Merge branch 'main' into promptless/flash-cli-dev-rename-endpoint-resolution

Author: promptless[bot]

runpodctl/reference/runpodctl-pod.mdx

@@ -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">
+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:

runpodctl/reference/runpodctl-serverless.mdx

@@ -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">
+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:
@@ -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: