Run 01a00b1e · KernelIndex

Primary measurement

23.9µsmean

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

71.10× reference

Identity

implementationflashinfer_wrapper_03f7b0

projectFlashInfer-Bench baselines

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadnum_pages = 989669 · batch_size = 1 · len_indptr = 2 · num_kv_indices = 808 · bf16

comparison keysha256:3a6f4b53fad1bf9b…

sourceFlashInfer-Bench

external idtrace/flashinfer_wrapper_03f7b0/2cde88e6-dc7a-4cd0-8a97-980cd2c02740

sha256:f0ffb403e6f155f190708d6…

Correctness

comparatorflashinfer_bench_eval

max absolute error0.015625

max relative error14.621920585632324

resultpassed

Workload

num_pages989669

batch_size1

len_indptr2

num_kv_indices808

q_pebf16 [1, 16, 64]

q_nopebf16 [1, 16, 512]

ckv_cachebf16 [989669, 1, 512]

kpe_cachebf16 [989669, 1, 64]

kv_indptrint32 [2]

kv_indicesint32 [808]

definition comparatorsol_execbench_eval

Measurements

latency · mean23.9 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": 23878
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2025-10-21T07:53:55.721Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.015625,
        "maximumRelativeError": 14.621920585632324
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.023877889137620314,
          "speedup_factor": 71.100979088285,
          "reference_latency_ms": 1.6977412962463296
        },
        "benchmark": "mla_paged_decode_h16_ckv512_kpe64_ps1"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:ac97ada863ebcb0bed97dd33993ed8c6dc3f77c645295215c7612234f96d2075",
      "environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
      "implementationDigest": "sha256:d63f2eb0f0a06bf1c4e9dd1f35d4aebd4c281ea806f8598245b7382024e120b5"
    },
    "metadata": {
      "name": "sol-trace-mla-paged-decode-h16-ckv512-kpe64-ps1-2cde88e6",
      "title": "flashinfer_wrapper_03f7b0 · mla_paged_decode_h16_ckv512_kpe64_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 MLA paged decode h16 ckv512 kpe64 ps1 →JSON

flashinfer / wrapper03f7b0