Transformers
GeGLU MLP · seq = 1024 · batch = 2 · hidden = 2048 · intermediate = 4096 · bf16 · run 01a0202b-233e…
●passedReported evidence
Not re-observed recently.
Primary measurement
674.3µsmedian
Rank 2 in its comparison group · source-native comparison · observed 2025-11-11
ms 20 0.6736640334129333 · ms 50 0.6743040084838867 · ms 80 0.677068829536438
Identity
implementationTransformers
projectHugging Face Transformers
revisionunknown
workloadseq = 1024 · batch = 2 · hidden = 2048 · intermediate = 4096 · bf16
comparison keysha256:028b85e876988d5e…
sourceLiger-Kernel benchmarks
external idtiled_geglu/forward/huggingface/nvidia-geforce-rtx-4090/batch2-hidden2048-intermediate4096-seq1024-bf16/2025-11-11-06-22-52
sha256:b891eea33872dd046b317be…
Correctness
Marked passed by the source; the correctness policy was not published.
Workload
seq1024
batch2
hidden2048
intermediate4096
xbf16 [2, 1024, 2048]
w_upbf16 [4096, 2048]
w_downbf16 [2048, 4096]
w_gatebf16 [4096, 2048]
definition comparatornot_asserted
Measurements
latency · median674.3 µs
latency · p20673.7 µs
latency · p80677.1 µs
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 manifestHide manifest
{
"run": {
"kind": "BenchmarkRun",
"spec": {
"status": "passed",
"timing": {
"latencyNs": {
"median": 674304
},
"primaryStatistic": "median"
},
"observedAt": "2025-11-11T06:22:52.000Z",
"measurements": [
{
"unit": "ns",
"value": 673664,
"metric": "latency",
"statistic": "p20"
},
{
"unit": "ns",
"value": 677069,
"metric": "latency",
"statistic": "p80"
}
],
"sourceNative": {
"source": "liger-kernel-bench",
"metrics": {
"ms_20": 0.6736640334129333,
"ms_50": 0.6743040084838867,
"ms_80": 0.677068829536438
},
"benchmark": "tiled_geglu/forward",
"externalId": "tiled_geglu/forward/huggingface/nvidia-geforce-rtx-4090/batch2-hidden2048-intermediate4096-seq1024-bf16/2025-11-11-06-22-52"
},
"protocolDigest": "sha256:a79eaf4df66c97c6adc1fb2d09df78682155d1ea86652ae0b70199875bde7747",
"workloadDigest": "sha256:7477e51bd95bff47821a6d62d904a46ce595577d4de14aaaa025304660c6fed1",
"environmentDigest": "sha256:e2646efafa5e5fbd428b49a99b1c076c10d51654a549c4e50ec36da7662d4328",
"implementationDigest": "sha256:d12c674a0643ab8fef38f7997fd47abbc4f9018f1da04629789cd5fd11fad7b4"
},
"metadata": {
"name": "liger-tiled-geglu-forward-huggingface-nvidia-geforce-rtx-4090-batch2-hidden2048-intermediate4096-seq",
"title": "GeGLU MLP (tiled benchmark) · huggingface · 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 GeGLU MLP →JSON