Create a GPU Container Job
Create a GPU Container Job with the CLI, then confirm it.
Create a GPU Container Job from the CLI. Answer the prompts or pass flags, and CosmicAC creates the job.
Prerequisites
You need the following before you start:
- A running CosmicAC deployment. See Installation.
- The CosmicAC CLI installed and configured. See Install the CLI.
Steps
Create the job
Create the job interactively by answering prompts, or non-interactively by passing flags.
Start the interactive job setup:
cosmicac jobs createSelect GPU Container as the job type.
Set these fields:
- Job name: a name to identify the job.
- Tags: comma-separated labels for the job.
- Location: the region where the job runs.
- GPU type: the GPU to use. The CLI lists the GPUs available in your location.
- GPU count: the number of GPUs for the job. One of 1, 2, 4, or 8.
- Root disk size: the disk size in GB, for example 250. The minimum is 100.
- Notifications: the job lifecycle events this job reports. All four are on by default, and interactive mode prompts for them with a checkbox.
An event reaches your webhook only if it's also turned on in Settings → Notifications. See What controls delivery.
The Job configuration reference describes each field and its CLI flag.
Confirm the job
List your jobs to confirm CosmicAC created the job:
cosmicac jobs listThe job appears in the table with its ID, name, tags, and status. Wait for it to provision. You can access the job once its status is running. See Access a GPU Container Job.
Help and troubleshooting
The job never leaves Creating or Starting
Find the job's container ID. The output lists Container ID for each container:
cosmicac jobs detail <jobId>CosmicAC names that container's KubeVirt virtual machine instance (VMI) <container-id>-n0. A multi-node job has one VMI per node.
Where you run kubectl against your cluster, list the VMIs in the namespace you set in K8S_NAMESPACE:
kubectl get vmi -n <namespace>If the VMI reports Running while CosmicAC still shows the job as Creating or Starting, cosmicac-wrk-agent-instance can't reach cosmicac-wrk-server-k8s-nvidia. The two connect directly, and some cluster networks block that connection.
To carry the connection through a relay, see Set up a relay for CosmicAC.