open-edge-platform / open-edge-platform/model_api
API to cancel pending inference requests
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 71
- Forks
- 22
- Avg merge
- 1d 2h
- Merged PRs (30d)
- 4
Description
OpenVINO async API provides a cancel method to abort running inference requests. This method gives more control to the user over the pending requests, allowing for example to cancel requests that are taking too long.
As far as I know, Model API doesn't expose a similar method. It would be nice if it could be added to Model and AsyncPipeline.
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 tracing the Model and AsyncPipeline entry points and compare their pending-request handling with OpenVINO's asynchronous cancel method. Define how cancellation should behave for each API, then verify that pending inference requests can be aborted through both Model and AsyncPipeline without leaving inconsistent state.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- api, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100