Kfserving: Support for PySpark 2.4.4 Mllib

[ace-gabriel]

/kind feature

Hi, our current pipeline and models are implemented using PySpark Mllib. After looking at the examples I realize we currently don't support PySpark Mllib. Can we include PySpark model server as additional feature in the next release? Thanks

Link on how MLflow implement Spark: https://www.mlflow.org/docs/latest/python_api/mlflow.spark.html

[issue-label-bot[bot]]

Issue-Label Bot is automatically applying the labels:

| Label | Probability |
| ------------- | ------------- |
| feature | 0.98 |

Please mark this comment with :thumbsup: or :thumbsdown: to give our bot feedback!
Links: app homepage, dashboard and code for this bot.

[issue-label-bot[bot]]

Issue-Label Bot is automatically applying the labels:

| Label | Probability |
| ------------- | ------------- |
| area/engprod | 0.76 |

Please mark this comment with :thumbsup: or :thumbsdown: to give our bot feedback!
Links: app homepage, dashboard and code for this bot.

[Talador12]

Who is working on this? There is no current assignee.

Support for Spark ML would be a huge boon for KFServing!