轻量级推理框架让视觉语言动作模型在低算力设备上更快响应
BLURR: A Boosted Low-Resource Inference for Vision-Language-Action Models
- 通过指令前缀缓存与单步滚动调度降低每步计算开销
- 在相同任务成功率下，有效浮点运算量减少60%以上，延迟显著降低
- 无需重训练即可部署，适合网页交互与机器人实时控制场景
视觉-语言-动作（VLA）模型虽能实现出色的零样本操作能力，但其推理计算开销大，难以在消费级GPU上用于高频率机器人控制或实时网页演示。本文提出BLURR，一种无需重训练、不修改模型权重的轻量级推理封装。基于pi-zero VLA控制器，在SimplerEnv评测中，BLURR保持原始任务成功率的同时，通过指令前缀键值缓存、混合精度执行和单步滚动调度，显著降低有效浮点运算量（FLOPs）与实际运行时延。我们还构建了交互式网页演示，支持实时切换控制器与开关推理选项，直观展示不同配置下的操作效果。结果表明，BLURR是资源受限环境下部署现代VLA策略的实用方案。
原文摘要 · Abstract (English)
Vision-language-action (VLA) models enable impressive zero shot manipulation, but their inference stacks are often too heavy for responsive web demos or high frequency robot control on commodity GPUs. We present BLURR, a lightweight inference wrapper that can be plugged into existing VLA controllers without retraining or changing model checkpoints. Instantiated on the pi-zero VLA controller, BLURR keeps the original observation interfaces and accelerates control by combining an instruction prefix key value cache, mixed precision execution, and a single step rollout schedule that reduces per step computation. In our SimplerEnv based evaluation, BLURR maintains task success rates comparable to the original controller while significantly lowering effective FLOPs and wall clock latency. We also build an interactive web demo that allows users to switch between controllers and toggle inference options in real time while watching manipulation episodes. This highlights BLURR as a practical approach for deploying modern VLA policies under tight compute budgets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。