All Products
Search
Document Center

Hologres:AI resource metrics

Last Updated:Mar 26, 2026

Monitor AI nodes (GPU) and AI model services in Hologres using these metrics. Track resource usage, invocation volume, and latency, and configure alerting based on the data.

Metric categories

Two categories of metrics are available:

  • AI Resource Metrics — Monitor overall AI node usage.

  • AI Model Metrics — Monitor resource usage and invocation statistics per deployed model. Use these metrics to evaluate whether each model is using its allocated resources efficiently.

For information about deploying models, see AI Models and Deployment.

AI Resource metrics

Supported instance types: General-purpose, Compute group type, and Primary/standby instance.

Data appears in this category only after you purchase AI resources and start using them. See AI Resource Pricing and Purchase for details.
MetricDescription
AI Resource Group CPU UsageTotal CPU usage of the AI node
AI Resource Group Memory UsageTotal memory usage of the AI node
AI Resource Group GPU UsageTotal GPU usage of the AI node

AI Model metrics

Data appears in this category only after you deploy a model and invoke it through AI Function. See AI Models and Deployment for deployment details and AI Function for invocation details.

Resource usage

These metrics show how much of the AI node's resources a specific model consumes.

MetricDescription
AI Model Service CPU UsageCPU usage for this model
AI Model Service Memory UsageMemory usage for this model
AI Model Service GPU UsageGPU usage for this model

Invocation statistics

These metrics show the volume, success rate, latency, and traffic of invocations through AI Function for a specific model.

MetricDescription
AI Model Service Invocation QPSQPS of model invocations through AI Function
AI Model Service Successful Invocation QPSSuccessful QPS of model invocations through AI Function
AI Model Service Failed Invocation QPSFailed QPS of model invocations through AI Function
AI Model Service Average Response TimeAverage latency of model invocations through AI Function
AI Model Service Maximum Response TimeMaximum latency of model invocations through AI Function
AI Model Service Inbound TrafficInbound traffic from model invocations through AI Function
AI Model Service Outbound TrafficOutbound traffic from model invocations through AI Function