PyTorch

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 719872
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2025-04-28T04:46:11.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 716800,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 726016,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 0.7167999744415283,
          "ms_50": 0.719871997833252,
          "ms_80": 0.7260159850120544
        },
        "benchmark": "multi_token_attention/forward",
        "externalId": "multi_token_attention/forward/torch/nvidia-geforce-rtx-3090/batch2-heads_in4-heads_out4-k3-seq1024-bf16/2025-04-28-04-46-11"
      },
      "protocolDigest": "sha256:a79eaf4df66c97c6adc1fb2d09df78682155d1ea86652ae0b70199875bde7747",
      "workloadDigest": "sha256:95c56ccd8ab844776371ebadf2826eae823473667906a8b56f00a458432cc14d",
      "environmentDigest": "sha256:b12fdfab6a337672499b10212a1e986e49e4383777bd7cbb58321b09af4bf6a3",
      "implementationDigest": "sha256:6d4198771fde93bb65a4b8958b54d34a4cf41b41ae68b21aa09bf478b4aa6660"
    },
    "metadata": {
      "name": "liger-multi-token-attention-forward-torch-nvidia-geforce-rtx-3090-batch2-heads-in4-heads-out4-k3-seq",
      "title": "Multi-token attention · torch · forward",
      "labels": {
        "liger_version": "0.1.1"
      }
    },
    "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 GeForce RTX 3090",
        "architecture": "sm_86"
      },
      "software": {}
    },
    "metadata": {
      "name": "liger-bench-nvidia-geforce-rtx-3090",
      "title": "Liger benchmark host · GeForce RTX 3090"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  }
}