Log 23 ๐ซ
ยท 2 min read
Objectiveโ
Deploy watsonx.ai on self-managed AWS infrastructure for customer software evaluation
Milestonesโ
- Deploy and configuration of boot node to establish a beach-head into the customer AWS environment
- Complete
- Deploy OCP using the documented UPI installation steps
- Complete
- Install Cloud Pak for Data
- Complete
- Deploy and configure watsonx.ai on self-managed AWS infrastructure on ref environment and document
- In Progress
Today's Accomplishmentsโ
- GPU node provisioned
- Deployment of Granite model
Summaryโ
- Provisioning GPU node
- Installing GPU operator
- Installing watsonx.ai operator
- Waiting on the installer
- Facing issues with Mistral IBM models for watsonx.ai - support case open
Decisions and Action Items (DAI)โ
- MCG Secrets created for Cloud Pak components
- Authorized Instance Topology
- Installed Cloud Pak shared components
- Installed Knative
- GPU Node Activity and Billing
Lessons Learnedโ
- GPU Node Activity
- AWS was charging for a GPU Node while powered-down
- Provisioned the GPU Node using a reserve instance (30 days starting May 6)
Next Stepsโ
- Deploy watsonx.ai
- Install NeuralSeek
- Application configuration
- NeuralSeek
- watsonx.ai Prompt Lab
- watsonx Assistant
- watsonx Orchestrate
- ServiceNow skills
- Microsoft Outlook skills