Seldon Core
Seldon Core
Seldon Core is the leading open source framework for easily and quickly deploying models and experiments at scale.
Try Core Enterprise for the functionality of Core with the reassurance of enterprise-level support.
Seldon Core, which leverages streaming technologies such as Kafka, enables you to build high-performance inference pipelines that support synchronous and asynchronous request flows for your inference components. The open and extensible design provides support for a wide range of model artifacts and custom models to be easily run side by side on industry-leading model servers, including NVIDIA Triton and Seldon’s MLServer.
Better infrastructure for energy and cost efficiency
Configurable multi-model serving and overcommit allows you to deploy and host multiple models on a single server
Optimize traffic flow for improved user experience
Use advanced inference redirection for A/B tests and shadow models
Supports monitoring and explainability
Easily audit and debug data flows through your inference pipelines with replayable data transforms
Run ML pipelines anywhere
Build pipelines with support for testing on local infrastructure before seamlessly deploying to a production Kubernetes cluster
Data-Centric Deployment Pipelines
Seldon Core enables data-centricity and easier model deployments through experiments, ensembles, and transformers.
Runs on any cloud, is framework agnostic, and supports top ML libraries, toolkits, and languages.
Seldon is backed by a thriving MLOps community with over 3,000 members. Join them here.
Blazing Fast, Industry-Ready ML
Seldon Core converts your ML models (Tensorflow, Pytorch, H2o, etc.) or language wrappers (Python, Java, etc.) into production REST/GRPC microservices.
Seldon Core handles scaling to thousands of production machine learning models and provides advanced machine learning capabilities out of the box including Advanced Metrics, Request Logging, Explainers, Outlier Detectors, A/B Tests, Canaries and more.
Platform Integrations
Seamlessly integrate Seldon’s advanced deployment features into your existing workflow with support for Kubeflow, OpenShift, GCP Marketplace and OperatorHub.