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

# Field Guide

The Field Guide collects practical material for users integrating NVIDIA cuVS into libraries, databases, and production systems, as well as users running NVIDIA cuVS directly in standalone workflows. These pages cover compatibility, integration patterns, runtime compilation, and extension points that are useful once you move beyond the basic API guides.

## Topic Guides

- [Compatibility](/user-guide/field-guide/compatibility): understand NVIDIA cuVS release compatibility, ABI windows, and stable binary boundaries.
- [Integration Patterns](/user-guide/field-guide/integration-patterns): compare direct, offloaded, and service-oriented ways to integrate NVIDIA cuVS into products.
- [JIT Compilation](/user-guide/field-guide/jit-compilation): understand when NVIDIA cuVS triggers just-in-time compilation, how caches behave, and how to warm up JIT-compiled kernels.
- [UDF Usage](/user-guide/field-guide/udf-usage): supply custom CUDA User-Defined-Functions to cuVS APIs