TensorFlow 2.21 GPU wheel for JetPack 7.2 / Jetson Orin

Robotics & Edge Computing Jetson Systems Jetson AGX Orin
, ,
1

I built and tested a prebuilt TensorFlow 2.21.0 GPU wheel for Jetson Orin
running JetPack 7.2.

Repository:

Supported environment:

  • Jetson AGX Orin, Orin NX, Orin Nano
  • JetPack 7.2
  • Ubuntu 24.04
  • Python 3.12
  • aarch64
  • CUDA GPU support
  • sm_87

Install:

pip install https://github.com/RitishKam/tensorflow-jetson-jp7/releases/download/v2.21.0-jp7.2/tensorflow_jetson_jp7-2.21.0+jp7.2.cu12-cp312-cp312-manylinux_2_27_aarch64.whl

The build currently passes 30/30 GPU tests, including:

  • cuBLAS
  • cuDNN
  • XLA
  • Keras training
  • mixed precision
  • SavedModel
  • TFLite conversion

The goal is to make GPU-enabled TensorFlow easier to install on JetPack 7,
without manual LD_LIBRARY_PATH configuration.

I would especially appreciate testing reports from Orin NX and Orin Nano users.

2

Hello @idz208564!

Based on the title and content of your topic, it looks like it may receive better visibility and feedback in a different category. We took the liberty of moving it for you.

If this was an incorrect assessment, please send me a direct message.

Disclaimer: this moderation suggestion and message were generated with AI assistance.