mlcommons / mlcommons/inference
Is that a bug in DLRM V2 model?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.6k
- Forks
- 650
- Avg merge
- 1d 22h
- Merged PRs (30d)
- 6
Description
It looks like something is wrong in the model weights/.snapshot_metadata directory. All files are missing. There is an error message related to this. Python3.10 and Python3.11 both are tested. There is no error message during downloading.
FileNotFoundError: [Errno 2] No such file or directory: '/home/smci/MLC/repos/local/cache/download-file_ml-model-dlrm-t_bd6fcecb/model_weights/.snapshot_metadata'
Here is the run command.
mlcr run-mlperf,inference,_find-performance,_full,_r5.1
--model=dlrm-v2-99
--implementation=reference
--framework=pytorch
--category=datacenter
--scenario=Offline
--execution_mode=test
--device=cpu
--quiet
--test_query_count=10 --rerun
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 mlcr run-mlperf,inference,_find-performance,_full,_r5.1 command for dlrm-v2-99 and inspect the model cache path shown in the FileNotFoundError. Trace how the download creates model_weights/.snapshot_metadata and compare the downloaded contents with the expected model files. Done means the weights and metadata are present and the command completes without this error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100