mlcommons / mlcommons/modelbench

automatic evalutator spin-up and spin-down CLI

Open
#866 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
134
Forks
36
Avg merge
1d 11h
Merged PRs (30d)
17

Description

smart proxy receives eval requests, decides which evals to turn on (gcp, together, etc)

all eval requests go through the proxy

if the proxy fails to get a response, restart the evaluator

maybe web UI to see what the proxy and evaluator are up to at any given time

turn the eval machines off at the end of a run or when they're not used

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

No files, tests, or entry points are named. Start by mapping how evaluation requests reach the smart proxy and how evaluator machines are started and stopped. Clarify the restart conditions, idle shutdown behavior, and whether the web UI is in scope; done should include reliable lifecycle handling and an agreed way to observe proxy and evaluator status.

Written by the indexing model from the issue text.

Assessment

Tech stack
gcp, python
Domain
backend, cli, cloud
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.