Completed
22:10 - Configuring Tracing with Llama Stack and OTel Sidecars
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Why Observability Matters More with AI Applications
Automatically move to the next video in the Classroom when playback concludes
- 1 0:00 - Introduction: Why AI Observability Matters Now
- 2 1:15 - Live Demo Preview: RAG with Llama Stack & Safety Features
- 3 4:30 - The State of AI in Enterprise: Moving from Research to Business-Critical
- 4 6:55 - Unique Monitoring Challenges Posed by LLMs
- 5 9:15 - Prefill vs. Decode: The Core Difference in LLM Serving Patterns
- 6 12:05 - Building the Open-Source Stack: Prometheus, Grafana, Tempo, and OTel
- 7 15:00 - Kubernetes Deep Dive: ServiceMonitors Explained
- 8 18:45 - Deploying the Model: Using llm-d for vLLM Quick Start
- 9 22:10 - Configuring Tracing with Llama Stack and OTel Sidecars
- 10 27:50 - Critical Signals to Monitor: Performance, Cost, and Quality
- 11 32:00 - Live Demo: Analyzing GPU Usage, vLLM Dashboards & Traces in Grafana
- 12 37:45 - Q&A: Open-Source Cost, Langfuse, and Actionable Analytics for Different Personas
