Transformers

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 1315872
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2026-02-28T00:23:31.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 1315744,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 1317760,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 1.3157440423965454,
          "ms_50": 1.3158719539642334,
          "ms_80": 1.3177599906921387
        },
        "benchmark": "group_norm/backward",
        "externalId": "group_norm/backward/huggingface/nvidia-b200/batch128-channels2048-channels_per_group4-hidden512-fp32/2026-02-28-00-23-31"
      },
      "protocolDigest": "sha256:080e6e66e4ec75a131aa0c9121c74b8e8eed64e7b6d621d567c6a28f79548be8",
      "workloadDigest": "sha256:b199535cdbfa3a661538e2514efb3cf390710301cfdd131cc994618f41c6c21b",
      "environmentDigest": "sha256:ad459e643ef802f7008f1fa8915785c905d05abbfdb5eb0328be214f8d9f3a8b",
      "implementationDigest": "sha256:e8c7d555b6002524eb04f3e8a91c03603172925143b51877f4050be074e9e025"
    },
    "metadata": {
      "name": "liger-group-norm-backward-huggingface-nvidia-b200-batch128-channels2048-channels-per-group4-hidden51",
      "title": "GroupNorm · huggingface · 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 B200",
        "architecture": "sm_100"
      },
      "software": {}
    },
    "metadata": {
      "name": "liger-bench-nvidia-b200",
      "title": "Liger benchmark host · B200"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  }
}