Skip to content

docs: Document new pod and serverless create flags #615

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
promptless wants to merge 5 commits into
base: main
Choose a base branch
from
Open

docs: Document new pod and serverless create flags #615

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
f6c00c3
Add new flags for pod and serverless create commands
promptless[bot] Apr 13, 2026
4e6548b
Merge branch 'main' into promptless/runpodctl-create-flags
promptless[bot] Apr 14, 2026
ccc4808
Merge branch 'main' into promptless/runpodctl-create-flags
promptless[bot] Apr 16, 2026
19b6007
Merge branch 'main' into promptless/runpodctl-create-flags
promptless[bot] Apr 16, 2026
2bc484e
Merge branch 'main' into promptless/runpodctl-create-flags
promptless[bot] Apr 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 28 additions & 0 deletions runpodctl/reference/runpodctl-pod.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -168,6 +168,34 @@ Enable SSH on the Pod.
Network volume ID to attach. Use [`runpodctl network-volume list`](/runpodctl/reference/runpodctl-network-volume) to see available network volumes.
</ResponseField>

<ResponseField name="--min-cuda-version" type="string">
Copy link
Copy Markdown
Contributor Author

@promptless promptless bot Apr 15, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added 7 new pod create flags (--min-cuda-version, --docker-args, --registry-auth-id, --country-code, --stop-after, --terminate-after, --compliance) based on the PR's feature additions. Flag details sourced from the PR description and E2E verification table.

Source: runpod/runpodctl#271

Minimum CUDA version required (e.g., `11.8`, `12.4`). The Pod will only be scheduled on machines that meet this CUDA version requirement.
</ResponseField>

<ResponseField name="--docker-args" type="string">
Docker arguments passed to the container at runtime (e.g., `"sleep infinity"`).
</ResponseField>

<ResponseField name="--registry-auth-id" type="string">
Container registry authentication ID for pulling private images. Use [`runpodctl registry list`](/runpodctl/reference/runpodctl-registry) to see available registry credentials.
</ResponseField>

<ResponseField name="--country-code" type="string">
Country code for regional deployment (e.g., `US`, `CA`, `EU`). Restricts Pod placement to machines in the specified region.
</ResponseField>

<ResponseField name="--stop-after" type="string">
Automatically stop the Pod after the specified duration (e.g., `1h`, `24h`, `7d`).
</ResponseField>

<ResponseField name="--terminate-after" type="string">
Automatically terminate the Pod after the specified duration (e.g., `1h`, `24h`, `7d`). Unlike `--stop-after`, this permanently deletes the Pod.
</ResponseField>

<ResponseField name="--compliance" type="string">
Compliance settings for the Pod (e.g., regulatory requirements for data handling).
</ResponseField>

### Start a Pod

Start a stopped Pod:
Expand Down
36 changes: 36 additions & 0 deletions runpodctl/reference/runpodctl-serverless.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,6 +122,34 @@ Comma-separated list of preferred datacenter IDs. Use [`runpodctl datacenter lis
Network volume ID to attach. Use [`runpodctl network-volume list`](/runpodctl/reference/runpodctl-network-volume) to see available network volumes.
</ResponseField>

<ResponseField name="--network-volume-ids" type="string">
Copy link
Copy Markdown
Contributor Author

@promptless promptless bot Apr 15, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added 7 new serverless create flags (--network-volume-ids, --min-cuda-version, --scaler-type, --scaler-value, --idle-timeout, --flash-boot, --execution-timeout) based on the PR's feature additions. Flag descriptions, types, and validation details sourced from the PR's E2E verification table.

Source: runpod/runpodctl#271

Comma-separated list of network volume IDs to attach. Use this when attaching multiple network volumes to an endpoint.
</ResponseField>

<ResponseField name="--min-cuda-version" type="string">
Minimum CUDA version required for workers (e.g., `12.4`). Workers will only be scheduled on machines that meet this CUDA version requirement.
</ResponseField>

<ResponseField name="--scaler-type" type="string" default="QUEUE_DELAY">
Autoscaler type (`QUEUE_DELAY` or `REQUEST_COUNT`). `QUEUE_DELAY` scales based on queue wait time; `REQUEST_COUNT` scales based on concurrent requests.
</ResponseField>

<ResponseField name="--scaler-value" type="int">
Scaler threshold value. For `QUEUE_DELAY`, this is the target delay in seconds. For `REQUEST_COUNT`, this is the number of concurrent requests per worker before scaling.
</ResponseField>

<ResponseField name="--idle-timeout" type="int">
Idle timeout in seconds. Workers shut down after being idle for this duration. Valid range: 5-3600 seconds.
</ResponseField>

<ResponseField name="--flash-boot" type="bool">
Enable or disable flash boot for faster worker startup. When enabled, workers start from cached container images.
</ResponseField>

<ResponseField name="--execution-timeout" type="int">
Execution timeout in seconds. Jobs that exceed this duration are terminated. The CLI accepts seconds but converts to milliseconds internally.
</ResponseField>

### Update an endpoint

Update endpoint configuration:
Expand Down Expand Up @@ -156,6 +184,14 @@ Scaler type (`QUEUE_DELAY` or `REQUEST_COUNT`).
Scaler value.
</ResponseField>

<ResponseField name="--flash-boot" type="bool">
Enable or disable flash boot for faster worker startup.
</ResponseField>

<ResponseField name="--execution-timeout" type="int">
Execution timeout in seconds. Jobs that exceed this duration are terminated.
</ResponseField>

### Delete an endpoint

Delete an endpoint:
Expand Down
Loading