Add S3 config parameters to flux/dlrm/retinanet yaml files

[ddn-kums]

The v3.0 workloads {flux|dlrm|retinanet}_{b200|mi355} are currently missing S3 storage parameters. We would need to create new {flux|dlrm|retinanet}_{b200|mi355} workload yaml files for the currently support S3 libraries {s3dlio|minio|s3torch} and add the following fields (similar to unet3d).

storage:
  storage_type: s3
  storage_root: <s3-bucket-name>
  storage_library: <{s3dlio|minio|s3torch}>
  storage_options:
    endpoint_url: <S3_URL>
    region: us-east-1
    s3_force_path_style: true

checkpoint:
  checkpoint_folder: s3://<s3-bucket-name>/s3dlio/llama3-8b

FYI: @russfellows

[ddn-kums]

As of 04/09, S3 storage parameters are only included in the following workload yaml files:

$ date; ls -1 workload/*.yaml  | egrep 's3dlio|minio|s3torch'
Thu Apr  9 12:33:55 AM UTC 2026
workload/datagen_s3dlio_azure.yaml
workload/datagen_s3dlio_multiendpoint.yaml
workload/datagen_s3dlio_s3.yaml
workload/llama3_8b_checkpoint_minio.yaml
workload/llama3_8b_checkpoint_s3dlio.yaml
workload/llama3_8b_checkpoint_s3torch.yaml
workload/pytorch_s3dlio_azure.yaml
workload/pytorch_s3dlio_local_test.yaml
workload/pytorch_s3dlio_multiendpoint.yaml
workload/pytorch_s3dlio.yaml
workload/pytorch_s3torchconnector.yaml
workload/resnet50_s3dlio_test.yaml
workload/test_unet3d_datagen_s3dlio.yaml
workload/test_unet3d_train_s3dlio.yaml
workload/unet3d_h100_minio_datagen.yaml
workload/unet3d_h100_minio.yaml
workload/unet3d_h100_s3dlio_datagen.yaml
workload/unet3d_h100_s3dlio.yaml
workload/unet3d_h100_s3torch_datagen.yaml
workload/unet3d_h100_s3torch.yaml

[russfellows]

With the new updates to mlpstorage in my fork, no specific YAML changes will be required for object storage. Hence, with my most recent changes, this should not be an issue. Please confirm if / when possible.