domino-model-endpoints

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

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/ToXMon/tolu --skill domino-model-endpoints-toxmon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: domino-model-endpoints
Source: https://github.com/ToXMon/tolu/tree/main/agent-zero-backup/workdir/memory-palace/skills/domino/domino-model-endpoints
Command: npx skills add https://github.com/ToXMon/tolu --skill domino-model-endpoints-toxmon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reduces the complexity of publishing, operating, and debugging production inference APIs on Domino Data Lab by consolidating deployment steps, monitoring guidance, and troubleshooting practices into a single, actionable reference.

Core Features & Use Cases

  • Publish Prediction Endpoints: Guidance to create model functions, register models, and publish REST prediction endpoints via Domino UI or API.
  • Monitoring & Alerting: Instructions to access Domino's Grafana dashboards, key Prometheus queries for latency and error rates, and example alert rules for error rate and high latency.
  • Scaling & GPU Inference: Recommendations for replica autoscaling, resource sizing, and NVIDIA Triton integration for high-performance GPU inference.
  • Use Case: MLOps engineers deploying a classification model can publish a model API, validate performance with Grafana, configure alerts for P99 latency, and perform blue/green version rollouts.

Quick Start

Deploy a Domino model API named my-classifier from model.py using the predict function and ensure the default environment includes uwsgi.

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 a model API on Domino Data Lab?

To deploy a model API on Domino Data Lab, create a model function, register the model, and publish the REST prediction endpoint via the Domino UI or API. Ensure your default compute environment includes uwsgi installed.

How do I monitor model endpoints and configure latency alerts in Grafana?

Monitor model endpoints by accessing Domino's Grafana dashboards and using key Prometheus queries for latency and error rates. You can configure example alert rules to trigger notifications for high error rates or P99 latency spikes.

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

Yes, you can integrate NVIDIA Triton with Domino model endpoints to optimize high-performance GPU inference. The setup provides recommendations for replica autoscaling and resource sizing alongside Triton integration.

Do I need uwsgi installed to publish prediction endpoints on Domino?

Yes, you need uwsgi installed in your default compute environment to publish and operate prediction endpoints on Domino. This prerequisite supports both synchronous and asynchronous request patterns with API token authentication.

What is the best way to manage model versions and perform rollouts in MLOps?

The best way to manage model versions in MLOps involves using Domino's model publish APIs to perform blue/green version rollouts. This allows you to validate prediction endpoint performance with Grafana before shifting traffic.