amd-mixture-of-experts · submission 25943
AMD DeepSeek-style MoE layer · bs = 1 · seed = 9371 · seqlen = 2048 · dexpert = 2048 · dhidden = 7168 · nroutedexperts = 32 · nsharedexperts = 1 · nexpertspertoken = 4 · fp16 · run 01a006cd-ec8a…
●passedReported evidence
Not re-observed recently.
Primary measurement
4.95msmean of 3
Rank 23 in its comparison group · source-native comparison · observed 2025-05-21
best ns 4944190 · mean ns 4946507.333333333 · leaderboard score s 0.008921958461693412
Identity
implementationamd-mixture-of-experts · submission 25943
projectKernelBot user 376
revisionsubmission-25943
workloadbs = 1 · seed = 9371 · seqlen = 2048 · dexpert = 2048 · dhidden = 7168 · nroutedexperts = 32 · nsharedexperts = 1 · nexpertspertoken = 4 · fp16
comparison keysha256:a11fec553fc287b0…
sourceGPU MODE KernelBot
external idsubmission/25943/benchmark/0
sha256:9c03236972e06f4cb393be0…
Correctness
Marked passed by the source; the correctness policy was not published.
Workload
bs1
seed9371
seqlen2048
dexpert2048
dhidden7168
nroutedexperts32
nsharedexperts1
nexpertspertoken4
inputfp16 [1, 2048, 7168]
definition comparatorkernelbot_eval
Measurements
latency · max4.95 ms · n=3
latency · mean4.95 ms · n=3
latency · min4.94 ms · n=3
latency · std2.01 µs · n=3
Protocol
harnessreference-kernels eval.py
timerwall_clock
primaryStatisticmean
correctnessReferenceproblem reference implementation
comparabilityFamilygpumode_kernelbot
Environment
gpuAMD Instinct MI300X (gfx942)
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": {
"samples": 3,
"latencyNs": {
"mean": 4946507,
"maximum": 4947712,
"minimum": 4944190
},
"primaryStatistic": "mean"
},
"observedAt": "2025-05-21T20:54:25.381Z",
"measurements": [
{
"unit": "ns",
"value": 2007.396655704431,
"metric": "latency",
"statistic": "std",
"sampleCount": 3
}
],
"sourceNative": {
"source": "gpumode-kernelbot",
"metrics": {
"best_ns": 4944190,
"mean_ns": 4946507.333333333,
"leaderboard_score_s": 0.008921958461693412
},
"benchmark": "amd-mixture-of-experts/0",
"externalId": "submission/25943"
},
"protocolDigest": "sha256:7c66da4b5866502eb10444a7ba013d0f6bdf1620c55847945008cad2fbf98aec",
"workloadDigest": "sha256:83ec2927d923cdd5616c8c43cb3970963f0fdec0c720c7a921b72f9ae73a4973",
"environmentDigest": "sha256:f722892449ed976f3e21b12df8b92b34573fc232883fec6a2f3da399a00abdd5",
"implementationDigest": "sha256:9aa1c13cc59d44f525abc89cebcc3d54b646732d82288a3d9661ddb52c0395d7"
},
"metadata": {
"name": "kernelbot-25943-bs1-dexpert2048-dhidden7168-nexpertspertoken4-nroutedexperts32-nsharedexperts1-seed9",
"title": "amd-mixture-of-experts · submission 25943 · case 0",
"labels": {
"torch": "2.8.0.dev20250520+rocm6.3",
"platform": "Linux-5.15.0-136-generic-x86_64-with-glibc2.35"
}
},
"apiVersion": "kernelindex.dev/v1alpha1"
},
"protocol": {
"kind": "BenchmarkProtocol",
"spec": {
"harness": {
"name": "reference-kernels eval.py",
"repository": "https://github.com/gpu-mode/reference-kernels"
},
"correctness": {
"reference": "problem reference implementation",
"comparator": "kernelbot_eval"
},
"measurement": {
"timer": "wall_clock",
"primaryStatistic": "mean"
},
"comparability": {
"notes": "Per-case wall-clock statistics as published in the KernelBot dataset. Comparable only within one leaderboard problem and GPU type; runner software versions ride each run's labels.",
"family": "gpumode_kernelbot"
}
},
"metadata": {
"name": "gpumode-kernelbot-eval",
"title": "GPU MODE KernelBot evaluation harness"
},
"apiVersion": "kernelindex.dev/v1alpha1"
},
"environment": {
"kind": "ExecutionEnvironment",
"spec": {
"hardware": {
"vendor": "amd",
"product": "AMD Instinct MI300X",
"architecture": "gfx942"
},
"software": {}
},
"metadata": {
"name": "gpumode-kernelbot-amd-instinct-mi300x",
"title": "KernelBot runner · AMD Instinct MI300X"
},
"apiVersion": "kernelindex.dev/v1alpha1"
}
}Cite this record (permalink, digest, access date)
Report an issue with this run
Published 2026-08-15 · GPU MODE KernelBot · June 9 Researcher Reciprocity License v1.0All results for AMD DeepSeek-style MoE layer →JSON