Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment

arXiv:2604.24447v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are promising for generalist robot control, but on-robot deployment is bottlenecked by real-time inference under tight cost and energy budgets. Most prior evaluations rely on desktop-grade GPUs, obscuring the trade-offs and opportunities offered by heterogeneous edge accelerators (GPUs/XPUs/NPUs). We present a systematic analysis for low-cost VLA deployment via model-hardware co-characterization. First, we build a cross-accelerator leaderboard and evaluate model-hardware pairs under CET (Cost, Energy, Time), showing that right-sized edge devices can be more cost-/energy-efficient than flagship GPUs while meeting control-rate constraints. Second, using in-depth profiling, we uncover a consistent two-phase inference pattern: a compute-bound VLM backbone followed by a memory-bound Action Expert, which induces phase-dependent underutilization and hardware inefficiency. Finally, guided by these insights, we propose DP-Cache and V-AEFusion to reduce diffusion redundancy and enable asynchronous pipeline parallelism, achieving up to 2.9x speedup on GPUs and 6x on edge NPUs with only marginal success degradation. The example leaderboard website is available at: https://vla-leaderboard-01.vercel.app/.

Related

• TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative Connection
• CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception
• IntentVLM: Open-Vocabulary Intention Recognition through Forward-Inverse Modeling with Video-Language Models
• KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models

Source: arXiv cs.AI | 2026-04-28