File size: 935 Bytes
aa3ac98 81fff32 aa3ac98 f2afc26 aa3ac98 81fff32 aa3ac98 05bebc1 f2afc26 aa3ac98 f2afc26 aa3ac98 f2afc26 aa3ac98 05bebc1 f2afc26 05bebc1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 |
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "numpy",
# "torch==2.8.0",
# "kernels-benchmark-tools",
# "kernels",
# ]
#
# [tool.uv.sources]
# kernels-benchmark-tools = { path = "../../../../../tools", editable = true }
# ///
import torch
import sys
from kernels_benchmark_tools import KernelTypeEnum, run_benchmark
from kernels import get_kernel
# Load the activation kernel
activation = get_kernel("kernels-community/activation")
def hf_kernels_swiglu(input_tensor):
hidden_dim = input_tensor.shape[-1] // 2
out_shape = input_tensor.shape[:-1] + (hidden_dim,)
out = torch.empty(out_shape, dtype=input_tensor.dtype, device=input_tensor.device)
return activation.silu_and_mul(out, input_tensor)
run_benchmark(
kernel_type=KernelTypeEnum.ACTIVATION,
impl_name="hf_kernels_swiglu",
impl_tags={"family": "hf-kernels", "backend": "cuda"},
impl_func=hf_kernels_swiglu,
) |