Transformers

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 245920
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2025-08-07T21:42:21.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 243968,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 248768,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 0.24396799504756927,
          "ms_50": 0.24592000246047974,
          "ms_80": 0.24876800179481506
        },
        "benchmark": "llama4_rope/full",
        "externalId": "llama4_rope/full/huggingface/nvidia-h100-80gb-hbm3/hidden8192-kv_heads8-q_heads32-seq1024-bf16/2025-08-07-21-42-21"
      },
      "protocolDigest": "sha256:5b02ee9a2140fbc6fcc1c89800f6c177ba22718c8897cb532bf0ba91867c1e58",
      "workloadDigest": "sha256:52c061cd6e5592fe55b436aa184e545f8d4f65d4a54f37cc15cd2c94b42d49e2",
      "environmentDigest": "sha256:2750ae381d6de582f1eb6b9008e0987463d19ede8af127d97d76c5ae09121393",
      "implementationDigest": "sha256:cca024409163839a832c1d39bd301f536494b645171665d65fae5faf2717be48"
    },
    "metadata": {
      "name": "liger-llama4-rope-full-huggingface-nvidia-h100-80gb-hbm3-hidden8192-kv-heads8-q-heads32-seq1024-bf16",
      "title": "Llama 4 rotary position embedding · huggingface · full",
      "labels": {
        "liger_version": "0.6.1"
      }
    },
    "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 forward pass plus the backward 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-full",
      "title": "Liger benchmark harness · full 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"
  }
}