open-edge-platform / open-edge-platform/model_api

API to cancel pending inference requests

Open
#493 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.