外观
论文arXiv 2607.241483 个月前
一种具有质心复用的运动感知向量量化框架，用于高效 VLA 推理
原文链接：A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference（arXiv 2607.24148 · 发布日期：2026-07-27）
A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference
面向VLA模型GPU推理延迟高的问题，VQVLA以运动感知向量量化和质心复用加速推理，并在实验中验证相对GPU和多种加速器提速。
核心要点
- 动机是VLA模型在GPU上推理延迟高，现有加速器仍按全精度处理，未充分利用冗余。
- MotionVQ根据机器人执行状态动态调整量化精度，以减少内存访问并保持任务成功率。
- 合并质心的向量化GEMM在码本索引表示上运行，通过空间聚合和时间复用消除冗余乘法。
- 实验显示VQVLA相对A100 GPU、Dadu-Corki等方法取得提速，且精度下降可忽略。
英文摘要 (Abstract)
Vision-Language-Action (VLA) models have demonstrated strong potential for embodied AI, yet their high inference latency on GPUs limits real-time deployment. Existing accelerators, such as Dadu-Corki, improve efficiency but treat VLA models as full-precision workloads, leaving substantial redundancy in both memory and computation underexploited. In this paper, we propose VQVLA, an algorithm-hardware co-design framework that accelerates VLA inference by exploiting weight similarity and execution dynamics. We first introduce MotionVQ, a motion-aware vector quantization scheme that dynamically adjusts quantization precision based on the robot's execution state, reducing memory access while preserving task success rate. We then propose a merged-centroid vectorized GEMM paradigm that operates on the codebook-index representation, eliminating redundant multiplications through spatial aggregation and temporal reuse of centroids. To realize these optimizations, we design an accelerator that efficiently supports dynamic precision selection and centroid-reuse computation. Experimental results show that VQVLA achieves 6.5x, 2.8x, 1.9x, 3.3x, and 4.3x speedup over the A100 GPU, Dadu-Corki, LUT-DLA, CodeGEMM, and ShiftAddLLM, respectively, with negligible accuracy degradation.
作者：Zhuoran Song, Haozhe Jiang, Chunyu Qi, Minnan Pei, Gang Li, Xiaoyao Liang, Haibing Guan
来源
本页事实对应的公开页面，以原文为准。