Run 01a016ae · KernelIndex

Primary measurement

9.25msmedian

Rank 1 in its comparison group · source-native comparison · observed 2024-09-03

ms 20 9.252832412719727 · ms 50 9.252832412719727 · ms 80 9.252832412719727

Identity

implementationTransformers

projectHugging Face Transformers

revisionunknown

workloadseq = 2048 · batch = 4 · hidden = 4096 · intermediate = 11008 · bf16

comparison keysha256:6286ce863c7daf84…

sourceLiger-Kernel benchmarks

external idswiglu/forward/huggingface/nvidia-a100-sxm4-80gb/batch4-hidden4096-intermediate11008-seq2048-bf16/2024-09-03-15-40-28

sha256:cc5ad504213b441b4b5fa04…

Correctness

Marked passed by the source; the correctness policy was not published.

Workload

seq2048

batch4

hidden4096

intermediate11008

xbf16 [4, 2048, 4096]

w_upbf16 [11008, 4096]

w_downbf16 [4096, 11008]

w_gatebf16 [11008, 4096]

definition comparatornot_asserted

Measurements

latency · median9.25 ms

latency · p209.25 ms

latency · p809.25 ms

Protocol

harnessLiger-Kernel benchmark scripts

timercuda_events

primaryStatisticmedian

comparabilityFamilyliger_kernel_bench

Environment

gpuNVIDIA A100 (sm_80)

Artifacts

No artifacts published with this run.

Replications and notes

No attestations yet.

Community attestations. They never change the evidence level; only a KernelIndex-controlled rerun does.

Add a reproduction or note

Canonical manifest

Show manifest

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 9252832
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2024-09-03T15:40:28.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 9252832,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 9252832,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 9.252832412719727,
          "ms_50": 9.252832412719727,
          "ms_80": 9.252832412719727
        },
        "benchmark": "swiglu/forward",
        "externalId": "swiglu/forward/huggingface/nvidia-a100-sxm4-80gb/batch4-hidden4096-intermediate11008-seq2048-bf16/2024-09-03-15-40-28"
      },
      "protocolDigest": "sha256:a79eaf4df66c97c6adc1fb2d09df78682155d1ea86652ae0b70199875bde7747",
      "workloadDigest": "sha256:22cebf93eb9ca52a9bd49f32f2eb51beb9dc41c28c6b27967449542f51d3b640",
      "environmentDigest": "sha256:90c9e2764222f592477cfccf3373519add5a1b881563956ad058c4f99e41b6b9",
      "implementationDigest": "sha256:70659a76da921ebc2777c752d1b601f56545c50a49056f176d2bf35d29374512"
    },
    "metadata": {
      "name": "liger-swiglu-forward-huggingface-nvidia-a100-sxm4-80gb-batch4-hidden4096-intermediate11008-seq2048-b",
      "title": "SwiGLU MLP · huggingface · 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"
  }
}

Cite this record (permalink, digest, access date)

Report an issue with this run

Published 2026-08-18 · Liger-Kernel benchmarks · BSD-2-ClauseAll results for SwiGLU MLP →JSON