VLAモデルの特性解析:エッジAIアーキテクチャにおける行動生成ボトルネックの特定
Characterizing VLA Models: Identifying the Action Generation Bottleneck for Edge AI Architectures
エッジハードウェア上でVLAモデルの性能を評価し、メモリ帯域がボトルネックとなる行動生成フェーズを特定。将来の大規模モデルへの拡張に必要なハードウェア要件を予測した。
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: Manoj Vishwanathan, Suvinay Subramanian, Anand Raghunathan
分類: cs.PF, cs.AI, cs.AR, cs.RO
原文アブストラクト
Vision-Language-Action (VLA) models are an emerging class of workloads critical for robotics and embodied AI at the edge. As these models scale, they demonstrate significant capability gains, yet they must be deployed locally to meet the strict latency requirements of real-time applications. This paper characterizes VLA performance on two generations of edge hardware, viz. the Nvidia Jetson Orin and Thor platforms. Using MolmoAct-7B, a state-of-the-art VLA model, we identify a primary execution bottleneck: up to 75% of end-to-end latency is consumed by the memory-bound action-generation phase. Through analytical modeling and simulations, we project the hardware requirements for scaling to 100B parameter models. We also explore the impact of high-bandwidth memory technologies and processing-in-memory (PIM) as promising future pathways in edge systems for embodied AI.
