Getting Started

Requirements Deploy CosmicAC

Install the CLI Create a GPU Container Job Create a Managed Inference Job (vLLM)Create an API key

Guides

GPU Container Job

Managed Inference Job

Platform management

Concepts

Architecture GPU Container Job Managed Inference Job

Reference

CosmicAC CLI commands

Configuration reference Task deployment commands Job configuration reference Recommended model parameters

Quick Start

Create your first GPU Container Job or Managed Inference Job with the CosmicAC CLI or the web interface.

After you deploy CosmicAC, install the CosmicAC CLI to create your first job. You can also create jobs in the CosmicAC web interface.

Install the CLI

Install the CLI

Create and manage jobs from your terminal.

Create a GPU Container Job

Create a GPU Container Job

Run workloads on a GPU machine with shell access.

You can also create one in the web interface. See Create a GPU Container Job (web interface).

Create a Managed Inference Job

Create a Managed Inference Job

Serve a model behind an OpenAI-compatible endpoint.

Create an API key

Authenticate requests to your Managed Inference endpoint.

You can also create one in the web interface. See Create a Managed Inference Job (web interface).

Deploy CosmicAC

Previous Page

Install the CLI

Next Page

On this page

Install the CLI Create a GPU Container Job Create a Managed Inference Job