mlcommons / mlcommons/inference

Loadgen needs to be updated to help support and enforce the no-sorting outside of the dataset rules for LLMs

Open
#2,172 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

postmortem 5.0
Dominant language
Python
Stars
1.6k
Forks
650
Avg merge
1d 22h
Merged PRs (30d)
6

Description

Options

  • Send the size of the original dataset to the SUT
  • Verification of the order that queries were responded by loadgen. Potentially introduce a new test for this.
  • Handle it in loadgen next

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

Review the loadgen implementation and any existing LLM query-order tests. Use the checklist as the starting scope: determine how the original dataset size reaches the SUT, how response order can be verified, and what remaining loadgen handling is required. Done means the no-sorting-outside-the-dataset rules are supported and enforced.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, tooling
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.