Run 01a0202b · KernelIndex

Primary measurement

2.72msmedian

Rank 1 in its comparison group · source-native comparison · observed 2025-11-11

ms 20 2.715123176574707 · ms 50 2.7152960300445557 · ms 80 2.7155072689056396

Identity

implementationLiger

projectLiger-Kernel

revisionunknown

workloadseq = 4096 · batch = 2 · hidden = 2048 · intermediate = 4096 · bf16

comparison keysha256:f0797942f189fc98…

sourceLiger-Kernel benchmarks

external idtiled_swiglu/forward/liger/nvidia-geforce-rtx-4090/batch2-hidden2048-intermediate4096-seq4096-bf16/2025-11-11-06-23-14

sha256:2ff429e6492690ef417a161…

Correctness

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

Workload

seq4096

batch2

hidden2048

intermediate4096

xbf16 [2, 4096, 2048]

w_upbf16 [4096, 2048]

w_downbf16 [2048, 4096]

w_gatebf16 [4096, 2048]

definition comparatornot_asserted

Measurements

latency · median2.72 ms

latency · p202.72 ms

latency · p802.72 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

Canonical manifest

Show manifest

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 2715296
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2025-11-11T06:23:14.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 2715123,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 2715507,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 2.715123176574707,
          "ms_50": 2.7152960300445557,
          "ms_80": 2.7155072689056396
        },
        "benchmark": "tiled_swiglu/forward",
        "externalId": "tiled_swiglu/forward/liger/nvidia-geforce-rtx-4090/batch2-hidden2048-intermediate4096-seq4096-bf16/2025-11-11-06-23-14"
      },
      "protocolDigest": "sha256:a79eaf4df66c97c6adc1fb2d09df78682155d1ea86652ae0b70199875bde7747",
      "workloadDigest": "sha256:2cb70c9a555a9ddc81564d0547434011e587d67ca3cef87d4ef5c02ccc73c190",
      "environmentDigest": "sha256:e2646efafa5e5fbd428b49a99b1c076c10d51654a549c4e50ec36da7662d4328",
      "implementationDigest": "sha256:70a682a3136a79d191bc46b7ccb18a8047564299ed31429e872c4b24efaa861f"
    },
    "metadata": {
      "name": "liger-tiled-swiglu-forward-liger-nvidia-geforce-rtx-4090-batch2-hidden2048-intermediate4096-seq4096-",
      "title": "SwiGLU MLP (tiled benchmark) · liger · 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

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