PyTorch eager

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "samples": 100,
        "latencyNs": {
          "mean": 8280000,
          "maximum": 8900000,
          "minimum": 7900000,
          "confidence95": [
            8243348,
            8316652
          ]
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2026-03-05T08:38:15.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 187000,
          "metric": "latency",
          "statistic": "std"
        }
      ],
      "sourceNative": {
        "source": "kernelbench",
        "metrics": {
          "max_ms": 8.9,
          "min_ms": 7.9,
          "std_ms": 0.187,
          "mean_ms": 8.28
        },
        "benchmark": "H100_PCIe_LambdaLabs/baseline_time_torch.json",
        "externalId": "H100_PCIe_LambdaLabs/torch/level2/51_Gemm_Subtract_GlobalAvgPool_LogSumExp_GELU_ResidualAdd.py"
      },
      "protocolDigest": "sha256:547725b033a9911eae0c5ac362344a85aed824894ed4ab476af945b9bb491ea6",
      "workloadDigest": "sha256:0edfac16d56e826b56b269f78eee5dc5116bcc41090fef4f52eaf4c54d61f3eb",
      "environmentDigest": "sha256:89f9b28b06758f22a1df331fea58bfde2c9cc0f3627d1829509743ea538f0011",
      "implementationDigest": "sha256:c756a040239c7e84f56635bc840a36e0329053f9ddfef9a5c2a331728cb7465f"
    },
    "metadata": {
      "name": "kernelbench-h100-pcie-lambdalabs-torch-l2-51-gemm-subtract-globalavgpool-logsumexp-gelu-residualadd",
      "title": "Gemm Subtract GlobalAvgPool LogSumExp GELU ResidualAdd · PyTorch eager · Lambda Labs"
    },
    "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": "PCIe",
        "architecture": "sm_90"
      },
      "software": {}
    },
    "metadata": {
      "name": "kernelbench-h100-pcie-lambdalabs",
      "title": "KernelBench host · H100 PCIe (Lambda Labs)"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  }
}