KServe

Learn how open source impacts watsonx through some of the key open source projects that IBM has invested in.

In this tutorial, learn how to serve your custom models by using ModelMesh Serving.

Use Caikit to serve Hugging Face AI models that are consumed by your application.

Using KServe and Ray Serve together is a flexible, scalable, and efficient approach to serving machine learning models in production

In this learning path, learn how to use Kubeflow Pipelines to orchestrate ML workflows.

In this tutorial, learn how to configure ModelMesh Serving to use Kubernetes "built-in" storage via persistent volumes.

Create, deploy, and manage machine learning workflows on Kubernetes using Kubeflow Pipelines

In this tutorial, you learn how to leverage Kubeflow Pipelines to improve and customize the large language models (LLMs) results by training the prompt tuning configuration based on your prompt datasets. This process can be automated and configured based on other new datasets and LLMs as well.

A mature, general-purpose model serving management and routing layer. Optimized for high volume, high density, and frequently changing model use cases, ModelMesh intelligently loads and unloads models to and from memory to strike a balance between responsiveness and compute.

A standard cloud-agnostic model inference platform that provides pluggable production serving.