torch.compile (inductor)
MobileNetV1 · width = 224 · height = 224 · batch_size = 10 · input_channels = 3 · fp32 · run 01a03f0e-f6ef…
●passedReported evidence
Not re-observed recently.
Primary measurement
1.81ms±0.01 · mean of 100
Rank 2 in its comparison group · source-native comparison · observed 2026-03-05
max ms 2.34 · min ms 1.77 · std ms 0.0576 · mean ms 1.81
Identity
implementationtorch.compile (inductor)
projectPyTorch
revisionunknown
workloadwidth = 224 · height = 224 · batch_size = 10 · input_channels = 3 · fp32
comparison keysha256:00d9bc30518d1a33…
sourceKernelBench baseline timings
external idH100_Modal/torch-compile-inductor/level3/19_MobileNetV1.py
sha256:05930e7b5210c1d21f220bc…
Correctness
Marked passed by the source; the correctness policy was not published.
Workload
width224
height224
batch_size10
input_channels3
input_1fp32 [10, 3, 224, 224]
definition comparatornot_asserted
Measurements
latency · max2.34 ms · n=100
latency · mean1.81 ms · n=100
latency · min1.77 ms · n=100
latency · std57.6 µs
Protocol
harnessKernelBench timing scripts
timercuda_events
primaryStatisticmean
comparabilityFamilykernelbench_baseline_timing
Environment
gpuNVIDIA H100 (sm_90)
Artifacts
No artifacts published with this run.
Replications and notes
No attestations yet.
Community attestations. They never change the evidence level; only a KernelIndex-controlled rerun does.
Add a reproduction or note
Canonical manifest
Show manifestHide manifest
{
"run": {
"kind": "BenchmarkRun",
"spec": {
"status": "passed",
"timing": {
"samples": 100,
"latencyNs": {
"mean": 1810000,
"maximum": 2340000,
"minimum": 1770000,
"confidence95": [
1798710,
1821290
]
},
"primaryStatistic": "mean"
},
"observedAt": "2026-03-05T08:38:15.000Z",
"measurements": [
{
"unit": "ns",
"value": 57600,
"metric": "latency",
"statistic": "std"
}
],
"sourceNative": {
"source": "kernelbench",
"metrics": {
"max_ms": 2.34,
"min_ms": 1.77,
"std_ms": 0.0576,
"mean_ms": 1.81
},
"benchmark": "H100_Modal/baseline_time_torch_compile_inductor_default.json",
"externalId": "H100_Modal/torch-compile-inductor/level3/19_MobileNetV1.py"
},
"protocolDigest": "sha256:547725b033a9911eae0c5ac362344a85aed824894ed4ab476af945b9bb491ea6",
"workloadDigest": "sha256:00996d9be006d45ff397db32ee5299c5fc946a80d8168f53bbb7015a6ac62b45",
"environmentDigest": "sha256:2750ae381d6de582f1eb6b9008e0987463d19ede8af127d97d76c5ae09121393",
"implementationDigest": "sha256:70ea2f7bc18e53af8b4fe96b1ef8c694d864308a3fc0362d553c0507ed0f3fe2"
},
"metadata": {
"name": "kernelbench-h100-modal-torch-compile-inductor-l3-19-mobilenetv1",
"title": "MobileNetV1 · torch.compile (inductor) · Modal"
},
"apiVersion": "kernelindex.dev/v1alpha1"
},
"protocol": {
"kind": "BenchmarkProtocol",
"spec": {
"harness": {
"name": "KernelBench timing scripts",
"repository": "https://github.com/ScalingIntelligence/KernelBench"
},
"measurement": {
"timer": "cuda_events",
"primaryStatistic": "mean"
},
"comparability": {
"notes": "Mean of 100 timed forward passes (CUDA events, warm-up excluded) of the reference module on fixed inputs; the 95% interval is the mean's, from the reported standard deviation. The upstream JSON records no torch or CUDA version. Comparable only within one problem and one timing host.",
"family": "kernelbench_baseline_timing"
}
},
"metadata": {
"name": "kernelbench-timing-v1",
"title": "KernelBench baseline timing"
},
"apiVersion": "kernelindex.dev/v1alpha1"
},
"environment": {
"kind": "ExecutionEnvironment",
"spec": {
"hardware": {
"vendor": "nvidia",
"product": "NVIDIA H100",
"formFactor": "80GB HBM3",
"architecture": "sm_90"
},
"software": {}
},
"metadata": {
"name": "kernelbench-h100-modal",
"title": "KernelBench host · H100 80GB HBM3 (Modal)"
},
"apiVersion": "kernelindex.dev/v1alpha1"
}
}Cite this record (permalink, digest, access date)
Report an issue with this run
Published 2026-08-26 · KernelBench baseline timings · MITAll results for MobileNetV1 →JSON