skills.rest
jvdomino
jvdominoCOMMUNITY
Explore all skills by this author →
GitHub

domino-model-endpoints

Deploy and monitor model endpoints in Domino with Grafana and NVIDIA Triton support.

Updated Aug 23, 2026
Search Tags:#monitoring#deployment#api#grafana#triton#model-endpoints#uwsgi
One-click install
npx skills add https://github.com/jvdomino/domino-data-lab-plugin --skill domino-model-endpoints
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: domino-model-endpoints
Source: https://github.com/jvdomino/domino-data-lab-plugin/tree/main/skills/model-endpoints
Command: npx skills add https://github.com/jvdomino/domino-data-lab-plugin --skill domino-model-endpoints

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deploy and monitor model endpoints in Domino.

Core Features & Use Cases

  • Create, deploy, and version model endpoints
  • Monitor latency, errors, and resource usage with Grafana dashboards
  • Use GPU inference with NVIDIA Triton and auto-scaling to handle traffic surges
  • Debug and diagnose endpoint issues in production environments

Quick Start

Publish a new model endpoint by providing a model.py with a predict function and clicking Publish in the Domino UI.

Frequently Asked Questions about domino-model-endpoints

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy and monitor model endpoints in Domino?▼

To deploy and monitor Domino model endpoints, you publish a model.py file with a predict function via the Domino UI, then track latency, errors, and resource usage using integrated Grafana dashboards.

Can I use NVIDIA Triton for GPU inference with Domino model endpoints?▼

Yes, Domino model endpoints support GPU inference using NVIDIA Triton, allowing you to accelerate predictions and utilize auto-scaling to handle traffic surges in production environments.

Do I need uwsgi in my environment to publish a Domino model endpoint?▼

Yes, deploying and monitoring Domino model endpoints requires a default environment configured with uwsgi to properly serve the model API.

How can I monitor API latency and errors for production model endpoints?▼

You can monitor production model endpoints by using built-in Grafana dashboards to visualize API latency, error rates, and resource usage for your deployed Domino models.

What is the best way to debug production issues with deployed model APIs?▼

The best way to debug production model API issues is to use Domino endpoint monitoring alongside Grafana dashboards to diagnose latency, errors, and resource usage anomalies.

Related Skills

Explore More Software Engineering Skills→
ToXMonToXMon

domino-model-endpoints

Deploys and monitors model API endpoints on Domino Data Lab via REST and Grafana dashboards.

Community
Advanced
Proxy2021Proxy2021
5

api_monitor

Aggregate endpoint metrics, latency, and alert status to monitor API health.

Community
Advanced
dominodatalabdominodatalab
6

domino-model-endpoints

Deploy, monitor, and scale ML models as API endpoints in Domino Data Lab.

Official
Advanced
belokonmbelokonm
8

machine-learning-engineer

Deploy ML models to production with infrastructure-as-code templates and monitoring.

Community
Advanced