submission 66578
albert9823 · python · License unknown
Use it
Vendorable · source mirrored · license unknownView source →
No package. Vendor the mirrored source: 19 lines, June 9 Researcher Reciprocity License v1.0.
submission.py
curl "https://kernelindex.com/api/v1/implementations/kernelbot-grayscale-v2-66578?include=source"interfacepython
Compatibility
measured onNVIDIA A100
declared hardwareNVIDIA A100
architecturessm_80
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:b0700222df3b69171d4dfce7cd4e2a9944847c7a528750e53174ce52702719ab
license declaredunknown
license concludedunknown
authorsalbert9823
imported2026-08-15
Kernel source
submission.py19 lines
from task import input_t, output_t
import torch
def custom_kernel(data: input_t) -> output_t:
# Unpack (input_rgb, output_gray)
x, out = data # x: (H, W, 3), out: (H, W)
# Match device & dtype with input
weights = torch.tensor(
[0.2989, 0.5870, 0.1140],
device=x.device,
dtype=x.dtype
)
# Compute grayscale along the channel dim
out[...] = torch.sum(x * weights, dim=-1)
return out
Source code from GPU Mode and the KernelBot dataset · June 9 Researcher Reciprocity License v1.0
Best evidence level for this revision: reported
JSON