Skip to content
KernelIndex
Search⌘K

flashinfer / wrapper7f6051

Fused add RMSNorm h5120 · batch_size = 1174 · bf16 · run 01a00b1e-8788…
●passedReported evidence

Not re-observed recently.

Primary measurement
12.7µsmean

Rank 1 in its comparison group · source-native comparison · observed 2026-03-24

10.49× reference

Identity
implementationflashinfer_wrapper_7f6051
projectFlashInfer-Bench baselines
revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c
workloadbatch_size = 1174 · bf16
comparison keysha256:269aa1edc2d9a8bd…
sourceFlashInfer-Bench
external idtrace/flashinfer_wrapper_7f6051/e6d6a433-d5a8-4e4f-9756-f7da07bbd382
sha256:778bd21ddb4689054ad68d6…

Correctness

comparatorflashinfer_bench_eval
max absolute error0.03125
max relative error0.007751937955617905
resultpassed

Workload

batch_size1174
weightbf16 [5120]
residualbf16 [1174, 5120]
hidden_statesbf16 [1174, 5120]
definition comparatorsol_execbench_eval

Measurements

latency · mean12.7 µs

Protocol

harnessflashinfer-bench
timerharness_reported
primaryStatisticmean
correctnessReferencedefinition reference implementation
comparabilityFamilyflashinfer_bench_trace

Environment

gpuNVIDIA B200 (unknown)
cudaToolkit12.8
frameworkpytorch 2.9.1+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": 12672
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2026-03-24T20:24:22.829Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.03125,
        "maximumRelativeError": 0.007751937955617905
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.012672,
          "speedup_factor": 10.489977904040405,
          "reference_latency_ms": 0.132929
        },
        "benchmark": "fused_add_rmsnorm_h5120"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:992e017cf9f30ade2ebaf9f486796cd9482952c5a1c865dc1fd12e4257e79c24",
      "environmentDigest": "sha256:af7cb68a0bb0eb9671092a620668c2600f0431301fc46a71807ea75fb7de8bce",
      "implementationDigest": "sha256:d3fa5fac7faa15594fb8db18208ea246bead347196f12e5001731a34ed3e0fa4"
    },
    "metadata": {
      "name": "sol-trace-fused-add-rmsnorm-h5120-e6d6a433",
      "title": "flashinfer_wrapper_7f6051 · fused_add_rmsnorm_h5120"
    },
    "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": "2.9.1+cu128"
        },
        "libraries": {
          "triton": "3.5.1"
        },
        "cudaToolkit": "12.8"
      }
    },
    "metadata": {
      "name": "sol-trace-nvidia-b200-2-9-1-cu128-3-5-1-12-8",
      "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.