[Feature] Remote Inference Endpoints Support

[joshuayao]

Priority

P1-Stopper

OS type

Ubuntu

Hardware type

Xeon-GNR

Running nodes

Single Node

Description

The feature is from @louie-tsai:

• GenAIExamples: enabled remote inference endpoints for AgentQnA, Productivity Suite, ChatQnA, DocSum, CodeSum, FinanceAgent, workflowExecAgent, AudioQnA, CodeTrans, MulitmodalQnA, VideoQnA, VisualQnA
• GenAIComps : Enable remote endpoint for dynamic model switching/ endpoints without model name in it.
• GenAIInfra: enabled remote inference endpoints in helm chats for ChatQnA, CodeGen and DocSum - Owner : Pramod