Developer Guide

Use these pages when contributing to NVIDIA cuVS or working on integrations that need to follow NVIDIA cuVS development conventions.

Coding Guidelines

Coding Guidelines: find language-specific conventions for C, C++, Java, and Python development.
C Guidelines: follow NVIDIA cuVS C API design, ABI-stable handle ownership, and lifecycle conventions.
C++ Guidelines: follow NVIDIA cuVS C++ API design, resource-management, and implementation conventions.
Java Guidelines: follow NVIDIA cuVS Java API design, native binding, packaging, and resource-management conventions.
Python Guidelines: follow NVIDIA cuVS Python API, packaging, and binding conventions.

ABI Stability: understand ABI expectations for developer-facing APIs and downstream integrations.
Link-time Optimization: use JIT LTO for CUDA compilation and linking workflows.

Contributing: learn how to set up a development environment, submit changes, and work with the project.

Use these pages when contributing to NVIDIA cuVS or working on integrations that need to follow NVIDIA cuVS development conventions.

Coding Guidelines: find language-specific conventions for C, C++, Java, and Python development.
C Guidelines: follow NVIDIA cuVS C API design, ABI-stable handle ownership, and lifecycle conventions.
C++ Guidelines: follow NVIDIA cuVS C++ API design, resource-management, and implementation conventions.
Java Guidelines: follow NVIDIA cuVS Java API design, native binding, packaging, and resource-management conventions.
Python Guidelines: follow NVIDIA cuVS Python API, packaging, and binding conventions.

ABI Stability: understand ABI expectations for developer-facing APIs and downstream integrations.
Link-time Optimization: use JIT LTO for CUDA compilation and linking workflows.

Contributing: learn how to set up a development environment, submit changes, and work with the project.