wcandillon / wcandillon/react-native-webgpu
Is it possible to run onnx models on `react-native-webgpu`?
Open
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 1.2k
- Forks
- 70
- Avg merge
- 1d 6h
- Merged PRs (30d)
- 23
Description
Hi,
I run onnx models in my app but they run on the CPU so most are quite slow. Is there a easy way to offload these to run on the GPU using this lib?
Contributor guide
No contributing guide indexed for this repository
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 by reviewing the react-native-webgpu APIs described by the repository and the issue's ONNX model use case. Determine whether the library exposes a supported path for GPU-backed ONNX execution; done means a documented working approach or a clear statement that it is not supported.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- react-native, typescript
- Domain
- machine-learning, mobile
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100