Skip to content
KernelIndex
Search⌘K

Transformers

GeGLU MLP · seq = 8192 · batch = 2 · hidden = 2048 · intermediate = 4096 · bf16 · run 01a0202b-233f…
●passedReported evidence

Not re-observed recently.

Primary measurement
6.09msmedian

Rank 4 in its comparison group · source-native comparison · observed 2025-11-11

Compare with #1 →

ms 20 6.087679862976074 · ms 50 6.087679862976074 · ms 80 6.087679862976074

Identity
implementationTransformers
projectHugging Face Transformers
revisionunknown
workloadseq = 8192 · batch = 2 · hidden = 2048 · intermediate = 4096 · bf16
comparison keysha256:82a5981c5cd3bf2a…
sourceLiger-Kernel benchmarks
external idtiled_geglu/forward/deepspeed_tiled/nvidia-geforce-rtx-4090/batch2-hidden2048-intermediate4096-seq8192-bf16/2025-11-11-06-22-54
sha256:db052b5af601ce0f8bbf5d4…

Correctness

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

Workload

seq8192
batch2
hidden2048
intermediate4096
xbf16 [2, 8192, 2048]
w_upbf16 [4096, 2048]
w_downbf16 [2048, 4096]
w_gatebf16 [4096, 2048]
definition comparatornot_asserted

Measurements

latency · median6.09 ms
latency · p206.09 ms
latency · p806.09 ms

Protocol

harnessLiger-Kernel benchmark scripts
timercuda_events
primaryStatisticmedian
comparabilityFamilyliger_kernel_bench

Environment

gpuNVIDIA GeForce RTX 4090 (sm_89)

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
I

Published under your account name. Community attestations never change the evidence level; a maintainer can hide abuse.

Canonical manifest

Show manifest
{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 6087680
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2025-11-11T06:22:54.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 6087680,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 6087680,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 6.087679862976074,
          "ms_50": 6.087679862976074,
          "ms_80": 6.087679862976074
        },
        "benchmark": "tiled_geglu/forward",
        "externalId": "tiled_geglu/forward/deepspeed_tiled/nvidia-geforce-rtx-4090/batch2-hidden2048-intermediate4096-seq8192-bf16/2025-11-11-06-22-54"
      },
      "protocolDigest": "sha256:a79eaf4df66c97c6adc1fb2d09df78682155d1ea86652ae0b70199875bde7747",
      "workloadDigest": "sha256:ab43ec62d339ccbe92fb35cdcb31012c6453f6853c9c05e9f176a2aec6f31f04",
      "environmentDigest": "sha256:e2646efafa5e5fbd428b49a99b1c076c10d51654a549c4e50ec36da7662d4328",
      "implementationDigest": "sha256:d12c674a0643ab8fef38f7997fd47abbc4f9018f1da04629789cd5fd11fad7b4"
    },
    "metadata": {
      "name": "liger-tiled-geglu-forward-deepspeed-tiled-nvidia-geforce-rtx-4090-batch2-hidden2048-intermediate4096",
      "title": "GeGLU MLP (tiled benchmark) · deepspeed_tiled · forward",
      "labels": {
        "liger_version": "0.6.3"
      }
    },
    "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 4090",
        "architecture": "sm_89"
      },
      "software": {}
    },
    "metadata": {
      "name": "liger-bench-nvidia-geforce-rtx-4090",
      "title": "Liger benchmark host · GeForce RTX 4090"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  }
}
Cite this record (permalink, digest, access date)
Report an issue with this run

A maintainer reviews every report. If accepted, the record is retracted or superseded; its history stays visible.

Published 2026-08-20 · Liger-Kernel benchmarks · BSD-2-ClauseAll results for GeGLU MLP →JSON