PyTorch

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 16928
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2026-03-27T06:09:46.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 15616,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 17664,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 0.015615999698638916,
          "ms_50": 0.01692800037562847,
          "ms_80": 0.017664000391960144
        },
        "benchmark": "relu_squared/backward",
        "externalId": "relu_squared/backward/torch/nvidia-h100-80gb-hbm3/hidden128-rows4096-bf16/2026-03-27-06-09-46"
      },
      "protocolDigest": "sha256:080e6e66e4ec75a131aa0c9121c74b8e8eed64e7b6d621d567c6a28f79548be8",
      "workloadDigest": "sha256:ecef57ab0ad62ff36088c4c7c917d1700d0c313720dced61d578dedf2ffbecb9",
      "environmentDigest": "sha256:2750ae381d6de582f1eb6b9008e0987463d19ede8af127d97d76c5ae09121393",
      "implementationDigest": "sha256:ce55d39a62f0f84142e1fb25300736a7880501f42bec3a607a0d6fb5925a1ee6"
    },
    "metadata": {
      "name": "liger-relu-squared-backward-torch-nvidia-h100-80gb-hbm3-hidden128-rows4096-bf16-2026-03-27-06-09-46",
      "title": "ReLU squared · torch · backward",
      "labels": {
        "liger_version": "0.7.0"
      }
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  },
  "protocol": {
    "kind": "BenchmarkProtocol",
    "spec": {
      "harness": {
        "name": "Liger-Kernel benchmark scripts",
        "repository": "https://github.com/linkedin/Liger-Kernel"
      },
      "measurement": {
        "timer": "cuda_events",
        "primaryStatistic": "median"
      },
      "comparability": {
        "notes": "Timed: the backward pass of the module output given a random upstream gradient, via triton.testing.do_bench with quantiles 0.5/0.2/0.8 (median with p20/p80 spread). The upstream CSV records no CUDA, driver, or torch version; the Liger release rides each run's labels. Comparable only within one kernel, workload, timed pass, and GPU.",
        "family": "liger_kernel_bench"
      }
    },
    "metadata": {
      "name": "liger-bench-do-bench-backward",
      "title": "Liger benchmark harness · backward pass"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  },
  "environment": {
    "kind": "ExecutionEnvironment",
    "spec": {
      "hardware": {
        "vendor": "nvidia",
        "product": "NVIDIA H100",
        "formFactor": "80GB HBM3",
        "architecture": "sm_90"
      },
      "software": {}
    },
    "metadata": {
      "name": "liger-bench-nvidia-h100-80gb-hbm3",
      "title": "Liger benchmark host · H100 80GB HBM3"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  }
}