mlcommons / mlcommons/endpoints

[Feature]: Inline accuracy check of performance runs

Open
#313 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

status: needs-triage type: feature
Dominant language
Python
Stars
21
Forks
28
Avg merge
3d 17h
Merged PRs (30d)
13

Description

Motivation

Multi-turn benchmarking benefits from inline accuracy check of performance run outputs.

Proposed Solution
  1. Allow collecting outputs during performance run for multi-turn datasets (or in general)
  2. Add accuracy tests for performance run outputs.
Alternatives Considered

No response

Additional Context

No response

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 locating the performance-run implementation and the multi-turn dataset handling described in the proposal. Trace how run outputs are currently processed, then identify the existing accuracy-test entry points; done means outputs can be collected during performance runs and accuracy checks cover those outputs.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
performance, testing
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
52/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.