can i run it on an agent that doesn't have gpu?

how do i run it without the file? for i have no gpu, or config the file so that the clearml will not throw the error

and where to put the file?

when i run clearml-serving it throughs me an error "please provide specific config.pbtxt definion"

ok i have managed to deploy model by thr clearml-serving, now they are runing on the docker container engine (that doesn't have GPU in it) , what is the entrypoints to the model in order to get predictions?

yes!!

i run it on docker and right now only exposing it by -p 8080:8000

does the clearml server is a worker i can serve on models?

and what ports does it use?