Hi all, I am trying to add a model to my recently setup k8s self-hosted clearml-serving. The command looks like this and worked whith my previous docker setup:
clearml-serving --id fec7d23cc2b848b48d15041ce965ed81 model add --engine triton --endpoint "advanced_basic_classifier" --preprocess "src/preprocessing/preprocess.py" --model-id 837276fc8d8a443fb91f48d722300b0a --input-size 1 64 --input-name "INPUT__0" --input-type float32 --output-size 1 11 --output-name "OUTPUT__0" --output-type float32
But with the k8s setup I get this error on the triton node

E0405 14:50:27.960808 35 model_repository_manager.cc:996] Poll failed for model directory 'advanced_basic_classifier': Invalid model name: Could not determine backend for model 'advanced_basic_classifier' with no backend in model configuration. Expected model name of the form 'model.<backend_name>'.

Afterwards I changed the endpoint to advanced_basic_classifier.pytorch according to the error message and got a new error

E0405 14:55:27.962135 35 model_repository_manager.cc:996] Poll failed for model directory 'advanced_basic_classifier.pytorch': unexpected 'platform' and 'backend' pair, got:, pytorch

So I tried to specify the platform with the aux-config flag, but the error message still did not change. Even when I pass a whole config.pbtxt file with the aux-config flag no specification of the platform is detected. Does anybody know how to solve this issue?