Welcome
Self-hosted GPU compute. Run GPU Container jobs and serve open-source language models on your own Kubernetes cluster.
CosmicAC is a self-hosted platform for GPU compute. You deploy it on your own Kubernetes cluster, then use it to run GPU Container jobs and serve open-source language models through a single API endpoint.
Because CosmicAC runs entirely on your infrastructure, your data, models, and inference traffic never leave your cluster.
CosmicAC job types
CosmicAC runs two kinds of job. Choose the one that fits your task.
Get started
Deploy CosmicAC, then connect the CLI to start running jobs.
Once you have CosmicAC running, start here:
Learn the concepts
Understand how CosmicAC runs jobs and serves models on your cluster.
Guides
Follow step-by-step instructions for common tasks.
Reference
Look up commands, configuration options, and release details.