model-serving

/kind feature

Describe the solution you'd like
[A clear and concise description of what you want to happen.]
Add a sample of MMS using a custom model server similar to sklearn and triton that will reside [in

Currently deployment creation allow users to set an env var and pass to the BentoServer container. However in production scenarios, users may want to get env var values directly from existing configmap or secret resources in their k8s cluster. e.g.:

env:
        # Define the environment variable
        - name: SPECIAL_LEVEL_KEY
          valueFrom:
            configMapKeyRef:
      

So far, there is only one Worker base type with JSON serialization and Pickle IPC serialization.

• #139
• #140

@zacbrannelly Not sure if this is possible in the current released version, so creating this just to keep track.