Open sourceActive

KubeAI

Kubernetes solution for running inference on open-weight LLMs with web UI and OpenAI-compatible API.

Field note

What it does

KubeAI is a Kubernetes solution for running inference on open-weight large language models (LLMs). It uses model servers like vLLM and Ollama, and provides a web UI powered by Open WebUI and an OpenAI-compatible API.

Capabilities

Available capabilities

Web UI LLM Inference OpenAI-compatible API Kubernetes Deployment

Accessing the MSlurm cluster #

KubeAI

What it does

Available capabilities

Tags

Ways to use it

Product features

Accessing the MSlurm cluster #

Creating a new user from the command line #

Creating and removing MSlurm users #

Introduction to Slurm #

Lambda's Slurm #

Managed Slurm #

Managing users from the Slurm console #

Removing a user from the command line #

Running jobs on the MSlurm cluster #

Shared features #

Unmanaged Slurm #

Using Lambda's Managed Slurm #