Story (Required)

As a developer who is going to use the Software Templates and create a Component, I would like to use the vLLM model server. But I dont really know how much system specs I need to run a vLLM model.

Background (Required)

Currently when we choose vLLM, we just say:
If you choose vLLM, ensure your cluster has Nvidia GPU supported, and is with enough cpu and memory
 
We need to be a bit more specifc according to the UX, to help user understand the requirements.

Out of scope

<Defines what is not included in this story>

Approach (Required)

• Figure out what the bare minimum is to run the vLLM model servers
• Since we use the vLLM image uay.io/rh-aiservices-bu/vllm-openai-ubi9:0.4.2, we need to figure out if there is anything specific for this image

Dependencies

<Describes what this story depends on. Dependent Stories and EPICs should be linked to the story.>

Acceptance Criteria (Required)

• Figure out the bare minimum spec requirements like CPU, memory and GPU to run the vLLM model servers
• Follow UX recommendation of having the Model Server desc to be under each name in the dropbox rather than below the dropbox field

Done Checklist

Code is completed, reviewed, documented and checked in
Unit and integration test automation have been delivered and running cleanly in continuous integration/staging/canary environment
Continuous Delivery pipeline(s) is able to proceed with new code included
Customer facing documentation, API docs, design docs etc. are produced/updated, reviewed and published
Acceptance criteria are met
If the Grafana dashboard is updated, ensure the corresponding SOP is updated as well