mlcommons / mlcommons/modelbench
Improve external resource provisioning
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 134
- Forks
- 36
- Avg merge
- 1d 11h
- Merged PRs (30d)
- 17
Description
The startup process with dedicated endpoints, both internal and vendor, is chaotic. Let's look at making that a first-class platform feature, so that each SUT/annotator can signal that it's ready to run, and that things using them wait until they're ready.
(same idea as modeltune 223, except for third-party vendors)
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 reviewing the issue's description of startup sequencing for dedicated internal and vendor endpoints, then compare the referenced modeltune 223 discussion. The issue names no files or tests; done would require an agreed first-class readiness and waiting design for SUTs, annotators, and their dependents.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- backend, infrastructure
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100