使用 cuDLA 在 NVIDIA Jetson AGX Orin 上以 Python 執行原生 DLA 推理
Run Native DLA Inference in Python on NVIDIA Jetson AGX Orin Using cuDLA
NVIDIA 介紹如何使用 cuDLA 在 NVIDIA Jetson AGX Orin 上以 Python 執行原生 DLA 推理。Jetson AGX Orin 的 DLA 可執行支援的神經網絡運算,讓應用程式將部分推理工作從 GPU 卸載至專用硬件。
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…
來源:NVIDIA Technical Blog:Agentic AI / Generative AI · developer.nvidia.com