Liger

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 410240
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2024-09-03T15:40:08.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 408710,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 411904,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 0.40871042013168335,
          "ms_50": 0.4102399945259094,
          "ms_80": 0.4119040071964264
        },
        "benchmark": "rope/backward",
        "externalId": "rope/backward/liger/nvidia-a100-sxm4-80gb/hidden8192-kv_heads8-q_heads32-seq16384-bf16/2024-09-03-15-40-08"
      },
      "protocolDigest": "sha256:080e6e66e4ec75a131aa0c9121c74b8e8eed64e7b6d621d567c6a28f79548be8",
      "workloadDigest": "sha256:8b228683a228b8af40407bd899af1c29de9d7d67eab76eed00cf5286e62800d4",
      "environmentDigest": "sha256:90c9e2764222f592477cfccf3373519add5a1b881563956ad058c4f99e41b6b9",
      "implementationDigest": "sha256:51eb16de033f2219f67b768ae0f8b919b4f1af7bd11ee0c19e51fe8df440fa54"
    },
    "metadata": {
      "name": "liger-rope-backward-liger-nvidia-a100-sxm4-80gb-hidden8192-kv-heads8-q-heads32-seq16384-bf16-2024-09",
      "title": "Rotary position embedding · liger · backward",
      "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 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 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"
  }
}