在 NVIDIA Jetson AGX Orin 上用 cuDLA 运行原生 DLA Python 推理
Run Native DLA Inference in Python on NVIDIA Jetson AGX Orin Using cuDLA
NVIDIA 发布技术博客，介绍如何在 Jetson AGX Orin 上通过 cuDLA 在 Python 中运行原生 DLA 推理。DLA 是专用于深度学习推理的硬件加速器，可承接支持的神经网络算子，将推理负载从 GPU 卸载，从而提升能效。
AI applications at the edge often need to run multiple neural networks within limited compute and power budgets. NVIDIA Deep Learning Accelerator (DLA)...
AI applications at the edge often need to run multiple neural networks within limited compute and power budgets. NVIDIA Deep Learning Accelerator (DLA) platforms provide dedicated hardware for deep learning inference. On NVIDIA Jetson AGX Orin, DLA executes supported neural network operations, allowing applications to offload inference work from the GPU. This can improve power efficiency and leave…
来源：NVIDIA Technical Blog · developer.nvidia.com