Johnny Núñez Cano

Johnny Núñez Cano

AI Developer Advocate at NVIDIA — Physical AI, Robotics & Edge Computing. Applied Research & Solutions Architect. Championing open-source models, frameworks, and hardware. CVPR 2026 Tutorial Co-organizer. PhD in Computer Vision.

Jetson Containers — 30+ AI Libraries Ported to Edge

Published:

Core contributor to dusty-nv/jetson-containers — the official collection of Machine Learning containers for NVIDIA Jetson and JetPack-L4T.

Contributions

Ported over 30 AI libraries and frameworks to Jetson’s aarch64 architecture, including:

  • Inference engines — TensorRT-LLM, vLLM, SGLang, FlashInfer
  • ML frameworks — PyTorch, TensorFlow, ONNX Runtime, JAX
  • Computer vision — OpenCV, Detectron2, YOLO variants
  • Robotics — ROS/ROS 2, Isaac ROS, MoveIt2
  • Generative AI — Stable Diffusion, Cosmos, LLM serving stacks

Impact

These containers enable thousands of developers worldwide to run state-of-the-art AI models on edge devices without fighting dependency and build issues. The project is a cornerstone of the NVIDIA Jetson developer ecosystem.