imjasonh/gcloud-help
1
0
Fork 0
mirror of https://github.com/imjasonh/gcloud-help synced 2026-07-18 14:56:05 +00:00
Code Activity

gcloud: Wed Jul 2 11:05:25 UTC 2025

Browse source
This commit is contained in:
Automated 2025-07-02 11:05:25 +00:00
parent f645b4c02d
commit e53f7148d8
197 changed files with 6280 additions and 495 deletions
Download patch file Download diff file Expand all files Collapse all files

18
gcloud/ai/endpoints/deploy-model
View file

@ -84,18 +84,22 @@ 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 specifications that control autoscaling behavior. At most one
entry is allowed per metric.
METRIC-NAME
Resource metric name. Choices are 'cpu-usage', 'gpu-duty-cycle'.
Resource metric name. Choices are 'cpu-usage', 'gpu-duty-cycle',
'request-counts-per-minute'.
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%.
Target value for the given metric. For cpu-usage and
gpu-duty-cycle, the target is the target resource utilization in
percentage (1% - 100%). For request-counts-per-minute, the target
is the number of requests per minute per replica.
For example: --autoscaling-metric-specs=cpu-usage=70
For example, to set target CPU usage to 70% and target requests to
600 per minute per replica:
--autoscaling-metric-specs=cpu-usage=70,request-counts-per-minute=600
--deployed-model-id=DEPLOYED_MODEL_ID
User-specified ID of the deployed-model.