Foundations
Serving a Generative Model
- The InferenceService Manifest
- Serving a Quantized Qwen Model
- Calling the Model
- Demo Deploying and Calling the Qwen Model
Foundations
Course: KServe Fundamentals: Serving ML Models on Kubernetes
Guide to deploying and operating generative and predictive ML models on Kubernetes using KServe, including installation, InferenceService and LLMISvc, serving patterns, and troubleshooting
Notes for the KServe Fundamentals: Serving ML Models on Kubernetes course: 11 lessons across 4 sections.