Run 01a00b1e · KernelIndex

Primary measurement

22.6µsmean

Rank 1 in its comparison group · source-native comparison · observed 2026-04-06

Compare with #1 →

338.78× reference

Identity

implementationflashinfer_wrapper_d90b98

projectFlashInfer-Bench baselines

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadtotal_q = 1371 · total_kv = 1371 · len_indptr = 30 · bf16

comparison keysha256:2b93a71d567000b3…

sourceFlashInfer-Bench

external idtrace/flashinfer_wrapper_d90b98/bdff69a3-5f9b-42b7-b8db-1b312f34bdf4

sha256:85f881c579a5a3c60937ff1…

Correctness

comparatorflashinfer_bench_eval

max absolute error0.015625

max relative error2891.460205078125

resultpassed

Workload

total_q1371

total_kv1371

len_indptr30

kbf16 [1371, 16, 192]

qbf16 [1371, 16, 192]

vbf16 [1371, 16, 128]

kv_indptrint32 [30]

qo_indptrint32 [30]

definition comparatorsol_execbench_eval

Measurements

latency · mean22.6 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": 22565
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2026-04-06T16:24:10.648Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.015625,
        "maximumRelativeError": 2891.460205078125
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.022565333793560665,
          "speedup_factor": 338.77829785119496,
          "reference_latency_ms": 7.64464537302653
        },
        "benchmark": "mla_ragged_prefill_causal_h16_qk192_vo128"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:a0a9dd73d13aad2a3a7e33bc5c71e7928f46ce09b27b3b186be81702d9e4876f",
      "environmentDigest": "sha256:83c9b6e78d493927f18878d57448d9a0d2221a70840b562455b2665a2897ba19",
      "implementationDigest": "sha256:7ea424535a43467c4a56a0f6102017255639162cb40f5002e92454310a911b5f"
    },
    "metadata": {
      "name": "sol-trace-mla-ragged-prefill-causal-h16-qk192-vo128-bdff69a3",
      "title": "flashinfer_wrapper_d90b98 · mla_ragged_prefill_causal_h16_qk192_vo128"
    },
    "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 MLA ragged prefill causal h16 qk192 vo128 →JSON

flashinfer / wrapperd90b98