Skip to content
KernelIndex
Search⌘K

gpt-5 / triton21bcc2

RMSNorm h4096 · batch_size = 64 · bf16 · run 01a02032-5ac1…
●passedReported evidence

Not re-observed recently.

Primary measurement
10.2µsmean

Rank 3 in its comparison group · source-native comparison · observed 2025-10-16

Compare with #1 →

64.52× reference

Identity
implementationgpt-5_triton_21bcc2
projectgpt-5-2025-08-07
revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c
workloadbatch_size = 64 · bf16
comparison keysha256:9fc6d4a6a9963314…
sourceFlashInfer-Bench
external idtrace/gpt-5_triton_21bcc2/14531e96-f6e6-4515-abb4-10855f72c80e
sha256:fae7455fd1ab8cd366350aa…

Correctness

comparatorflashinfer_bench_eval
max absolute error0.015625
max relative error0.0058139534667134285
resultpassed

Workload

batch_size64
weightbf16 [4096]
hidden_statesbf16 [64, 4096]
definition comparatorsol_execbench_eval

Measurements

latency · mean10.2 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
I

Published under your account name. Community attestations never change the evidence level; a maintainer can hide abuse.

Canonical manifest

Show manifest
{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "mean": 10185
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2025-10-16T12:17:56.597Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.015625,
        "maximumRelativeError": 0.0058139534667134285
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.010184669076162278,
          "speedup_factor": 64.5231356685711,
          "reference_latency_ms": 0.6571467845407194
        },
        "benchmark": "rmsnorm_h4096"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:cce2f4b5235b2610bdb9c1bf6bdb89a4fbc65141280daf66b01f0f54e2f161cc",
      "environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
      "implementationDigest": "sha256:fde311bab96aaa5b07c6b6d67d98fa76031e2e7a0d771525039739dc2f2f5d98"
    },
    "metadata": {
      "name": "sol-trace-rmsnorm-h4096-14531e96",
      "title": "gpt-5_triton_21bcc2 · rmsnorm_h4096"
    },
    "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

A maintainer reviews every report. If accepted, the record is retracted or superseded; its history stays visible.

Published 2026-08-20 · FlashInfer-Bench · Apache-2.0All results for RMSNorm h4096 →JSON