AI RESEARCH
When NPUs Are Not Always Faster: A Stage-Level Analysis of Mobile LLM Inference
arXiv CS.AI
•
ArXi:2605.27435v1 Announce Type: cross Deploying large language models (LLMs) on mobile devices increasingly relies on heterogeneous execution, yet no prior study has systematically characterized NPU effectiveness at the operator and pipeline level. We present the first stage-aware, multi-level benchmarking study of mobile LLM inference on a CPU-NPU heterogeneous SoC. We