PyTorch eager

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "samples": 100,
        "latencyNs": {
          "mean": 2590000,
          "maximum": 4000000,
          "minimum": 2570000,
          "confidence95": [
            2570000,
            2617832
          ]
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2026-03-05T08:38:15.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 142000,
          "metric": "latency",
          "statistic": "std"
        }
      ],
      "sourceNative": {
        "source": "kernelbench",
        "metrics": {
          "max_ms": 4,
          "min_ms": 2.57,
          "std_ms": 0.142,
          "mean_ms": 2.59
        },
        "benchmark": "H100_Modal/baseline_time_torch.json",
        "externalId": "H100_Modal/torch/level1/9_Tall_skinny_matrix_multiplication_.py"
      },
      "protocolDigest": "sha256:547725b033a9911eae0c5ac362344a85aed824894ed4ab476af945b9bb491ea6",
      "workloadDigest": "sha256:da79074e772998ebd75fa6199576695f03fdbe89faff6c0188cc07c81184b163",
      "environmentDigest": "sha256:2750ae381d6de582f1eb6b9008e0987463d19ede8af127d97d76c5ae09121393",
      "implementationDigest": "sha256:e56e42b6246545d6d3bd0afd748bf8703ee7b6f47f85eb69cce3c9d300cd5880"
    },
    "metadata": {
      "name": "kernelbench-h100-modal-torch-l1-9-tall-skinny-matrix-multiplication",
      "title": "Tall skinny matrix multiplication · PyTorch eager · 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"
  }
}