Liger

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 532416
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2024-09-03T15:31:39.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 529101,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 534765,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 0.5291008353233337,
          "ms_50": 0.5324159860610962,
          "ms_80": 0.53476482629776
        },
        "benchmark": "cross_entropy/forward",
        "externalId": "cross_entropy/forward/liger/nvidia-a100-sxm4-80gb/tokens16384-vocab4096-fp32/2024-09-03-15-31-39"
      },
      "protocolDigest": "sha256:a79eaf4df66c97c6adc1fb2d09df78682155d1ea86652ae0b70199875bde7747",
      "workloadDigest": "sha256:df069011a833333c75db108c9ab4f5218a0504fc94981ec3a1241be70443d1f1",
      "environmentDigest": "sha256:90c9e2764222f592477cfccf3373519add5a1b881563956ad058c4f99e41b6b9",
      "implementationDigest": "sha256:f703c6ddb6c1893842a45a539fe1ac9858c062af9f59c74a32f5d1aa4aa4e707"
    },
    "metadata": {
      "name": "liger-cross-entropy-forward-liger-nvidia-a100-sxm4-80gb-tokens16384-vocab4096-fp32-2024-09-03-15-31-",
      "title": "Cross-entropy loss · liger · forward",
      "labels": {
        "liger_version": "0.2.1"
      }
    },
    "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 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"
  }
}