Run 01a00b1e · KernelIndex

Primary measurement

489.1µsmean

Rank 1 in its comparison group · source-native comparison · observed 2026-04-12

28.69× reference

Identity

implementationflashinfer_wrapper_fe59e7

projectFlashInfer-Bench baselines

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadtotal_q = 10941 · total_kv = 10941 · len_indptr = 8 · bf16

comparison keysha256:c5520b911b8c57a1…

sourceFlashInfer-Bench

external idtrace/flashinfer_wrapper_fe59e7/81936a49-e2db-4712-9c16-0c6506c8606c

sha256:c22083d79ee78e65df5cee8…

Correctness

comparatorflashinfer_bench_eval

max absolute error0.015625

max relative error16444.888671875

resultpassed

Workload

total_q10941

total_kv10941

len_indptr8

kbf16 [10941, 8, 128]

qbf16 [10941, 24, 128]

vbf16 [10941, 8, 128]

kv_indptrint32 [8]

qo_indptrint32 [8]

definition comparatorsol_execbench_eval

Measurements

latency · mean489.1 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": 489083
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2026-04-12T13:17:47.945Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.015625,
        "maximumRelativeError": 16444.888671875
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.4890826642513275,
          "speedup_factor": 28.694393903820743,
          "reference_latency_ms": 14.0339306195577
        },
        "benchmark": "gqa_ragged_prefill_causal_h24_kv8_d128"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:0d6d0109854dc22fc21cb64cdd4f28119006ebb1e82baa646cb19d06d21e48b9",
      "environmentDigest": "sha256:1766500d1b1ecc9787a211f3c98e76bf311671f443544a305252cb4d9564be8b",
      "implementationDigest": "sha256:1ae32bdf663d64c4ba87676614658cc570a1530f315eee8d5c4f3faeb9f2b080"
    },
    "metadata": {
      "name": "sol-trace-gqa-ragged-prefill-causal-h24-kv8-d128-81936a49",
      "title": "flashinfer_wrapper_fe59e7 · gqa_ragged_prefill_causal_h24_kv8_d128"
    },
    "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 ragged prefill causal h24 kv8 d128 →JSON

flashinfer / wrapperfe59e7