Statements (50)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:cloud_service
|
gptkbp:enables |
A/B testing
model deployment online prediction |
gptkbp:hasFeature |
logging
monitoring model monitoring GPU support private endpoints explanations IAM-based access control CPU support endpoint monitoring custom prediction routines endpoint authentication endpoint authorization endpoint autoscaling endpoint creation endpoint deletion endpoint description endpoint health checks endpoint labels endpoint metadata endpoint resource management endpoint traffic allocation endpoint update endpoint version management error metrics latency metrics multi-model deployment prediction logging public endpoints request/response logging scaling policies |
https://www.w3.org/2000/01/rdf-schema#label |
Vertex AI Endpoints
|
gptkbp:integratesWith |
gptkb:Vertex_AI_Model_Registry
gptkb:Vertex_AI_Pipelines gptkb:Vertex_AI_Workbench |
gptkbp:partOf |
gptkb:Vertex_AI
|
gptkbp:provides |
gptkb:Google_Cloud_Platform
|
gptkbp:supports |
gptkb:REST_API
gptkb:gRPC_API versioning auto-scaling traffic splitting custom containers pre-built containers |
gptkbp:usedFor |
serving machine learning models
|
gptkbp:bfsParent |
gptkb:Vertex_AI
|
gptkbp:bfsLayer |
5
|