PyTorch AttributeError: module 'torch.distributed' has no attribute 'is_initialized' error

Robotics & Edge Computing Jetson Systems Jetson AGX Orin
1

I have a Jetson AGX Orin flashed with newest Jetpack 6.2 and I’m trying to run embedding models (Qwen3-Embedding) using SentenceTransformers library.

I’m using python 3.10 and I have installed this version of PyTorch and I’m using SentenceTransformers lib version 5.0.0 and I’m getting this error:

AttributeError: module 'torch.distributed' has no attribute 'is_initialized'

Do anyone know how to overcome this?

2

*** Please note that this reply is generated by LLM automatically ***

Based on the provided context, I’ll try to provide a comprehensive answer to the question.

The question is about running embedding models (Qwen3Embedding) using the SentenceTransformers library on a Jetson AGX Orin device flashed with the latest Jetpack 6.2. The user is experiencing an error and is seeking help to overcome it.

Firstly, let’s break down the components involved:

  1. Jetson AGX Orin: A high-performance AI computing platform from NVIDIA.
  2. Jetpack 6.2: The latest software development kit (SDK) for NVIDIA Jetson devices, which includes the operating system, libraries, and tools for developing AI applications.
  3. Python 3.10: The version of Python being used on the Jetson AGX Orin device.
  4. PyTorch: A popular open-source machine learning library, which has been installed on the device.
  5. SentenceTransformers: A library for sentence embeddings, which is being used to run the Qwen3Embedding model.

Given the error message is not provided, I’ll offer some general troubleshooting steps and potential solutions:

  1. Check the compatibility of SentenceTransformers with PyTorch: Ensure that the version of SentenceTransformers (0.5.0) is compatible with the version of PyTorch installed on the device.
  2. Verify the installation of PyTorch: Double-check that PyTorch has been installed correctly on the device, and that the correct version is being used.
  3. Check the model compatibility: Verify that the Qwen3Embedding model is compatible with the SentenceTransformers library and the PyTorch version being used.
  4. Update the SentenceTransformers library: If the library is outdated, try updating it to the latest version to see if the issue is resolved.
  5. Check the device’s resources: Ensure that the device has sufficient resources (e.g., memory, compute power) to run the model.
  6. Consult the documentation and community forums: Check the official documentation and community forums for SentenceTransformers, PyTorch, and Jetson AGX Orin to see if similar issues have been reported and resolved.

In comparison to other components mentioned in the context, the issue seems to be specific to the combination of SentenceTransformers, PyTorch, and the Jetson AGX Orin device. The other components, such as the mttcan driver, USB CAN interface, and MCP2515 with Orin Nano, do not appear to be directly related to the issue at hand.

If the user provides more details about the error message, I can offer more specific guidance and potential solutions.

*** Please give the thumbs up if you get answers you like. Or provide feedback to help us improve the answer. ***

4

Hi,

Please try the package installed at the link below instead:

Thanks

5

That worked like a charm!!! Thank you!!!