A-IO: Adaptive Inference Orchestration for Memory-Bound NPUs

arXiv:2604.09752v2 Announce Type: replace-cross Abstract: During the deployment of Large Language Models (LLMs), the autoregressive decoding phase on heterogeneous NPU platforms (e.g., Ascend 910B) faces severe memory-bound challenges. This study reveals the ``Model Scaling Paradox'' caused by the...