A high-throughput and memory-efficient inference and serving engine for LLMs

Notebook images for ODH

Collection of Architectural Decision Records

Tensors and Dynamic neural networks in Python with strong GPU acceleration

odh qe tier tests

Model components of the Llama Stack APIs

Operator for installation and lifecycle management of CodeFlare distributed workload stack, starting with MCAD and InstaScale

Machine Learning Toolkit for Kubernetes

Dashboard for ODH

Controller for ModelMesh

Repository for official documentation of ODH Core components

Open Data Hub operator to manage ODH component integrations

Training operators on Kubernetes.

Common pipeline-editor components used in different clients (e.g. Elyra application, Web browser extensions, etc)

Elyra extends JupyterLab with an AI centric approach.

Standardized Serverless ML Inference Platform on Kubernetes

Development repository for the Triton language and compiler

Taxonomy tree that will allow you to create models tuned with your data

Command-line interface. Use this to chat with the model or train the model (training consumes the taxonomy data)

Artifacts for the Distributed Workloads stack as part of ODH

Kubeflow Model Registry

Build your own wheels

Examples for building and running LLM services and applications locally with Podman