How are you currently trying to wrap it up in python?

Hi @<1569496075083976704:profile|SweetShells3> , do you mean to run the CLI command via python code?

Expected behavior - pic 1
Actual behavior - pic 2

Hi @<1523701070390366208:profile|CostlyOstrich36> Yes

Or run clearml-serving python code without CLI wrapper

@<1523701070390366208:profile|CostlyOstrich36>

I spin endpoint with:
!clearml-serving --id "<>" model add --engine triton --endpoint 'modelname' --model-id '<>' --preprocess 'preprocess.py' --input-size '[-1, -1]' '[-1, -1]' '[-1, -1]' --input-name 'input_ids' 'token_type_ids' 'attention_mask' --input-type int64 int64 int64 --output-size '[-1, -1]' --output-name 'logits' --output-type float32 --aux-config name=\"modelname\" platform=\"onnxruntime_onnx\" default_model_filename=\"model.bin\"

Also I tried with os.system:
os.system("clearml-serving --id "<>" model add --engine triton --endpoint 'modelname' --model-id '<>' --preprocess 'preprocess.py' --input-size '[-1, -1]' '[-1, -1]' '[-1, -1]' --input-name 'input_ids' 'token_type_ids' 'attention_mask' --input-type int64 int64 int64 --output-size '[-1, -1]' --output-name 'logits' --output-type float32 --aux-config name=\"modelname\" platform=\"onnxruntime_onnx\" default_model_filename=\"model.bin\"")