[Feature Request]: More granular treatment of failed inferences
Open
ml
new feature
P2
python
run-inference
- Dominant language
- Java
- Stars
- 8.7k
- Forks
- 4.7k
- Avg merge
- 2d 2h
- Merged PRs (30d)
- 205
Description
### What would you like to happen?
When a batch of inferences fails, we would ideally like to be informed which record caused the failure so that it can be investigated directly.
### Issue Priority
Priority: 2
### Issue Component
Component: run-inference
Contributor guide
Research direction
The issue identifies only the run-inference component and does not name files, tests, or an entry point. Start by locating that component and tracing how batch inference failures are reported; done should include identifying which record caused a failure and covering that behavior with appropriate tests.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100