Run 01a00b1d · KernelIndex

Primary measurement

10.2µsmean

Rank 1 in its comparison group · source-native comparison · observed 2026-04-20

25.77× reference

Identity

implementationflashinfer_wrapper_68ff49

projectFlashInfer-Bench baselines

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadnum_pages = 66 · batch_size = 1 · len_indptr = 2 · num_kv_indices = 2 · bf16

comparison keysha256:fa32f829f18f3dfd…

sourceFlashInfer-Bench

external idtrace/flashinfer_wrapper_68ff49/82761919-e520-4a9d-b18d-ef5b07f25245

sha256:e196f66f0433da55092c516…

Correctness

comparatorflashinfer_bench_eval

max absolute error0.001953125

max relative error0.007575757801532745

resultpassed

Workload

num_pages66

batch_size1

len_indptr2

num_kv_indices2

qbf16 [1, 32, 64]

k_cachebf16 [66, 64, 8, 64]

v_cachebf16 [66, 64, 8, 64]

kv_indptrint32 [2]

kv_indicesint32 [2]

kv_last_page_lenint32 [1]

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)

cudaToolkit13.0

frameworkpytorch 2.11.0+cu130

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": 10197
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2026-04-20T07:33:21.249Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.001953125,
        "maximumRelativeError": 0.007575757801532745
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.010197333681086699,
          "speedup_factor": 25.76725880680814,
          "reference_latency_ms": 0.2627573360999425
        },
        "benchmark": "gqa_paged_decode_h32_kv8_d64_ps64"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:e26fa524346fef18b75eb9a8f624bf51b70e773f6a0815453ef1c391d5a76f6b",
      "environmentDigest": "sha256:83c9b6e78d493927f18878d57448d9a0d2221a70840b562455b2665a2897ba19",
      "implementationDigest": "sha256:00c3274edaddef3a4089443d1ed3c6f4dd9b23096d6583d4d8a99c067d2f11ea"
    },
    "metadata": {
      "name": "sol-trace-gqa-paged-decode-h32-kv8-d64-ps64-82761919",
      "title": "flashinfer_wrapper_68ff49 · gqa_paged_decode_h32_kv8_d64_ps64"
    },
    "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": "2.11.0+cu130"
        },
        "libraries": {
          "triton": "3.6.0"
        },
        "cudaToolkit": "13.0"
      }
    },
    "metadata": {
      "name": "sol-trace-nvidia-b200-2-11-0-cu130-3-6-0-13-0",
      "title": "NVIDIA B200 (trace-reported software)"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  }
}

Cite this record (permalink, digest, access date)

Report an issue with this run

Published 2026-08-16 · FlashInfer-Bench · Apache-2.0All results for GQA paged decode h32 kv8 d64 ps64 →JSON

flashinfer / wrapper68ff49