NVIDIA NIM for Vision Language Models (VLMs)

User Guide

• Overview
• Release Notes
• Getting Started
• Sampling Control
• Configuring a NIM
• Support Matrix
• Performance
• API Reference
• Observability
• Utilities
• Model Profiles
• KV Cache Reuse (a.k.a. prefix caching)
• Structured Generation
• Deploying with Helm

Examples

• Llama 3.2 Vision
• nemoretriever-parse

Notices

• Acknowledgements
• EULA