Run 01a02032 · KernelIndex

Primary measurement

6.29µsmean

Rank 1 in its comparison group · source-native comparison · observed 2025-10-16

142.89× reference

Identity

implementationgemini-2.5-pro_cuda_208a66

projectgemini-2.5-pro

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadbatch_size = 64 · bf16

comparison keysha256:152be93926d5d994…

sourceFlashInfer-Bench

external idtrace/gemini-2.5-pro_cuda_208a66/c2c0808b-f368-434a-bbd7-09c79cec998b

sha256:1b56d9f6fc3bd839bde99a4…

Correctness

comparatorflashinfer_bench_eval

max absolute error0.00390625

max relative error0.006535947788506746

resultpassed

Workload

batch_size64

weightbf16 [1536]

hidden_statesbf16 [64, 1536]

definition comparatorsol_execbench_eval

Measurements

latency · mean6.29 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

logssha256:800066abefe7ba51… · text/plain · unavailable

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 manifest

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "mean": 6291
        },
        "primaryStatistic": "mean"
      },
      "evidence": {
        "logs": {
          "uri": "kernelindex:artifact/sha256:800066abefe7ba51170c0b785b42d4d81ed187e0383d48a5e5f529850417b97a",
          "digest": "sha256:800066abefe7ba51170c0b785b42d4d81ed187e0383d48a5e5f529850417b97a"
        }
      },
      "observedAt": "2025-10-16T12:14:37.902Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.00390625,
        "maximumRelativeError": 0.006535947788506746
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.0062912167694673385,
          "speedup_factor": 142.8897816262161,
          "reference_latency_ms": 0.8989505903523766
        },
        "benchmark": "rmsnorm_h1536"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:dc73c744b410a9b59642467cdc9880a8bdf7327db96d851e9f29278e16fe032c",
      "environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
      "implementationDigest": "sha256:466acddda77d67cf70ed7558a73f65eca25ae24fd55a61ecf06c29b179d4af35"
    },
    "metadata": {
      "name": "sol-trace-rmsnorm-h1536-c2c0808b",
      "title": "gemini-2.5-pro_cuda_208a66 · rmsnorm_h1536"
    },
    "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 h1536 →JSON

gemini-2.5-pro / cuda208a66