1. What is the nature and description of the request?
> ROSA cluster and ROSA HCP cluster should support for EC2 G6 instances as per documentation[1] and documentation[2]
[2] https://docs.openshift.com/rosa/rosa_architecture/rosa_policy_service_definition/rosa-hcp-instance-types.html
[1] https://docs.openshift.com/rosa/rosa_architecture/rosa_policy_service_definition/rosa-instance-types.html

2. Why does the customer need this? (List the business requirements here)
2.1 Cx wants to run inferences with HighRes VIT model to detect cracks and damages in concrete having an image size of 20MP and inferencing at a rate of 28 seconds per inference
2.2 Cx requires Multi GPU EC2 instance types
2.3 Cx has noticed GPUs such as g5.12xlarge(A10) and p3.8xlarge(V100) are too much expensive and cheaper GPU such as g4dn.12xlarge(T4) do not meet performance requirement. On the other hand g6.*(L4) series offers sweet spot for price/performance. Refer attached image for cost estimation.

3. List any affected packages or components.
Nvidia GPU operator - https://docs.nvidia.com/datacenter/cloud-native/openshift/24.9.2/introduction.html
Node feature discovery operator - https://docs.openshift.com/container-platform/4.16/hardware_enablement/psap-node-feature-discovery-operator.html