All Tools
S
Dev ToolsFreemium
SELDON CORE
An MLOps framework to deploy, manage and scale AI systems in Kubernetes
BUSL-1.1
ABOUT
Standardizes deployment, monitoring, and management of production machine learning models at scale on Kubernetes. Enables data-centric AI pipelines, reduces infrastructure costs through multi-model serving and autoscaling, and supports advanced experimentation like A/B tests and canary deployments.
INSTALL
helm repo add seldon-charts https://seldonio.github.io/helm-charts/
helm repo update seldon-charts
helm upgrade seldon-core-v2-crds seldon-charts/seldon-core-v2-crds --namespace default --install
helm upgrade seldon-core-v2-setup seldon-charts/seldon-core-v2-setup --namespace seldon-mesh --set controller.clusterwide=true --install
helm upgrade seldon-core-v2-runtime seldon-charts/seldon-core-v2-runtime --namespace seldon-mesh --install
helm upgrade seldon-core-v2-servers seldon-charts/seldon-core-v2-servers --namespace seldon-mesh --install
INTEGRATION GUIDE
1. Real-time model serving and inference at scale via REST or gRPC
2. Composable AI pipelines connecting preprocessing, models, post-processing, and custom logic with Kafka-based data streaming
3. A/B testing, canary deployments, and shadow deployments for model experimentation in production
4. Multi-model serving and resource optimization with autoscaling and over-commit to minimize hardware costs
TAGS
MLOpsLLMOpsKubernetesmodel-servinginferencehelmai-deploymentpipelinesa-b-testingautoscaling