控制周期推理期限问题，通过批1性能剖析和闭环实验，在边缘GPU服务器与机载SoC上表征工作负载。

# 超越 LLM Serving：面向具身 AI 系统设计的 Vision-Language-Action 工作负载表征

::: v-pre
> 原文链接：[Beyond LLM Serving: Characterizing Vision-Language-Action Workloads for Embodied AI System Design](https://arxiv.org/abs/2610.05062)（arXiv 2610.05062 · 发布日期：2026-10-04）

**Beyond LLM Serving: Characterizing Vision-Language-Action Workloads for Embodied AI System Design**

本文针对VLA控制周期推理期限问题，通过批1性能剖析和闭环实验，在边缘GPU服务器与机载SoC上表征工作负载。

## 核心要点

- VLA若推理超期会让机器人基于陈旧观测行动，降低任务成功率。
- 研究聚焦单机器人批1控制场景，分析多类VLA组件的运行行为。
- 实验表明动作张量维度、平台均衡与GPU频率会影响瓶颈和能耗-时延折中点。
- 闭环中推理与动作执行重叠带来精度、速度、能耗权衡，配置无统一Pareto最优。

**验证范围与局限**：验证范围为四个代表性VLA模型，在一台边缘GPU服务器和两个机载SoC上的单次推理剖析及43,200个闭环回合。

## 英文摘要 (Abstract)

Vision-language-action (VLA) models translate multimodal observations into low-level robot actions. During robot operation, each control period sets an inference deadline, and overruns leave the robot acting on stale observations, reducing task success. Meeting this deadline motivates on-device or nearby edge execution, where a single robot requires batch-1 inference outside the design point of LLM serving systems. Although VLA architectures combine familiar vision-language, autoregressive, and diffusion-style components, their runtime behavior in this batch-1 control setting remains uncharacterized. We characterize four representative VLA models on an edge GPU server and two onboard SoCs, using single-inference profiling and 43,200 closed-loop episodes. Action tensor dimensionality determines whether a stage is memory- or compute-bound, platform balance can shift that bottleneck, and GPU frequency scaling yields a platform-dependent energy-latency sweet spot. In closed-loop operation, overlapping inference with action execution creates an accuracy-speed-energy tradeoff, and no configuration is Pareto-dominant across deployment SLOs. These results guide joint design of VLA model architectures, hardware, and runtime policies.

作者：SeongHun Jung, Sieun Moon, Jiyoung Jeong, Jimin Lee, Jaehyuk Huh
:::

## 原始参考来源 (Sources)

- [arXiv 2610.05062：Beyond LLM Serving: Characterizing Vision-Language-Action Workloads for Embodied AI System Design](https://arxiv.org/abs/2610.05062)