Is automated load testing best practise for MlOps

I have an an ml ops pipeline setup to automatically update a machine learning model in production. The general pipeline steps are:

1. Run unit tests
2. Preprocess training data
3. Train model
4. Evaluate model
5. Deploy model to beta endpoint
6. Run Integration tests
7. Deploy model to production endpoint (manually approved step)

My question is: Is it best practise to automatically perform some kind of load testing of the endpoint after step 5? By load testing I mean making sure that the endpoint will be able to handle the expected traffic in production