Run 01a00b1d · KernelIndex

Primary measurement

1.26msmean

Rank 1 in its comparison group · source-native comparison · observed 2026-03-31

1.45× reference

Identity

implementationflashinfer_wrapper_1b7890

projectFlashInfer-Bench baselines

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadnum_pages = 1729 · batch_size = 4 · len_indptr = 5 · num_kv_indices = 275 · bf16

comparison keysha256:8f42ab9fb82e50a9…

sourceFlashInfer-Bench

external idtrace/flashinfer_wrapper_1b7890/49bdb988-db6d-4f75-963f-954e9ec88c61

sha256:b9fd39439dd1f90ba85d5e9…

Correctness

comparatorflashinfer_bench_eval

max absolute error0.0009765625

max relative error26.206043243408203

resultpassed

Workload

num_pages1729

batch_size4

len_indptr5

num_kv_indices275

qbf16 [4, 24, 128]

k_cachebf16 [1729, 64, 4, 128]

v_cachebf16 [1729, 64, 4, 128]

kv_indptrint32 [5]

kv_indicesint32 [275]

kv_last_page_lenint32 [4]

definition comparatorsol_execbench_eval

Measurements

latency · mean1.26 ms

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

Canonical manifest

Show manifest

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "mean": 1255804
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2026-03-31T14:36:25.390Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.0009765625,
        "maximumRelativeError": 26.206043243408203
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 1.2558038333333332,
          "speedup_factor": 1.4455585751649376,
          "reference_latency_ms": 1.815338
        },
        "benchmark": "gqa_paged_decode_h24_kv4_d128_ps64"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:557df22111b9a254f783cd40877acaf4a55bdc47198f643395b128385d20492f",
      "environmentDigest": "sha256:af7cb68a0bb0eb9671092a620668c2600f0431301fc46a71807ea75fb7de8bce",
      "implementationDigest": "sha256:f93c7e9cdbce77603e6624341de86495d8c3315e276228537ef3fd79596f0cbc"
    },
    "metadata": {
      "name": "sol-trace-gqa-paged-decode-h24-kv4-d128-ps64-49bdb988",
      "title": "flashinfer_wrapper_1b7890 · gqa_paged_decode_h24_kv4_d128_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": "2.9.1+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

Published 2026-08-16 · FlashInfer-Bench · Apache-2.0All results for GQA paged decode h24 kv4 d128 ps64 →JSON

flashinfer / wrapper1b7890