Run 01a00b1e · KernelIndex

Primary measurement

20.5µsmean

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

82.34× reference

Identity

implementationflashinfer_wrapper_03f7b0

projectFlashInfer-Bench baselines

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadnum_pages = 989669 · batch_size = 1 · len_indptr = 2 · num_kv_indices = 508 · bf16

comparison keysha256:3830166605a9bbe1…

sourceFlashInfer-Bench

external idtrace/flashinfer_wrapper_03f7b0/4d9f5e3e-84d0-43d4-bb18-c451ef8009c0

sha256:fdaaa89c770034a9a5bff1a…

Correctness

comparatorflashinfer_bench_eval

max absolute error0.015625

max relative error13.896195411682129

resultpassed

Workload

num_pages989669

batch_size1

len_indptr2

num_kv_indices508

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 [508]

definition comparatorsol_execbench_eval

Measurements

latency · mean20.5 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": 20524
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2025-10-21T07:53:53.511Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.015625,
        "maximumRelativeError": 13.896195411682129
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.02052358733082311,
          "speedup_factor": 82.34404925742848,
          "reference_latency_ms": 1.6899952861084335
        },
        "benchmark": "mla_paged_decode_h16_ckv512_kpe64_ps1"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:6784510bc575df99706d3f64fe2ac096692ce7a160d6c0bff51e97102be106af",
      "environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
      "implementationDigest": "sha256:d63f2eb0f0a06bf1c4e9dd1f35d4aebd4c281ea806f8598245b7382024e120b5"
    },
    "metadata": {
      "name": "sol-trace-mla-paged-decode-h16-ckv512-kpe64-ps1-4d9f5e3e",
      "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