AI Factory How-To Guides

Use these guides to deploy and operate AI Factory capabilities. When you run in Hybrid Manager (recommended), follow the HM-specific notes in each guide.

Topics

Gen AI

• Configure Data Sources in Gen AI Builder — see Gen AI references in the hub

• Configure the Data Lake in Gen AI Builder — see Gen AI references in the hub

Model Serving

• How-To Deploy an NVIDIA NIM Microservices available on build.nvidia.comcontainer with KServe

• How-To Monitor deployed models with KServe

• How-To Update GPU Resources for an InferenceService

• How-To Configure a ClusterServingRuntime

• Accessing KServe endpoints (internal and external)

Model Library

• How-To Integrate Private Registry with Model Library

• How-To Define Repository Rules for Model Library

• How-To Manage Repository and Image Tag Metadata

• How-To Deploy AI Models from Model Library

Learn more

For conceptual background, see:

• Gen AI Builder Concepts (Assistants, Knowledge, Tools, Threads)

• Model Serving Reference Manual