Liger fused

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 211680
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2026-04-07T21:27:44.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 210720,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 212736,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 0.2107200026512146,
          "ms_50": 0.21167999505996704,
          "ms_80": 0.21273599565029144
        },
        "benchmark": "fused_add_rms_norm/backward",
        "externalId": "fused_add_rms_norm/backward/liger_rms_norm/nvidia-h100-80gb-hbm3/hidden4096-rows2048-fp32/2026-04-07-21-27-44"
      },
      "protocolDigest": "sha256:080e6e66e4ec75a131aa0c9121c74b8e8eed64e7b6d621d567c6a28f79548be8",
      "workloadDigest": "sha256:d480d00c99a1adff0dacb94d52af9bc3daa6b9850d16c1f466b51f4807d4b33b",
      "environmentDigest": "sha256:2750ae381d6de582f1eb6b9008e0987463d19ede8af127d97d76c5ae09121393",
      "implementationDigest": "sha256:9b417b271806017a7e78c087a31c17a4633f00e5df9c8b3c227d337c5aea8505"
    },
    "metadata": {
      "name": "liger-fused-add-rms-norm-backward-liger-rms-norm-nvidia-h100-80gb-hbm3-hidden4096-rows2048-fp32-2026",
      "title": "Fused add + RMSNorm · liger_rms_norm · 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"
  }
}