mlcommons / mlcommons/inference

loadgen 3.0 py_demo_offline.py Segmentation Fault

Open
#1,337 4 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

Hi Pals,

I have built the mlperf-loadgen v3.0 module and installed it in python 3.9.15.
I executed the py_demo_offline.py example, which ran into a segmentation fault.
All the other demo.py (py_demo_single_stream.py, py_demo_multi_stream.py, py_demo_server.py) work perfectly.

Is there any solution?

Sincerely,
Kevin

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 reproducing the segmentation fault with py_demo_offline.py using Python 3.9.15 and the MLPerf LoadGen v3.0 build, then compare its behavior with py_demo_single_stream.py, py_demo_multi_stream.py, and py_demo_server.py. Done means identifying and resolving the offline-demo crash while keeping the other demos working.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.