Run 01a02032 · KernelIndex

Primary measurement

1.32msmean

Rank 3 in its comparison group · source-native comparison · observed 2025-10-20

Compare with #1 →

29.29× reference

Identity

implementationclaude-opus-4-1_triton_28277f

projectclaude-opus-4-1-20250805

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadtotal_q = 969 · total_kv = 969 · len_indptr = 16 · bf16

comparison keysha256:d263e8051b2ab468…

sourceFlashInfer-Bench

external idtrace/claude-opus-4-1_triton_28277f/b3445888-8668-4721-9359-9da119ab9f34

sha256:cc8e5ad20add019e02dd289…

Correctness

comparatorflashinfer_bench_eval

max absolute error0.015625

max relative error1632.711181640625

resultpassed

Workload

total_q969

total_kv969

len_indptr16

kbf16 [969, 4, 128]

qbf16 [969, 32, 128]

vbf16 [969, 4, 128]

kv_indptrint32 [16]

qo_indptrint32 [16]

definition comparatorsol_execbench_eval

Measurements

latency · mean1.32 ms

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": 1319782
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2025-10-20T01:08:35.938Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.015625,
        "maximumRelativeError": 1632.711181640625
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 1.3197818978412732,
          "speedup_factor": 29.286560197807308,
          "reference_latency_ms": 38.65187199910482
        },
        "benchmark": "gqa_ragged_prefill_causal_h32_kv4_d128"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:700527a4350d7f0e3c9cbd5650c827fc25e2a7bc5af80107e2db436a6ff8bcce",
      "environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
      "implementationDigest": "sha256:b6c7a77a7154a6c178f823fddb57fffe8bc08b69cbb48566995c53b7ce9d6dae"
    },
    "metadata": {
      "name": "sol-trace-gqa-ragged-prefill-causal-h32-kv4-d128-b3445888",
      "title": "claude-opus-4-1_triton_28277f · gqa_ragged_prefill_causal_h32_kv4_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 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 2026-08-20 · FlashInfer-Bench · Apache-2.0All results for GQA ragged prefill causal h32 kv4 d128 →JSON

claude-opus-4-1 / triton28277f