Are there any plans to support streaming of prediction responses?

[Legion2]

I'm currently trying to setup streaming reponses of LLM generation from vLLM, however I receive an Streaming not yet supported error from modelmesh. I think this is coming from this code snippet:

modelmesh/src/main/java/com/ibm/watson/modelmesh/SidecarModelMesh.java

Line 433 in eaa2fde

String msg = "Streaming not yet supported";

It looks like implementing streaming is a non trivial task in this SidecarModelMesh class. Are there any plans on implementing streaming support or are there any blockers for this?