Liger

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 2606080
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2025-11-11T06:22:57.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 2605331,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 2607309,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 2.6053311824798584,
          "ms_50": 2.6060800552368164,
          "ms_80": 2.607308864593506
        },
        "benchmark": "tiled_geglu/backward",
        "externalId": "tiled_geglu/backward/liger_tiled/nvidia-geforce-rtx-4090/batch2-hidden2048-intermediate4096-seq1024-bf16/2025-11-11-06-22-57"
      },
      "protocolDigest": "sha256:080e6e66e4ec75a131aa0c9121c74b8e8eed64e7b6d621d567c6a28f79548be8",
      "workloadDigest": "sha256:7477e51bd95bff47821a6d62d904a46ce595577d4de14aaaa025304660c6fed1",
      "environmentDigest": "sha256:e2646efafa5e5fbd428b49a99b1c076c10d51654a549c4e50ec36da7662d4328",
      "implementationDigest": "sha256:273de05b950c7c7353e9e2b0d88f29cab729451b9b3034c01494e1d02bac3c46"
    },
    "metadata": {
      "name": "liger-tiled-geglu-backward-liger-tiled-nvidia-geforce-rtx-4090-batch2-hidden2048-intermediate4096-se",
      "title": "GeGLU MLP (tiled benchmark) · liger_tiled · backward",
      "labels": {
        "liger_version": "0.6.3"
      }
    },
    "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 GeForce RTX 4090",
        "architecture": "sm_89"
      },
      "software": {}
    },
    "metadata": {
      "name": "liger-bench-nvidia-geforce-rtx-4090",
      "title": "Liger benchmark host · GeForce RTX 4090"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  }
}