Files
nvbench/python
Oleksandr Pavlyk c9f0785aed Replace uses of deprecated typing.Tuple, typing.Callable, etc.
Also use typing.Self to encode that `Benchmark.addInt64Axis` returns
self.
2025-07-28 15:37:04 -05:00
..
2025-07-28 15:37:04 -05:00
2025-07-28 15:37:04 -05:00
2025-07-28 15:37:04 -05:00
2025-07-28 15:37:04 -05:00
2025-07-28 15:37:04 -05:00

CUDA Kernel Benchmarking Package

This package provides Python API to CUDA Kernel Benchmarking Library NVBench.

Building

Build NVBench project

cd nvbench/python
cmake -B nvbench_build --preset nvbench-ci -S $(pwd)/.. -DCMAKE_CUDA_COMPILER=/usr/local/cuda/bin/nvcc -DNVBench_ENABLE_EXAMPLES=OFF -DCMAKE_INSTALL_PREFIX=$(pwd)/nvbench_install
cmake --build nvbench_build/ --config Release --target install

nvbench_DIR=$(pwd)/nvbench_install/lib/cmake CUDACXX=/usr/local/cuda/bin/nvcc pip install -e .

Verify that package works

python test/run_1.py