microsoft / microsoft/winml-cli
feat: add built-in model support for YOLO
Open
Nobody has claimed this yet.
model / task scale
P2
triaged
- Dominant language
- Python
- Stars
- 40
- Forks
- 11
- Avg merge
- 1d 8h
- Merged PRs (30d)
- 50
Description
Summary
Add YOLO as a built-in model with ONNX export support and verified build config.
Tasks
- Add model config and any required ONNX export patches
- Verify
wmk config+wmk buildend-to-end - Verify analyzer autoconf discovers correct fusion flags
- Add integration test
Model
- HuggingFace:
Ultralytics/YOLO26 - Task: object-detection
🤖 Generated with Claude Code
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 existing built-in model configurations, ONNX export handling, the wmk config and wmk build entry points, and analyzer autoconf logic. Verify how the YOLO26 object-detection model is represented and run the end-to-end configuration and build flow. Done means the build succeeds with the expected fusion flags and an integration test covers the model.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- huggingface, python
- Domain
- build-system, cli, machine-learning, testing
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100