ServerStatuszScaffoldingActionsBackendsReport CardServerRPCRequestz: request statusRpcz: statisticsTracez: distributed tracingRuntimeInspectz: generic informationStreamzVarzProcessHeapz: download heap usageProfilez: download profiling informationThreadz: backtracesEnvironmentFlagz: flag valuesProcz: process attributes
aiplatform-dataplane-prediction on yudfwra-ak8

StubbyBackend LargeVisionModelAsyncService

StatusOK
Proto Service Namecloud.ai.large_models.vision.LargeVisionModelAsyncService
Stub Service NameLargeVisionModelAsyncService
Toolsrequestz

Configuration

Configured with the following CanonicalStubConfiguration proto (bypassing Cornea):

server_name: "LargeVisionModelAsyncService" smart_service { target: "cloud.ai.large_models.vision.largevisionmodelasyncservice-staging" client_channel_options { start_reachable: false backend_subset: false subset_size: 0 channel_type: BNS_CHANNEL } wait_sec: 0 }

See /stubz for Extensible Stubs run-time information.