Unstructured-IO / Unstructured-IO/unstructured-inference

Add support to Rocm (AMD) onnx provider

Open
#345 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
209
Forks
73
PR merge metrics
No merged PRs in 30d

Description

Hi, in models/yolox.py and detectron2onnx.py, we can add support to AMD GPUs by modifying ordered_providers list to

ordered_providers = [
    "ROCMExecutionProvider",
    "TensorrtExecutionProvider",
    "CUDAExecutionProvider"
]

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with models/yolox.py around the ordered_providers list and then inspect detectron2onnx.py for the corresponding provider configuration. Confirm how the existing provider order is used, add ROCMExecutionProvider support in both locations, and verify that the current CUDA and TensorRT providers remain represented.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Clearly specified
Newbie friendliness
52/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.