PyTorch

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 149280
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2026-06-10T21:03:38.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 148768,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 149888,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 0.14876799285411835,
          "ms_50": 0.14927999675273895,
          "ms_80": 0.14988799393177032
        },
        "benchmark": "megatron_rms_norm/forward",
        "externalId": "megatron_rms_norm/forward/megatron/nvidia-h100-80gb-hbm3/batch1-hidden16384-seq4096-bf16/2026-06-10-21-03-38"
      },
      "protocolDigest": "sha256:a79eaf4df66c97c6adc1fb2d09df78682155d1ea86652ae0b70199875bde7747",
      "workloadDigest": "sha256:cba362ef8ceca886494f4e3a3bffa7273290d7cf26b2c03033b3efacba3a315f",
      "environmentDigest": "sha256:2750ae381d6de582f1eb6b9008e0987463d19ede8af127d97d76c5ae09121393",
      "implementationDigest": "sha256:07486a893d05b3338eb1876548053826c12ab08c8afa12bcc829975f75e540c2"
    },
    "metadata": {
      "name": "liger-megatron-rms-norm-forward-megatron-nvidia-h100-80gb-hbm3-batch1-hidden16384-seq4096-bf16-2026-",
      "title": "RMSNorm, Megatron layout · megatron · forward",
      "labels": {
        "liger_version": "0.8.0"
      }
    },
    "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 module forward pass, 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-forward",
      "title": "Liger benchmark harness · forward 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"
  }
}