Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from http://cloud.google.com/stackdriver/docs/managed-prometheus/exporters/torchserve below:

TorchServe | Google Cloud Observability

Stay organized with collections Save and categorize content based on your preferences.

This document describes how to configure your Google Kubernetes Engine deployment so that you can use Google Cloud Managed Service for Prometheus to collect metrics from TorchServe. This document shows you how to do the following:

• Set up TorchServe to report metrics.
• Configure a PodMonitoring resource for Managed Service for Prometheus to collect the exported metrics.
• Access a dashboard in Cloud Monitoring to view the metrics.

These instructions apply only if you are using managed collection with Managed Service for Prometheus. If you are using self-deployed collection, then see the TorchServe documentation for installation information.

These instructions are provided as an example and are expected to work in most Kubernetes environments. If you are having trouble installing an application or exporter due to restrictive security or organizational policies, then we recommend you consult open-source documentation for support.

For information about TorchServe, see TorchServe. For information about setting up TorchServe on Google Kubernetes Engine, see the GKE guide for TorchServe.

To collect metrics from TorchServe by using Managed Service for Prometheus and managed collection, your deployment must meet the following requirements:

• Your cluster must be running Google Kubernetes Engine version 1.21.4-gke.300 or later.
• You must be running Managed Service for Prometheus with managed collection enabled. For more information, see Get started with managed collection.

TorchServe exposes Prometheus-format metrics automatically when the

flag is specified either in the

file or as an environment variable.

If you are setting up TorchServe yourself, then we recommend making the following additions to your config.properties file.

If you are following the Google Kubernetes Engine document Serve scalable LLMs on GKE with TorchServe, then these additions are part of the default setup.

Also, when deploying this image to GKE, modify your deployment and service YAML to expose the added metrics port:

To verify that TorchServe is emitting metrics on the expected endpoints, do the following:

1. Set up port forwarding by using the following command:

   kubectl -n NAMESPACE_NAME port-forward SERVICE_NAME 8082
   

2. Access the endpoint localhost:8082/metrics by using the browser or the curl utility in another terminal session.

For target discovery, the Managed Service for Prometheus Operator requires a PodMonitoring resource that corresponds to TorchServe in the same namespace.

You can use the following PodMonitoring configuration:

Ensure that the values of the

and

fields match those of the TorchServe pods you want to monitor.

To apply configuration changes from a local file, run the following command:

kubectl apply -n NAMESPACE_NAME -f FILE_NAME

You can also use Terraform to manage your configurations.

You can use Metrics Explorer to verify that you correctly configured TorchServe. It might take one or two minutes for Cloud Monitoring to ingest your metrics.

To verify the metrics are ingested, do the following:

1. In the Google Cloud console, go to the leaderboard Metrics explorer page:

   Go to Metrics explorer

   If you use the search bar to find this page, then select the result whose subheading is Monitoring.

2. In the toolbar of the query-builder pane, select the button whose name is either code MQL or code PromQL.
3. Verify that PromQL is selected in the Language toggle. The language toggle is in the same toolbar that lets you format your query.
4. Enter and run the following query:
   

   up{job="torchserve", cluster="CLUSTER_NAME", namespace="NAMESPACE_NAME"}

The Cloud Monitoring integration includes the TorchServe Prometheus Overview dashboard. Dashboards are automatically installed when you configure the integration. You can also view static previews of dashboards without installing the integration.

To view an installed dashboard, do the following:

1. In the Google Cloud console, go to the  Dashboards page:

   Go to Dashboards

   If you use the search bar to find this page, then select the result whose subheading is Monitoring.

2. Select the Dashboard List tab.
3. Choose the Integrations category.
4. Click the name of the dashboard, for example, TorchServe Prometheus Overview.

To view a static preview of the dashboard, do the following:

1. In the Google Cloud console, go to the  Integrations page:

   Go to Integrations

   If you use the search bar to find this page, then select the result whose subheading is Monitoring.

2. Click the Kubernetes Engine deployment-platform filter.
3. Locate the TorchServe integration and click View Details.
4. Select the Dashboards tab.

For information about troubleshooting metric ingestion problems, see Problems with collection from exporters in Troubleshooting ingestion-side problems.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-08-11 UTC.

[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-11 UTC."],[],[]]

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4