Epic Goal
- Work covers the Helm Chart that helps developers to run a privately hosted AI model for development
- We'll be focusing on using Granite models
- Two Helm chart deliveries:
- Something similar to what we're delivering for
DEVAI-192: llama.cpp, CPU-only, but this chart would not have an app in it nor app deployment - Uses VLLM and GPUs so you can use a larger Granite model and get faster responses (definitely better for a shared model)
- Something similar to what we're delivering for
Why is this important?
- …
Scenarios
- ...
Acceptance Criteria (Mandatory)
- CI - MUST be running successfully with tests automated
- Release Technical Enablement - Provide necessary release enablement details and documents.
- ...
Dependencies (internal and external)
- ...
Previous Work (Optional):
- …
Open questions::
- …
Done Checklist
- Acceptance criteria are met
- Non-functional properties of the Feature have been validated (such as performance, resource, UX, security or privacy aspects)
- User Journey automation is delivered
- Support and SRE teams are provided with enough skills to support the feature in production environment
- depends on
-
RHIDP-10160 Automate the conversion from Software Templates to Helm Chart on AI samples
-
- Closed
-