Run 01a02032 · KernelIndex

Primary measurement

25.4µsmean

Rank 4 in its comparison group · source-native comparison · observed 2025-10-16

Compare with #1 →

956.60× reference

Identity

implementationgemini-2.5-pro_triton_pr9imz

projectgemini-2.5-pro

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadnum_pages = 67 · batch_size = 1 · len_indptr = 2 · num_kv_indices = 50 · bf16

comparison keysha256:4ee1889c76b633f5…

sourceFlashInfer-Bench

external idtrace/gemini-2.5-pro_triton_pr9imz/13bd6f6d-915f-4653-9a77-8dbf7c35fb75

sha256:260fe6e8af120fdcc8fe6d0…

Correctness

comparatorflashinfer_bench_eval

max absolute error0.00048828125

max relative error0.006248361896723509

resultpassed

Workload

num_pages67

batch_size1

len_indptr2

num_kv_indices50

qbf16 [1, 32, 128]

k_cachebf16 [67, 1, 8, 128]

v_cachebf16 [67, 1, 8, 128]

kv_indptrint32 [2]

kv_indicesint32 [50]

definition comparatorsol_execbench_eval

Measurements

latency · mean25.4 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 manifest

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "mean": 25446
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2025-10-16T01:51:03.790Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.00048828125,
        "maximumRelativeError": 0.006248361896723509
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.025446181075476988,
          "speedup_factor": 956.6006904528597,
          "reference_latency_ms": 24.341834386189777
        },
        "benchmark": "gqa_paged_decode_h32_kv8_d128_ps1"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:a28591e131aa2ae557a6f7729b5396491b4376fba5b0a8d233a611c8b57dfa78",
      "environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
      "implementationDigest": "sha256:e5d6283af3f6143bf93e3bc93f551732f18d50a9d53538cf7fead3802f18b330"
    },
    "metadata": {
      "name": "sol-trace-gqa-paged-decode-h32-kv8-d128-ps1-13bd6f6d",
      "title": "gemini-2.5-pro_triton_pr9imz · gqa_paged_decode_h32_kv8_d128_ps1"
    },
    "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 GQA paged decode h32 kv8 d128 ps1 →JSON

gemini-2.5-pro / tritonpr9imz