Characterizing VLA Models: Identifying the Action Generation Bottleneck for Edge AI Architectures
This addresses performance bottlenecks for deploying real-time embodied AI on edge devices, though it is incremental as it focuses on characterization and projections.
The paper characterized Vision-Language-Action (VLA) models on edge hardware, identifying that up to 75% of latency comes from the memory-bound action-generation phase, and projected hardware needs for scaling to 100B parameters.
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.