microsoft / microsoft/onnxruntime
[Documentation] Use WebGPUExecutionProvider from python (or other non-web platform)
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 21.9k
- Forks
- 4.2k
- Avg merge
- 4d 11h
- Merged PRs (30d)
- 184
Description
### Describe the documentation issue
I've tried searching the documentation for instructions on how to use the `WebGPUExecutionProvider` from python, but no results seem to show up.
```py
>>> import onnxruntime
>>> onnxruntime.version
'1.23.1'
>>> onnxruntime.get_available_providers()
['CoreMLExecutionProvider', 'AzureExecutionProvider', 'CPUExecutionProvider']
```
OS: macOS 15.6
It would be very useful to show how to use the WebGPU EP outside of web-specific platforms. Is it necessary to install `onnxruntime-gpu` too?
### Page / URL
https://onnxruntime.ai/docs/execution-providers/
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start at the execution providers documentation page and review the Python example and provider-installation guidance described in the issue. Document how to use WebGPUExecutionProvider from Python or another non-web platform, including whether onnxruntime-gpu is required. Done means the page answers the installation question and provides a usable example.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 52/100