About

What is Seldon-Deploy?

Seldon Deploy provides oversight and governance for machine learning deployments.

Easily deploy your models in an audited way with gitops. Leverage advanced monitoring and perform alibi-powered explanations on requests.

Seldon Deploy is an enterprise product to accelerate deployment management on top of the open source tools Seldon Core, KFServing and Seldon Alibi.

  • Deploy machine learning models easily using industry leading Seldon and KfServing open projects.

  • Ensure safe model deployment using the Gitops paradigm.

  • Audit model predictions using Black Box Model Explainers.

  • Monitor running models and search request/response logs.

  • Update models via Canary workflows.

Seldon Core

Seldon Core is an open source platform for deploying machine learning models on a Kubernetes cluster.

  • Deploy machine learning models in the cloud or on-premise.

  • Get metrics and ensure proper governance and compliance for your running machine learning models.

  • Create powerful inference graphs made up of multiple components.

  • Provide a consistent serving layer for models built using heterogeneous ML toolkits.

KFServing

Seldon Core fits into the stack alongside Seldon Deploy and your existing training pipelines as shown below:

KFServing

See the Seldon Core documentation for further details.

KFServing

KFServing provides a Kubernetes Custom Resource Definition for serving machine learning (ML) models on arbitrary frameworks. It aims to solve production model serving use cases by providing performant, high abstraction interfaces for common ML frameworks like Tensorflow, XGBoost, ScikitLearn, PyTorch, and ONNX.

It encapsulates the complexity of autoscaling, networking, health checking, and server configuration to bring cutting edge serving features like GPU Autoscaling, Scale to Zero, and Canary Rollouts to your ML deployments. It enables a simple, pluggable, and complete story for Production ML Serving including prediction, pre-processing, post-processing and explainability.

KFServing

Alibi

KFServing

Alibi is an open source Python library aimed at machine learning model inspection and interpretation. The initial focus on the library is on black-box, instance based model explanations.

Its goals are:

  • Provide high quality reference implementations of black-box ML model explanation algorithms

  • Define a consistent API for interpretable ML methods

  • Support multiple use cases (e.g. tabular, text and image data classification, regression)

  • Implement the latest model explanation, concept drift, algorithmic bias detection and other ML model monitoring and interpretation methods