README example from https://github.com/huggingface/kernels

activation-kernel.py

# /// script
# dependencies = [
#  "numpy",
#  "torch",
#  "kernels",
# ]
# ///

import torch

from kernels import get_kernel

# Download optimized kernels from the Hugging Face hub
activation = get_kernel("kernels-community/activation")

# Random tensor
x = torch.randn((10, 10), dtype=torch.float16, device="cuda")

# Run the kernel
y = torch.empty_like(x)
activation.gelu_fast(y, x)

print(y)