Amazon SageMaker - enables developers to create, train, and deploy machine-learning (ML) models in the cloud, and on embedded systems and edge-devices. KFServing - enables serverless inferencing on Kubernetes and provides performant, high abstraction interfaces for common machine learning (ML) frameworks like TensorFlow, XGBoost, scikit-learn, PyTorch, and ONNX to solve production model serving use cases. Kubeflow - making deployments of machine learning (ML) workflows on Kubernetes simple, portable and scalable mlflow - an open source platform to manage the ML lifecycle, including experimentation, reproducibility, deployment, and a central model registry. NVIDIA Triton Inference Server - cloud inferencing solution; provides an inference service via an HTTP/REST or GRPC endpoint, allowing remote clients to request inferencing for any model being managed by the server; edge deployments Open PAI - AI computing resources sharing; AI assets (eg. Model, Data, Environment) share and reuse; IT ops platform for AI; training pipeline
