#

reduced-precision

Here is 1 public repository matching this topic...

KernelTuner / kernel_float

CUDA/HIP header-only library to use vector and low-precision floating-point types (16 bit, 8 bit) in GPU code

performance cpp gpu cuda kernel-tuner hip vectorization floating-point half-precision mixed-precision low-precision bfloat16 header-only-library reduced-precision

Updated Dec 2, 2024
C++

Improve this page

Add a description, image, and links to the reduced-precision topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the reduced-precision topic, visit your repo's landing page and select "manage topics."