How Far Are We From On-Device VLM Inference? A Measurement Study on Edge NPUs

Abstract

Diverse optimizations spanning model architecture, inference runtime, and hardware acceleration have been proposed for on-device vision-language model (VLM) deployment on edge NPUs. Still, cross-layer coordination of VLM execution on edge NPUs remains largely underexplored. This paper presents an empirical measurement study across six representative VLMs, three real-world edge platforms, and ten multimodal benchmarks. Our evaluation drills down from end-to-end application-level latency and thermal traces down to low-level kernel-scale execution behaviors, challenging several widely held community assumptions. First, softmax dominates attention costs; even lookup-table-based softmax optimizations cannot eliminate pipeline bubbles that severely underutilize NPU matrix units. Second, theoretical speedups from linear attention vanish under real-NPU execution due to prohibitive tensor-rearrangement overhead. Third, no hardware backend universally dominates autoregressive decoding: attention-tensor-shaped parallelism dictates NPU efficiency and shifts the CPU-NPU performance balance. We further find task-specific Sweet Resolutions for VLMs, which deliver meaningful accuracy gains at only modest latency overhead. Complementing these findings, we provide actionable cross-layer recommendations for hardware architects, runtime developers, and model designers.