imjasonh/gcloud-help
1
0
Fork 0
mirror of https://github.com/imjasonh/gcloud-help synced 2026-07-16 12:22:03 +00:00
Code Activity

gcloud: Wed Mar 12 10:54:38 UTC 2025

Browse source
This commit is contained in:
Automated 2025-03-12 10:54:38 +00:00
parent 6dc93282df
commit a459a88a5f
152 changed files with 2634 additions and 1748 deletions
Download patch file Download diff file Expand all files Collapse all files

5
gcloud/alpha/ai/endpoints/deploy-model
View file

@ -11,6 +11,7 @@ SYNOPSIS
[--enable-container-logging] [--machine-type=MACHINE_TYPE]
[--max-replica-count=MAX_REPLICA_COUNT]
[--min-replica-count=MIN_REPLICA_COUNT]
[--multihost-gpu-node-count=MULTIHOST_GPU_NODE_COUNT]
[--reservation-affinity=[key=KEY],
[reservation-affinity-type=RESERVATION-AFFINITY-TYPE],
[values=VALUES]] [--service-account=SERVICE_ACCOUNT] [--spot]
@ -133,6 +134,10 @@ OPTIONAL FLAGS
If not specified and the uploaded models use dedicated resources, the
default value is 1.
--multihost-gpu-node-count=MULTIHOST_GPU_NODE_COUNT
The number of nodes per replica for multihost GPU deployments. Required
for multihost GPU deployments.
--reservation-affinity=[key=KEY],[reservation-affinity-type=RESERVATION-AFFINITY-TYPE],[values=VALUES]
A ReservationAffinity can be used to configure a Vertex AI resource
(e.g., a DeployedModel) to draw its Compute Engine resources from a