Run 01a00b1e · KernelIndex

Primary measurement

10.2µsmean

Rank 1 in its comparison group · source-native comparison · observed 2026-04-09

Compare with #1 →

34.69× reference

Identity

implementationflashinfer_wrapper_33cb6f

projectFlashInfer-Bench baselines

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadtotal_q = 29 · total_kv = 29 · len_indptr = 2 · bf16

comparison keysha256:bd90893d331a60a1…

sourceFlashInfer-Bench

external idtrace/flashinfer_wrapper_33cb6f/d6151cde-e30c-4ec2-b951-ff72846c0386

sha256:2f2c18e020f08d67a7d067d…

Correctness

comparatorflashinfer_bench_eval

max absolute error0.015625

max relative error63.91754150390625

resultpassed

Workload

total_q29

total_kv29

len_indptr2

kbf16 [29, 1, 256]

qbf16 [29, 8, 256]

vbf16 [29, 1, 256]

kv_indptrint32 [2]

qo_indptrint32 [2]

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": 10240
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2026-04-09T02:00:21.927Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.015625,
        "maximumRelativeError": 63.91754150390625
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.010239999741315842,
          "speedup_factor": 34.68958496360263,
          "reference_latency_ms": 0.35522134105364483
        },
        "benchmark": "gqa_ragged_prefill_causal_h8_kv1_d256"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:3d91853b7a56e0a051e6f6fc88f126e26bbe9618a1d5614e0a37461b77f42cae",
      "environmentDigest": "sha256:83c9b6e78d493927f18878d57448d9a0d2221a70840b562455b2665a2897ba19",
      "implementationDigest": "sha256:fdf38318ea766afdda61fe7e9fb7c51696da2d903a6373327e53e57a4f0225f9"
    },
    "metadata": {
      "name": "sol-trace-gqa-ragged-prefill-causal-h8-kv1-d256-d6151cde",
      "title": "flashinfer_wrapper_33cb6f · gqa_ragged_prefill_causal_h8_kv1_d256"
    },
    "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 ragged prefill causal h8 kv1 d256 →JSON

flashinfer / wrapper33cb6f