open-edge-platform / open-edge-platform/model_api
Re-upload models to HF with a dynamic batch size
Open
@warrkan is already working on this.
Since Sep 1, 2026.
- Dominant language
- Python
- Stars
- 71
- Forks
- 22
- Avg merge
- 1d 2h
- Merged PRs (30d)
- 4
Description
The Geti models uploaded to https://huggingface.co/OpenVINO were all exported with a static batch size of 1, for example YOLOX-Tiny. In practice, clients cannot use these models for batch inference, an issue that's also discussed in ITEP-94275.
In scope of this ticket:
- Fix the model converter to export models with a dynamic batch size instead of 1. For reference, see how a similar issue was fixed in Geti: https://github.com/open-edge-platform/geti/pull/7076
- Re-export and upload all models to Huggingface
- Reply to the original issue once the bug has been resolved
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.
Assessment
This issue has not been assessed yet.