apache / apache/beam

[Feature Request]: Add optional thread safety to RunInference

Open
#23,853 0 comments 0 reactions 0 assignees View on GitHub
ml new feature P2 python run-inference
Dominant language
Java
Stars
8.7k
Forks
4.7k
Avg merge
1d 20h
Merged PRs (30d)
196

Description

### What would you like to happen?

There may be models which are not thread safe and will run into issues using RunInference (which relies on shared.py under the covers). We should add the ability to force type safety via locking when performing inference.

### Issue Priority

Priority: 2

### Issue Component

Component: run-inference

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.