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

<img width="768" height="432" src="https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-768x432.jpg" class="webfeedsFeaturedVisual wp-post-image" alt="" style="display: block; margin-bottom: 5px; clear:both;max-width: 100%;" link_thumbnail="" decoding="async" srcset="https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-768x432.jpg 768w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-179x101.jpg 179w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-300x169.jpg 300w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-625x352.jpg 625w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-1536x864.jpg 1536w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-645x363.jpg 645w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-660x370.jpg 660w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-500x281.jpg 500w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-160x90.jpg 160w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-362x204.jpg 362w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-196x110.jpg 196w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-1024x576.jpg 1024w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-960x540.jpg 960w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference.webp 1920w" sizes="(max-width: 768px) 100vw, 768px" title="dla-inference" />AI applications at the edge often need to run multiple neural networks within limited compute and power budgets. NVIDIA Deep Learning Accelerator (DLA)...<img width="768" height="432" src="https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-768x432.jpg" class="webfeedsFeaturedVisual wp-post-image" alt="" style="display: block; margin-bottom: 5px; clear:both;max-width: 100%;" link_thumbnail="" decoding="async" loading="lazy" srcset="https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-768x432.jpg 768w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-179x101.jpg 179w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-300x169.jpg 300w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-625x352.jpg 625w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-1536x864.jpg 1536w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-645x363.jpg 645w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-660x370.jpg 660w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-500x281.jpg 500w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-160x90.jpg 160w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-362x204.jpg 362w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-196x110.jpg 196w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-1024x576.jpg 1024w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference-960x540.jpg 960w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/dla-inference.webp 1920w" sizes="auto, (max-width: 768px) 100vw, 768px" title="dla-inference" /><p>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…</p> <p><a href="https://developer.nvidia.com/blog/run-native-dla-inference-in-python-on-nvidia-jetson-agx-orin-using-cudla/" rel="nofollow" data-wpel-link="internal" target="_self">Source</a></p>