---
format: "aidr-story-markdown/v1"
id: "e65e42f824f14c2b8ea397dea90b6ebd4cd2593a34ae92e5e046bfb991ef14c1"
canonical_url: "https://aidr.today/e65e42f8?lang=en"
title: "Run Native DLA Inference in Python on NVIDIA Jetson AGX Orin Using cuDLA"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-13T18:57:10.000Z"
category: "Frameworks"
topics: ["nvidia","inference","framework"]
source_urls: ["https://developer.nvidia.com/blog/run-native-dla-inference-in-python-on-nvidia-jetson-agx-orin-using-cudla/"]
summary: "NVIDIA cuDLA is the runtime API for managing execution on the NVIDIA Jetson AGX Orin DLA. The cuda.bindings.cudla module exposes these APIs directly to Python. Developers can integrate DLA execution into applications without writing C++ code. An image classification example shows how GPU and DLA stages work together in a single Python application."
---

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

> [Open the canonical story](<https://aidr.today/e65e42f8?lang=en>)

**Published:** 2026-11-13T18:57:10.000Z
**Category:** Frameworks
**Topics:** nvidia, inference, framework

## Summary

NVIDIA cuDLA is the runtime API for managing execution on the NVIDIA Jetson AGX Orin DLA\. The cuda\.bindings\.cudla module exposes these APIs directly to Python\. Developers can integrate DLA execution into applications without writing C\+\+ code\. An image classification example shows how GPU and DLA stages work together in a single Python application\.

## Sources

- [Story source](<https://developer.nvidia.com/blog/run-native-dla-inference-in-python-on-nvidia-jetson-agx-orin-using-cudla/>)