User Story:
As a customer, I would like to understand the relative performance of NVIDIA NIMs models on Red Hat software stack compared to the same models running with other inference runtime. I would also like to understand the performance improvements going into NVIDIA's NIM software stack over a period of time.

Acceptance criteria:

• Initial Performance tests results for NVIDIA NIM - readout with a slide deck

• Subsequently, the same tests automated in PSAP's CPT for AI workloads to reduce the time to get future results