Add modelmesh support

[drewbutlerbb4]

Signed-off-by: Andrew-Butler [email protected]

Rework the inference services asset to work with model-mesh predictors. Includes accessing the predictors with the kubernetes Python sdk, adding cluster role and role binding, and parsing the predictor yaml, and displaying predictor info in UI.

[mlx-bot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: drewbutlerbb4

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:

• OWNERS [drewbutlerbb4]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[drewbutlerbb4]

@Tomcli I have a cluster-role and cluster-rolebinding that need to applied on installation. Could you advise on how to get that working?

[Tomcli]

@drewbutlerbb4 do you have the command/yaml for the new cluster-role? I can convert them into something kustomize can understand and deploy it as part of the deployment.

[Tomcli]

it would look something like this
https://github.com/machine-learning-exchange/mlx/blob/main/manifests/base/mlx-deployments/mlx-api.yaml#L75-L89

[drewbutlerbb4]

Thanks @Tomcli, I have updated accordingly

[drewbutlerbb4]

Okay @Tomcli, I have added that below. Thanks!

[Tomcli]

/lgtm