Explore serverless machine learning model inference on Kubernetes using KServe in this 38-minute conference talk from Devoxx. Learn how to integrate popular ML frameworks for easy model inference and prototyping, leverage Knative Serving for cost-effective autoscaling, build complex ML pipelines using inference graphs, and implement effective monitoring and deployment strategies. Gain practical insights into deploying your own models as various scenarios are described in detail, empowering you to take your ML deployments to the next level on Kubernetes.
Serverless Machine Learning Model Inference on Kubernetes with KServe
Overview
Syllabus
Serverless Machine Learning Model Inference on Kubernetes with KServe by Stavros Kontopoulos
Taught by
Devoxx
Related Courses
-
Building End-to-end Machine Learning Workflows with Kubeflow
-
Building an ML Inference Platform with Knative - Serverless Containers on Kubernetes
-
Develop Custom Object Detection Models with NVIDIA and Azure Machine Learning
-
Model Serving at the Edge - Challenges and Solutions with ModelMesh
-
Serving Machine Learning Models at Scale Using KServe
-
Serverless Machine Learning Inference with KFServing
