submission 186878
literid · python · License unknown
Use it
Vendorable · source mirrored · license unknownView source →
No package. Vendor the mirrored source: 15 lines, June 9 Researcher Reciprocity License v1.0.
pytorch_no_compile.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-vectorsum-v2-186878?include=source"interfacepython
Compatibility
measured onNVIDIA H100
declared hardwareNVIDIA H100
architecturessm_90
dtypesfp32
Benchmark evidence
1 measurement across 1 GPU, fastest first.
Operation / workload
Hardware
Latency
Rank
Observed
Reported · How evidence levels are derived →
Source and license
sourceavailable
revision digestsha256:53da50b8e8c1ac4d4d67754008785fdc2fdc5c761fa0912f383336550bf5f203
license declaredunknown
license concludedunknown
authorsliterid
imported2026-08-15
Kernel source
pytorch_no_compile.py15 lines
import torch
from task import input_t, output_t
def _custom_kernel(data: input_t) -> output_t:
data, output = data
output = data.sum()
return output
# Compile the kernel for better performance
custom_kernel = _custom_kernel
Source code from GPU Mode and the KernelBot dataset · June 9 Researcher Reciprocity License v1.0
Best evidence level for this revision: reported
JSON