gpt-5 / triton159afd
RMSNorm h7168 · batch_size = 32 · bf16 · run 01a02032-5ac4…
●passedReported evidence
Not re-observed recently.
Primary measurement
12.3µsmean
Rank 4 in its comparison group · source-native comparison · observed 2025-10-16
69.69× reference
Identity
implementationgpt-5_triton_159afd
projectgpt-5-2025-08-07
revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c
workloadbatch_size = 32 · bf16
comparison keysha256:566bee9eb797fe35…
sourceFlashInfer-Bench
external idtrace/gpt-5_triton_159afd/08ca44b8-2c3a-407d-87a7-85454ef4d748
sha256:69a3765a8aecfa014789ef4…
Correctness
comparatorflashinfer_bench_eval
max absolute error0.0078125
max relative error0.0069444444961845875
resultpassed
Workload
batch_size32
weightbf16 [7168]
hidden_statesbf16 [32, 7168]
definition comparatorsol_execbench_eval
Measurements
latency · mean12.3 µs
Protocol
harnessflashinfer-bench
timerharness_reported
primaryStatisticmean
correctnessReferencedefinition reference implementation
comparabilityFamilyflashinfer_bench_trace
Environment
gpuNVIDIA B200 (unknown)
cudaToolkit12.8
frameworkpytorch 2.8.0+cu128
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": {
"mean": 12318
},
"primaryStatistic": "mean"
},
"observedAt": "2025-10-16T12:20:57.552Z",
"correctness": {
"comparator": "sol_execbench_eval",
"maximumAbsoluteError": 0.0078125,
"maximumRelativeError": 0.0069444444961845875
},
"sourceNative": {
"source": "flashinfer-bench",
"metrics": {
"latency_ms": 0.012317618184177951,
"speedup_factor": 69.68845307142092,
"reference_latency_ms": 0.8583957567797661
},
"benchmark": "rmsnorm_h7168"
},
"protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
"workloadDigest": "sha256:b477fda28b7a912017a1bbce97222834bba6cfb72d750f9e3a6ea84ff283304b",
"environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
"implementationDigest": "sha256:df56ce0a16c6e91a6fb710a19cc1df0daaf9742d2c0fdc53f6e2a13842c5e61c"
},
"metadata": {
"name": "sol-trace-rmsnorm-h7168-08ca44b8",
"title": "gpt-5_triton_159afd · rmsnorm_h7168"
},
"apiVersion": "kernelindex.dev/v1alpha1"
},
"protocol": {
"kind": "BenchmarkProtocol",
"spec": {
"harness": {
"name": "flashinfer-bench",
"repository": "https://github.com/flashinfer-ai/flashinfer-bench"
},
"correctness": {
"reference": "definition reference implementation",
"comparator": "flashinfer_bench_eval"
},
"measurement": {
"timer": "harness_reported",
"primaryStatistic": "mean"
},
"comparability": {
"family": "flashinfer_bench_trace"
}
},
"metadata": {
"name": "flashinfer-bench-trace",
"title": "FlashInfer-Bench trace harness"
},
"apiVersion": "kernelindex.dev/v1alpha1"
},
"environment": {
"kind": "ExecutionEnvironment",
"spec": {
"hardware": {
"vendor": "nvidia",
"product": "NVIDIA B200",
"architecture": "unknown"
},
"software": {
"framework": {
"name": "pytorch",
"version": "2.8.0+cu128"
},
"libraries": {
"triton": "3.4.0"
},
"cudaToolkit": "12.8"
}
},
"metadata": {
"name": "sol-trace-nvidia-b200-2-8-0-cu128-3-4-0-12-8",
"title": "NVIDIA B200 (trace-reported software)"
},
"apiVersion": "kernelindex.dev/v1alpha1"
}
}Cite this record (permalink, digest, access date)
Report an issue with this run
Published 2026-08-20 · FlashInfer-Bench · Apache-2.0All results for RMSNorm h7168 →JSON