> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/dsx/ncp/inference-ra/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/dsx/_mcp/server.

# NVIDIA Inference Reference Architecture

## Docs

- [NVIDIA Inference Reference Architecture](https://docs.nvidia.com/dsx/ncp/inference-ra/home.md): A reference architecture for NVIDIA Cloud Partners building cloud-native AI inference platforms on GPU Kubernetes clusters.