seldon-server
ML deployment platform
A platform for deploying machine learning models into production on-premise or in the cloud using Kubernetes and various machine learning frameworks.
Machine Learning Platform and Recommendation Engine built on Kubernetes
1k stars
135 watching
299 forks
Language: Java
last commit: over 4 years ago awsazureclouddeep-learningdeploymentdockergcpjavakafkakafka-streamskubernetesmachine-learningmicroservicespredictionpythonrecommendation-enginerecommender-systemseldonsparktensorflow
Related projects:
| Repository | Description | Stars |
|---|---|---|
 axsaucedo/seldon-core | Platform to deploy machine learning models on Kubernetes at scale | 18 |
| seldonio/mlserver | An inference server for machine learning models with support for multiple frameworks and scalable deployment options. | 720 |
 deploykf/deploykf | Builds machine learning platforms on Kubernetes by combining popular tools and services | 376 |
 caraml-dev/merlin | A platform for deploying and serving machine learning models in a scalable, cost-efficient, and easy-to-use manner | 167 |
| seldonio/tempo | An MLOps Python library that enables data scientists to deploy and orchestrate machine learning pipelines for production-ready inference. | 116 |
 samsung/veles | A distributed machine learning platform for rapid Deep learning application development | 906 |
 hydrospheredata/hydro-serving | A MLOps platform for deploying and versioning machine learning models in production. | 271 |
 combust/mleap | Enables deployment of machine learning data pipelines and algorithms to production | 1,504 |
 h2oai/h2o-3 | An in-memory machine learning platform that supports various algorithms and provides tools for building, deploying, and scaling machine learning models | 6,922 |
 aws-samples/machine-learning-using-k8s | Demystifies deploying machine learning models on Kubernetes | 163 |
 logicalclocks/hopsworks | A platform for managing machine learning data and workflows, integrating feature engineering, governance, and model serving capabilities. | 1,165 |
 jedld/tensor_stream | A Ruby-based framework for building and deploying machine learning models on various hardware platforms. | 507 |
 ebhy/budgetml | Simplifies deployment of machine learning models to production-ready endpoints with minimal configuration and cost. | 1,338 |
 star-whale/starwhale | An MLOps platform providing tools and services for efficient machine learning development and deployment | 208 |
 apache/incubator-samoa | A distributed streaming machine learning framework that enables development of new algorithms and execution in multiple processing engines | 248 |