AI296 – Develop, Test, and Run Granite Family LLMs with Red Hat Enterprise Linux AI — Lesson 4: Serving, Performance, Observability, Troubleshooting, Governance, and Operations

Learning Objectives

• Operate, diagnose, document, recover, and improve model serving, performance, and observability.
• Apply troubleshooting and governance and operations while preserving reviewable technical evidence.
• Recognize and correct the condition where the technical result is restored but monitoring, rollback, evidence, ownership, or handover remains incomplete.

Detailed Topics

• model serving: apply the concept to the course scenario, identify dependencies and controls, and record objective evidence of the result.
• performance: apply the concept to the course scenario, identify dependencies and controls, and record objective evidence of the result.
• observability: apply the concept to the course scenario, identify dependencies and controls, and record objective evidence of the result.
• troubleshooting: apply the concept to the course scenario, identify dependencies and controls, and record objective evidence of the result.
• governance and operations: apply the concept to the course scenario, identify dependencies and controls, and record objective evidence of the result.

Instructor Demonstration

The instructor demonstrates serving, performance, observability, troubleshooting, governance, and operations by tracing architecture, commands, configuration, system messages, and evidence. The walkthrough tests how the technical result is restored but monitoring, rollback, evidence, ownership, or handover remains incomplete and explains how to isolate the cause without masking related issues.

Hands-On Exercise

Conduct an operational acceptance review for Serving, Performance, Observability, Troubleshooting, Governance, and Operations and add the verified result to the RHEL AI project, model-serving configuration, evaluation results, security checklist, and operations guide.

1. Confirm scope, versions, access, dependencies, assumptions, and acceptance criteria.
2. Perform the workflow while recording commands, configuration, output, events, and decisions.
3. Test the normal path and one course-specific exception or boundary condition.
4. Retest the correction and document rollback, ownership, and follow-up actions.

Scenario Analysis

• Identify which dependency most strongly influences model serving in the stated scenario.
• Compare two approaches for troubleshooting and explain the security, reliability, performance, and support trade-offs.
• Decide what evidence must be retained in the RHEL AI project, model-serving configuration, evaluation results, security checklist, and operations guide before operational acceptance.

Troubleshooting Guidance

Begin with the first observable difference from the expected result. Check monitoring, troubleshooting, rollback, ownership, evidence, and handover separately, then correlate logs, events, commands, metrics, and configuration history. Treat the assumption that the technical result is restored but monitoring, rollback, evidence, ownership, or handover remains incomplete as a hypothesis until a reproducible retest confirms the cause.

Validation Checklist

• The required monitoring, troubleshooting, rollback, ownership, evidence, and handover were checked and recorded.
• The normal path and a course-specific exception were tested.
• The RHEL AI project, model-serving configuration, evaluation results, security checklist, and operations guide links conclusions to commands, configuration, logs, metrics, or other objective evidence.
• Corrective actions, rollback, ownership, and handover notes are complete.

Lesson Outcome

Learners can apply Serving, Performance, Observability, Troubleshooting, Governance, and Operations, explain the observed platform behavior, and support the result with a reviewable RHEL AI project, model-serving configuration, evaluation results, security checklist, and operations guide.