Run 01a00b1e · KernelIndex

Primary measurement

189.5µsmean

Rank 1 in its comparison group · source-native comparison · observed 2025-10-21

2014.62× reference

Identity

implementationflashinfer_wrapper_8cad92

projectFlashInfer-Bench baselines

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadtotal_q = 123 · num_pages = 135698 · len_indptr = 4 · num_kv_indices = 12 · bf16

comparison keysha256:62efa49e79b8f5cb…

sourceFlashInfer-Bench

external idtrace/flashinfer_wrapper_8cad92/7e6843d3-b230-43b4-923c-05b066fe0653

sha256:ac920615da4ed2a330d9bc6…

Correctness

comparatorflashinfer_bench_eval

max relative error40.57786560058594

resultpassed

Workload

total_q123

num_pages135698

len_indptr4

num_kv_indices12

qbf16 [123, 32, 128]

k_cachebf16 [135698, 1, 8, 128]

v_cachebf16 [135698, 1, 8, 128]

kv_indptrint32 [4]

qo_indptrint32 [4]

kv_indicesint32 [12]

definition comparatorsol_execbench_eval

Measurements

latency · mean189.5 µs

Protocol

harnessflashinfer-bench

timerharness_reported

primaryStatisticmean

correctnessReferencedefinition reference implementation

comparabilityFamilyflashinfer_bench_trace

Environment

gpuNVIDIA B200 (unknown)

cudaToolkit12.8

frameworkpytorch 2.8.0+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": 189455
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2025-10-21T14:14:06.667Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumRelativeError": 40.57786560058594
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.18945474849506316,
          "speedup_factor": 2014.6205151689232,
          "reference_latency_ms": 381.67942301432294
        },
        "benchmark": "gqa_paged_prefill_causal_h32_kv8_d128_ps1"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:600d14cf3bfe7a0511141684d2284080af56f0fa938c07e84cfd34a39239ce7b",
      "environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
      "implementationDigest": "sha256:a4874695882045ef20a8bbe3f81dc02f48b57c80495f8d424d6f80c64b07d49c"
    },
    "metadata": {
      "name": "sol-trace-gqa-paged-prefill-causal-h32-kv8-d128-ps1-7e6843d3",
      "title": "flashinfer_wrapper_8cad92 · gqa_paged_prefill_causal_h32_kv8_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 B200",
        "architecture": "unknown"
      },
      "software": {
        "framework": {
          "name": "pytorch",
          "version": "2.8.0+cu128"
        },
        "libraries": {
          "triton": "3.4.0"
        },
        "cudaToolkit": "12.8"
      }
    },
    "metadata": {
      "name": "sol-trace-nvidia-b200-2-8-0-cu128-3-4-0-12-8",
      "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 prefill causal h32 kv8 d128 ps1 →JSON

flashinfer / wrapper8cad92