torch.compile (inductor)
PyTorch · python · MIT
Use it
Vendorable · source mirrored · MITView source →
No package. Vendor the mirrored source: 28 lines, MIT.
63_Gemm_ReLU_Divide.py
curl "https://kernelindex.com/api/v1/implementations/kernelbench-l2-63-gemm-relu-divide-torch-compile-inductor?include=source"interfacepython · torch_compile_inductor
symbolModel.forward
Compatibility
measured onNVIDIA H100
declared hardwaredeclared only
architectures—
dtypes
Benchmark evidence
2 measurements across 1 GPU, fastest first.
Operation / workload
Hardware
Latency
Rank
Observed
Reported · How evidence levels are derived →
Source and license
sourceavailable
revision digestsha256:86be0045496fe8f43d33122ae76d4d690c15a28fc7a9c8038e90557fc5bbe8c0
license declaredMIT
license concludedMIT
imported2026-08-26
Kernel source
63_Gemm_ReLU_Divide.py28 lines
import torch
import torch.nn as nn
class Model(nn.Module):
"""
Simple model that performs a matrix multiplication, applies ReLU, and divides by a constant.
"""
def __init__(self, in_features, out_features, divisor):
super(Model, self).__init__()
self.linear = nn.Linear(in_features, out_features)
self.divisor = divisor
def forward(self, x):
x = self.linear(x)
x = torch.relu(x)
x = x / self.divisor
return x
batch_size = 1024
in_features = 8192
out_features = 8192
divisor = 2.0
def get_inputs():
return [torch.rand(batch_size, in_features)]
def get_init_inputs():
return [in_features, out_features, divisor]Source code from KernelBench, © 2023 Anne Ouyang, Simon Guo, Azalia Mirhoseini (Scaling Intelligence Lab, Stanford University), MIT License · MIT
Best evidence level for this revision: reported
JSON