在 NVIDIA Jetson AGX Orin 上使用 cuDLA 通过 Python 运行原生 DLA 推理
Run Native DLA Inference in Python on NVIDIA Jetson AGX Orin Using cuDLA
NVIDIA Jetson AGX Orin 通过 cuDLA 可在 Python 中运行原生 DLA 推理，支持在 DLA 硬件上执行特定神经网络操作以卸载 GPU 推理任务，提升边缘端应用的能效。
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