Edit on GitHub

deployment run

Deploy a model to a target environment. Can use an existing deployment declaration or create a new one on-the-fly.



The deployment run command creates a new deployment for a target environment. One can either use an existing deployment declaration (created with mlem declare deployment) or create a new one on-the-fly with various available options (see below).


  • -l <path>, --load <path> - File to load deployment config from
  • -m <path>, --model <path> - Path to MLEM model
  • --mp <path>, --model-project <path> - Project with model
  • --mr <commitish>, --model-rev <commitish> - Revision of model
  • -p <path>, --project <path> - Path to MLEM project [default: (none)]
  • --rev <commitish> - Repo revision to use [default: (none)]
  • -h, --help - Show this message and exit.

Example: Create a new deployment from scratch

Here, we define an environment and then run a deployment on it, providing the deployment configuration on-the-fly

$ mlem declare env heroku staging --api_key=...

$ mlem deployment run service_name --model model --env staging --name=my_service

Example: Run a deployment from a pre-configured deployment

Here, we define an environment, configure a deployment declaration on it using mlem declare deployment, and then run our deployment with a simple concise command which uses the existing pre-configured deployment declaration

$ mlem declare env heroku staging --api_key=...

$ mlem declare deployment heroku service_name --app_name=my_service --model=model --env=staging

$ mlem deploy run service_name

­čÉŤ Found an issue? Let us know! Or fix it:

Edit on GitHub

ÔŁô Have a question? Join our chat, we will help you:

Discord Chat