Unified and cross-platform CM interface for DevOps, MLOps and MLPerf

.

CM4MLOps repository

This repository is powered by the Collective Mind workflow automation framework.

Two key automations developed using CM are Script and Cache, which streamline machine learning (ML) workflows, including managing Docker runs. Both Script and Cache automations are part of the cmx4mlops repository.

The CM scripts, also housed in this repository, consist of hundreds of modular Python-wrapped scripts accompanied by yaml metadata, enabling the creation of robust and flexible ML workflows.

• CM Scripts Documentation: https://docs.mlcommons.org/cm4mlops/
• CM CLI Documentation: https://docs.mlcommons.org/ck/specs/cm-cli/

License

Apache 2.0

Copyright

© 2022-2025 MLCommons. All Rights Reserved.

Grigori Fursin, the cTuning foundation and OctoML donated the CK and CM projects to MLCommons to benefit everyone and encourage collaborative development.

Maintainer(s)

• MLCommons

Author

Grigori Fursin

We sincerely appreciate all contributors for their invaluable feedback and support!

Concepts

Check our ACM REP'23 keynote and the white paper.

Test image classification and MLPerf R-GAT inference benchmark via CMX PYPI package

pip install cmind
pip install cmx4mlops
cmx run script "python app image-classification onnx" --quiet
cmx run script --tags=run,mlperf,inference,generate-run-cmds,_submission,_short --submitter="MLCommons" --adr.inference-src.tags=_branch.dev --pull_changes=yes --pull_inference_changes=yes  --submitter="MLCommons" --hw_name=ubuntu-latest_x86 --model=rgat --implementation=python --backend=pytorch --device=cpu --scenario=Offline --test_query_count=500 --adr.compiler.tags=gcc --category=datacenter --quiet  --v --target_qps=1

Test image classification and MLPerf R-GAT inference benchmark via CMX GitHub repo

pip uninstall cmx4mlops
pip install cmind
cmx pull repo mlcommons@ck --dir=cmx4mlops/cmx4mlops
cmx run script "python app image-classification onnx" --quiet
cmx run script --tags=run,mlperf,inference,generate-run-cmds,_submission,_short --submitter="MLCommons" --adr.inference-src.tags=_branch.dev --pull_changes=yes --pull_inference_changes=yes  --submitter="MLCommons" --hw_name=ubuntu-latest_x86 --model=rgat --implementation=python --backend=pytorch --device=cpu --scenario=Offline --test_query_count=500 --adr.compiler.tags=gcc --category=datacenter --quiet  --v --target_qps=1

Parent project

Visit the parent Collective Knowledge project for further details.

Citing this project

If you found the CM automations helpful, kindly reference this article: [ ArXiv ]