gcloud: Wed Aug 17 09:22:03 UTC 2022

gcloud/ai/endpoints/deploy-model

@@ -6,6 +6,7 @@ SYNOPSIS
     gcloud ai endpoints deploy-model (ENDPOINT : --region=REGION)
         --display-name=DISPLAY_NAME --model=MODEL
         [--accelerator=[count=COUNT],[type=TYPE]]
+        [--autoscaling-metric-specs=[METRIC-NAME=TARGET,...]]
         [--deployed-model-id=DEPLOYED_MODEL_ID] [--disable-container-logging]
         [--enable-access-logging] [--machine-type=MACHINE_TYPE]
         [--max-replica-count=MAX_REPLICA_COUNT]
@@ -73,6 +74,20 @@ OPTIONAL FLAGS
 
             For example: --accelerator=type=nvidia-tesla-k80,count=1
 
+     --autoscaling-metric-specs=[METRIC-NAME=TARGET,...]
+        Metric specifications that overrides a resource utilization metric's
+        target value. At most one entry is allowed per metric.
+
+         METRIC-NAME
+            Resource metric name. Choices are 'cpu-usage', 'gpu-duty-cycle'.
+
+         TARGET
+            Target resource utilization in percentage (1% - 100%) for the given
+            metric. If the value is set to 60, the target resource utilization
+            is 60%.
+
+            For example: --autoscaling-metric-specs=cpu-usage=70
+
      --deployed-model-id=DEPLOYED_MODEL_ID
         User-specified ID of the deployed-model.