検索ベース投機とハードウェア加速によるVLA推論の高速化
Efficient VLA Inference via Retrieval-Based Speculation and Hardware Acceleration
ロボット動作生成の遅延を削減するため、RAGベースの軽量ドラフトモデルと専用ハードウェアを組み合わせ、VLAモデルの推論を最大7.6倍高速化した研究。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Zhengyang Cheng, He Zhu, Zeyu Guo, Zihan Liu, Anbang Wu, Yiming Gan, Jingwen Leng, Yu Feng, Minyi Guo
分類: cs.AR, cs.RO
原文アブストラクト
Vision-language-action (VLA) models enable robots to understand and execute complex instructions, but their autoregressive (AR) action generation introduces significant latency on resource-constrained robotic platforms. Speculative decoding can accelerate AR-based inference by parallelizing action generation and verification; however, existing approaches rely on costly draft models, which are inefficient on edge platforms. In this paper, we propose Zora, a hardware-software co-design framework for accelerating AR-based VLA inference. Specifically, Zora introduces a lightweight retrieval-augmented generation (RAG)-based draft model that exploits robotic dynamics without additional neural draft models. We further reduce batch verification overhead through a kinematics-guided action-acceptance strategy and a KV-cache-sharing attention mechanism. To address the retrieval overhead introduced by RAG-based drafting, we co-design dedicated hardware support, Zora core, to address the memory irregularity in RAG-based drafting. We evaluate Zora on four VLA models with the LIBERO benchmark. Zora retains comparable accuracy while achieving up to 3.4$\times$ speedup with software-only optimization and up to 7.6$\times$ speedup with hardware support over GPUs.
