Transformers

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 37972031
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2024-11-22T17:44:34.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 37954601,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 37989464,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 37.9546012878418,
          "ms_50": 37.97203063964844,
          "ms_80": 37.989463806152344
        },
        "benchmark": "fused_linear_cross_entropy/forward",
        "externalId": "fused_linear_cross_entropy/forward/huggingface/nvidia-a100-sxm4-80gb/hidden4096-tokens8192-vocab128256-bf16/2024-11-22-17-44-34"
      },
      "protocolDigest": "sha256:a79eaf4df66c97c6adc1fb2d09df78682155d1ea86652ae0b70199875bde7747",
      "workloadDigest": "sha256:d2bea62b8f405198b5437ebe64f054715f3628f51858e398f5c957bce6953841",
      "environmentDigest": "sha256:90c9e2764222f592477cfccf3373519add5a1b881563956ad058c4f99e41b6b9",
      "implementationDigest": "sha256:45096ed5d8a02d4239615c0c5778b4b48ba152f733b71e43fe37a51abcaa1e31"
    },
    "metadata": {
      "name": "liger-fused-linear-cross-entropy-forward-huggingface-nvidia-a100-sxm4-80gb-hidden4096-tokens8192-voc",
      "title": "Fused linear + cross-entropy · huggingface · forward",
      "labels": {
        "liger_version": "0.4.2"
      }
    },
    "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 A100",
        "formFactor": "SXM4-80GB",
        "architecture": "sm_80"
      },
      "software": {}
    },
    "metadata": {
      "name": "liger-bench-nvidia-a100-sxm4-80gb",
      "title": "Liger benchmark host · A100-SXM4-80GB"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  }
}