mlcommons / mlcommons/inference
loadgen 3.0 py_demo_offline.py Segmentation Fault
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
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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