mlcommons / mlcommons/inference

[Multimodal][vl2l] Offline Scenario hangs at the end of the benchmark

Open
#2,389 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

The command:
mlperf-inf-mm-vl2l --settings.scenario offline --settings.mode performance_only
might hang if the expected qps is too high.

You can try:
mlperf-inf-mm-vl2l --settings.scenario offline --settings.mode performance_only --settings.offline_expected_qps 10
and check if you can reproduce.

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 running mlperf-inf-mm-vl2l --settings.scenario offline --settings.mode performance_only, then compare it with the same command using --settings.offline_expected_qps 10. Trace the offline benchmark entry point to determine why a high expected QPS can hang at completion; done means the benchmark exits normally instead of hanging.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.