Run 01a00b1e · KernelIndex

Primary measurement

171.1µsmean

Rank 2 in its comparison group · source-native comparison · observed 2026-04-12

Compare with #1 →

4.16× reference

Identity

implementationflashinfer_wrapper_484d2c

projectFlashInfer-Bench baselines

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadtotal_q = 1 · num_pages = 33417 · len_indptr = 2 · num_kv_indices = 19 · bf16

comparison keysha256:fd8677f9f818b3f7…

sourceFlashInfer-Bench

external idtrace/flashinfer_wrapper_484d2c/68d2bc65-f48e-40c3-9ba7-ad1125db5d5b

sha256:8449b97e7fbe8f844de1345…

Correctness

comparatorflashinfer_bench_eval

max absolute error0.00390625

max relative error0.29585570096969604

resultpassed

Workload

total_q1

num_pages33417

len_indptr2

num_kv_indices19

qbf16 [1, 5, 128]

k_cachebf16 [33417, 1, 1, 128]

v_cachebf16 [33417, 1, 1, 128]

kv_indptrint32 [2]

qo_indptrint32 [2]

kv_indicesint32 [19]

definition comparatorsol_execbench_eval

Measurements

latency · mean171.1 µs

Protocol

harnessflashinfer-bench

timerharness_reported

primaryStatisticmean

correctnessReferencedefinition reference implementation

comparabilityFamilyflashinfer_bench_trace

Environment

gpuNVIDIA GB200 (unknown)

cudaToolkit13.0

frameworkpytorch 2.9.1+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": 171077
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2026-04-12T11:40:31.676Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.00390625,
        "maximumRelativeError": 0.29585570096969604
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.1710773358742396,
          "speedup_factor": 4.163450375738729,
          "reference_latency_ms": 0.7122719983259836
        },
        "benchmark": "gqa_paged_prefill_causal_h5_kv1_d128_ps1"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:8e257c0f6c04f48515fe6691c0acd6baf11991d7200743ad11e3153d9174fb37",
      "environmentDigest": "sha256:1766500d1b1ecc9787a211f3c98e76bf311671f443544a305252cb4d9564be8b",
      "implementationDigest": "sha256:55f48b083b7e6e5469cd58e5d1d25f570039035417a26fbab1c5b0248e115879"
    },
    "metadata": {
      "name": "sol-trace-gqa-paged-prefill-causal-h5-kv1-d128-ps1-68d2bc65",
      "title": "flashinfer_wrapper_484d2c · gqa_paged_prefill_causal_h5_kv1_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 GB200",
        "architecture": "unknown"
      },
      "software": {
        "framework": {
          "name": "pytorch",
          "version": "2.9.1+cu130"
        },
        "libraries": {
          "triton": "3.3.0"
        },
        "cudaToolkit": "13.0"
      }
    },
    "metadata": {
      "name": "sol-trace-nvidia-gb200-2-9-1-cu130-3-3-0-13-0",
      "title": "NVIDIA GB200 (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 prefill causal h5 kv1 d128 ps1 →JSON

flashinfer / wrapper484d2c