microsoft / microsoft/winml-cli
feat: support thin dependencies for WinMLPreTrainedModel?
Open
Nobody has claimed this yet.
enhancement
P2
triaged
- Dominant language
- Python
- Stars
- 40
- Forks
- 11
- Avg merge
- 1d 8h
- Merged PRs (30d)
- 50
Description
We have WinMLPreTrainedModel to run onnx file directly. If another app wants to leverage it to run on onnx (i.e. migrate from pytorch), it may only need dependencies for running but not building.
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 by locating WinMLPreTrainedModel and the packaging or dependency configuration used to run ONNX files. Determine which dependencies are required at runtime versus for building, then confirm the expected installation path for an app migrating from PyTorch. Done means the model can run with only the thin runtime dependency set, with the existing build workflow preserved.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 45/100