Liger
GeGLU MLP · seq = 1024 · batch = 8 · hidden = 4096 · intermediate = 11008 · bf16 · run 01a016ad-87a2…
●passedReported evidence
Not re-observed recently.
Primary measurement
30.0msmedian
Rank 2 in its comparison group · source-native comparison · observed 2024-09-03
ms 20 30.03536033630371 · ms 50 30.03536033630371 · ms 80 30.03536033630371
Identity
implementationLiger
projectLiger-Kernel
revisionunknown
workloadseq = 1024 · batch = 8 · hidden = 4096 · intermediate = 11008 · bf16
comparison keysha256:4b915c51c3a186c7…
sourceLiger-Kernel benchmarks
external idgeglu/full/liger/nvidia-a100-sxm4-80gb/batch8-hidden4096-intermediate11008-seq1024-bf16/2024-09-03-15-38-14
sha256:47091a0d67a2b4865870072…
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 · median30.0 ms
latency · p2030.0 ms
latency · p8030.0 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 manifestHide manifest
{
"run": {
"kind": "BenchmarkRun",
"spec": {
"status": "passed",
"timing": {
"latencyNs": {
"median": 30035360
},
"primaryStatistic": "median"
},
"observedAt": "2024-09-03T15:38:14.000Z",
"measurements": [
{
"unit": "ns",
"value": 30035360,
"metric": "latency",
"statistic": "p20"
},
{
"unit": "ns",
"value": 30035360,
"metric": "latency",
"statistic": "p80"
}
],
"sourceNative": {
"source": "liger-kernel-bench",
"metrics": {
"ms_20": 30.03536033630371,
"ms_50": 30.03536033630371,
"ms_80": 30.03536033630371
},
"benchmark": "geglu/full",
"externalId": "geglu/full/liger/nvidia-a100-sxm4-80gb/batch8-hidden4096-intermediate11008-seq1024-bf16/2024-09-03-15-38-14"
},
"protocolDigest": "sha256:5b02ee9a2140fbc6fcc1c89800f6c177ba22718c8897cb532bf0ba91867c1e58",
"workloadDigest": "sha256:b2a90871d1d2b4ede81c3530fd5851ec95bfff5d0586b7838cd15683c248c008",
"environmentDigest": "sha256:90c9e2764222f592477cfccf3373519add5a1b881563956ad058c4f99e41b6b9",
"implementationDigest": "sha256:273de05b950c7c7353e9e2b0d88f29cab729451b9b3034c01494e1d02bac3c46"
},
"metadata": {
"name": "liger-geglu-full-liger-nvidia-a100-sxm4-80gb-batch8-hidden4096-intermediate11008-seq1024-bf16-2024-0",
"title": "GeGLU MLP · liger · full",
"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 forward pass plus the backward 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-full",
"title": "Liger benchmark harness · full 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