Feature Overview (mandatory - Complete while in New status)

• Validation of inference for existing models supported by Neural Magic vLLM. We need to do functional testing here to make sure that these models RUN functionally in the vLLM-ent version packaged on RHEL AI 1.5. 

Scope for summit:

• Llama 3.3 70B Instruct
• Granite 3.1 8B Instruct
• Llama 3.1 8B

Goals (mandatory - Complete while in New status)

Provide high-level goal statement, providing user context and expected user outcome(s) for this Feature

• We need to just ensure that functionally, these models can be run for inference in downstream RHEL AI 1.5 for the summit timeline as these are the models that we will run full validation on for Summit for inference flows. 

Requirements (mandatory -_ Complete while in Refinement status):

TBD

Done - Acceptance Criteria (mandatory - Complete while in Refinement status):

TBD