databricks-model-serving

Name: databricks-model-serving
Availability: InStock
Author: Databricks

Manage Databricks Model Serving endpoints via CLI for LLMs and custom models.

13|13|Updated Mar 12, 2026

Search Tags:#deployment #cli #llm #endpoint #serving #databricks #model-serving

Ready to run

npx skills add https://github.com/databricks/devhub --skill databricks-model-serving-databricks

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: databricks-model-serving
Source: https://github.com/databricks/devhub/tree/main/examples/saas-tracker/template/.agents/skills/databricks-model-serving
Command: npx skills add https://github.com/databricks/devhub --skill databricks-model-serving-databricks

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Simplifies managing and configuring Databricks Model Serving endpoints from the command line, reducing manual setup and configuration errors.

Core Features & Use Cases

Create, configure, query, and monitor model-serving endpoints for LLMs, custom models, and external models.
Manage endpoint state, traffic, and scaling to support reliable production serving.
Use cases include rapid development, A/B testing, and seamless integration with Databricks Apps and asset bundles.

Quick Start

Create a new serving endpoint for your workspace using the databricks-model-serving CLI and verify its READY state with a get call.

Frequently Asked Questions about databricks-model-serving

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

FAQPage Schema

How do I create and query Databricks Model Serving endpoints from the CLI?▼

Manage Databricks Model Serving endpoints by executing CLI commands to create new endpoints for your workspace and verifying their READY state using a get call. This enforces CLI-based workflows with proper workspace authentication for scalable deployment.

Can I manage traffic and scaling for LLM endpoints using the Databricks CLI?▼

Yes, you can manage endpoint state, traffic distribution, and scaling configurations for LLM endpoints directly via the Databricks CLI. This enables reliable production serving and supports A/B testing across development and production environments.

What is the best way to automate model deployment for Databricks Apps and asset bundles?▼

Automating model deployment for Databricks Apps and asset bundles is best achieved through CLI-based workflows that configure and monitor model-serving endpoints. This seamlessly integrates custom and external models into your scalable deployment pipeline.

Does Databricks Model Serving support external models and custom models via the command line?▼

Yes, Databricks Model Serving supports creating, configuring, and querying endpoints for both external models and custom models via the command line. This enables unified endpoint management across different model types within your development and production environments.

Do I need explicit workspace authentication to automate Databricks endpoint configuration?▼

Yes, proper workspace authentication is required to automate Databricks endpoint configuration via the CLI. This enforces secure CLI-based workflows required for creating, querying, and monitoring model-serving endpoints across environments.