Run 01a016ad · KernelIndex

Primary measurement

18.5msmedian

Rank 2 in its comparison group · source-native comparison · observed 2024-09-03

Compare with #1 →

ms 20 18.521728515625 · ms 50 18.521728515625 · ms 80 18.521728515625

Identity

implementationTransformers

projectHugging Face Transformers

revisionunknown

workloadseq = 1024 · batch = 8 · hidden = 4096 · intermediate = 11008 · bf16

comparison keysha256:627c1f2a1d7ec231…

sourceLiger-Kernel benchmarks

external idgeglu/backward/huggingface/nvidia-a100-sxm4-80gb/batch8-hidden4096-intermediate11008-seq1024-bf16/2024-09-03-15-38-42

sha256:e5d02a1a38f24e2e8e249e6…

Correctness

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

Workload

seq1024

batch8

hidden4096

intermediate11008

xbf16 [8, 1024, 4096]

w_upbf16 [11008, 4096]

w_downbf16 [4096, 11008]

w_gatebf16 [11008, 4096]

definition comparatornot_asserted

Measurements

latency · median18.5 ms

latency · p2018.5 ms

latency · p8018.5 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": 18521729
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2024-09-03T15:38:42.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 18521729,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 18521729,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 18.521728515625,
          "ms_50": 18.521728515625,
          "ms_80": 18.521728515625
        },
        "benchmark": "geglu/backward",
        "externalId": "geglu/backward/huggingface/nvidia-a100-sxm4-80gb/batch8-hidden4096-intermediate11008-seq1024-bf16/2024-09-03-15-38-42"
      },
      "protocolDigest": "sha256:080e6e66e4ec75a131aa0c9121c74b8e8eed64e7b6d621d567c6a28f79548be8",
      "workloadDigest": "sha256:b2a90871d1d2b4ede81c3530fd5851ec95bfff5d0586b7838cd15683c248c008",
      "environmentDigest": "sha256:90c9e2764222f592477cfccf3373519add5a1b881563956ad058c4f99e41b6b9",
      "implementationDigest": "sha256:d12c674a0643ab8fef38f7997fd47abbc4f9018f1da04629789cd5fd11fad7b4"
    },
    "metadata": {
      "name": "liger-geglu-backward-huggingface-nvidia-a100-sxm4-80gb-batch8-hidden4096-intermediate11008-seq1024-b",
      "title": "GeGLU MLP · huggingface · 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"
  }
}

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 GeGLU MLP →JSON