legacy clean up

README.md

@@ -1,26 +1,22 @@
-## Unified and cross-platform CM interface for DevOps, MLOps and MLPerf
+# Legacy CM4MLOps repository with DevOps, MLOps and MLPerf automations
 
 [![License](https://img.shields.io/badge/License-Apache%202.0-green)](LICENSE.md)
 [![Powered by CM](https://img.shields.io/badge/Powered_by-MLCommons%20CM-blue)](https://pypi.org/project/cmind).
 
-[![CM script automation features test](https://github.com/mlcommons/cm4mlops/actions/workflows/test-cm-script-features.yml/badge.svg)](https://github.com/mlcommons/cm4mlops/actions/workflows/test-cm-script-features.yml)
-[![MLPerf inference bert (deepsparse, tf, onnxruntime, pytorch)](https://github.com/mlcommons/cm4mlops/actions/workflows/test-mlperf-inference-bert-deepsparse-tf-onnxruntime-pytorch.yml/badge.svg)](https://github.com/mlcommons/cm4mlops/actions/workflows/test-mlperf-inference-bert-deepsparse-tf-onnxruntime-pytorch.yml)
-[![MLPerf inference MLCommons C++ ResNet50](https://github.com/mlcommons/cm4mlops/actions/workflows/test-mlperf-inference-mlcommons-cpp-resnet50.yml/badge.svg)](https://github.com/mlcommons/cm4mlops/actions/workflows/test-mlperf-inference-mlcommons-cpp-resnet50.yml)
-[![MLPerf inference ABTF POC Test](https://github.com/mlcommons/cm4mlops/actions/workflows/test-mlperf-inference-abtf-poc.yml/badge.svg)](https://github.com/mlcommons/cm4mlops/actions/workflows/test-mlperf-inference-abtf-poc.yml)
-
-# CM4MLOps repository
 
 This repository is powered by the [Collective Mind workflow automation framework](https://github.com/mlcommons/ck/tree/master/cm).
 
+The latest sources are available in [this repository](https://github.com/mlcommons/ck/tree/master/cm4mlops).
+
 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.
+including managing Docker runs. Both Script and Cache automations are part of the **cm4mlops** repository.
 
 The [CM scripts](https://access.cknowledge.org/playground/?action=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/](https://docs.mlcommons.org/cm4mlops/)
-- **CM CLI Documentation**: [https://docs.mlcommons.org/ck/specs/cm-cli/](https://docs.mlcommons.org/ck/specs/cm-cli/)  
+- **CM Scripts Documentation**: [Browse](https://access.cknowledge.org/playground/?action=scripts)
+- **CM CLI Documentation**: [https://docs.mlcommons.org/ck/specs/cm-cli/](https://docs.mlcommons.org/ck/specs/cm-cli)  
 
 ## License
 
@@ -38,31 +34,22 @@ Grigori Fursin, the cTuning foundation and OctoML donated the CK and CM projects
 
 ## Author
 
-[Grigori Fursin](https://cKnowledge.org/gfursin)
+[Grigori Fursin](https://cKnowledge.org/gfursin).
 
-We sincerely appreciate all [contributors](https://github.com/mlcommons/ck/blob/master/CONTRIBUTORS.md) 
+We thank all [contributors](https://github.com/mlcommons/ck/blob/master/CONTRIBUTORS.md) 
 for their invaluable feedback and support!
 
 ## Concepts
 
 Check our [ACM REP'23 keynote](https://doi.org/10.5281/zenodo.8105339) and the [white paper](https://arxiv.org/abs/2406.16791).
 
-## Test image classification and MLPerf R-GAT inference benchmark via CMX PYPI package
-
-```bash
-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
 
 ```bash
-pip uninstall cmx4mlops
 pip install cmind
-cmx pull repo mlcommons@ck --dir=cmx4mlops/cmx4mlops
+cmx pull repo mlcommons@ck --dir=cm4mlops/cm4mlops
 cmx run script "python app image-classification onnx" --quiet
+cmx run script "run-mlperf inference _performance-only _short" --model=resnet50 --precision=float32 --backend=onnxruntime --scenario=Offline --device=cpu --env.CM_SUDO_USER=no --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
 ```
 

automation/script/module.py

@@ -6558,7 +6558,9 @@ def dump_repro(repro_prefix, rr, run_state):
         cm_output['version_info'] = version_info
 
     if rr['return'] == 0:
+
         # See https://cTuning.org/ae
+
         cm_output['acm_ctuning_repro_badge_available'] = True
         cm_output['acm_ctuning_repro_badge_functional'] = True
 

script/app-image-classification-torch-py/src/pytorch_classify_preprocessed.py

@@ -72,7 +72,7 @@ def main():
     path_to_model_pth = os.environ['CM_ML_MODEL_FILE_WITH_PATH']
 
     model = models.resnet50(pretrained=False)
-    model.load_state_dict(torch.load(path_to_model_pth))
+    model.load_state_dict(torch.load(path_to_model_pth, weights_only=False))
 
     model.eval()