feat: ORT GenAI Stateful Compilation changes

[ankitm3k]

Description

This PR enables the essential features to enable ORT GenAI with OVEP using Stateful Compilation of ov::Model, inspired from OV GenAI pipeline flow.

I have introduced a new provider option enable_causallm which can be set to True for enabling the ORT GenAI pipeline with Causal LLM Models that are fully supported on OVEP in the custom config file called genai_config.json

Sample genai_config.json -

"provider_options": [
    {
         // Key "OpenVINO" is case sensitive and must be used as below as its defined by MSFT
         "OpenVINO":
          {
              "device_type": "NPU",
              "enable_causallm" : "True",
              // (Applicable for NPU only) Optional setting for compilation with custom MAX_PROMPT_LEN & MIN_RESPONSE_LEN
              "load_config": "{\"NPU\":{\"MAX_PROMPT_LEN\":\"2048\",\"MIN_RESPONSE_LEN\":\"512\"}}"                            
                       
           }
    }
    ]

FYI the GenAI models in ONNX format are usually Stateless in nature & require dynamic shapes compilation.

[preetha-intel]

Is the name "beam_idx" particular to LLM model? It looks like a custom check

[ankitm3k]

yes its a input name which is a part of ov::model which gets created as a part of translation. It required for OV LLMCOmpilation & inference pipeline. Its model agnostic