Run 01a00b1e · KernelIndex

Primary measurement

16.5µsmean

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

165.03× reference

Identity

implementationflashinfer_wrapper_ea3787

projectFlashInfer-Bench baselines

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadtotal_q = 8 · num_pages = 989669 · len_indptr = 2 · num_kv_indices = 12 · bf16

comparison keysha256:003483cf8d8fe733…

sourceFlashInfer-Bench

external idtrace/flashinfer_wrapper_ea3787/d88c9577-ac5d-414c-9d57-d91cc14b7eed

sha256:f4572d3ab7906a3ab14b5d6…

Correctness

comparatorflashinfer_bench_eval

max absolute error0.015625

max relative error34.653892517089844

resultpassed

Workload

total_q8

num_pages989669

len_indptr2

num_kv_indices12

q_pebf16 [8, 16, 64]

q_nopebf16 [8, 16, 512]

ckv_cachebf16 [989669, 1, 512]

kpe_cachebf16 [989669, 1, 64]

kv_indptrint32 [2]

qo_indptrint32 [2]

kv_indicesint32 [12]

definition comparatorsol_execbench_eval

Measurements

latency · mean16.5 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": 16474
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2025-10-21T08:05:45.411Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0.015625,
        "maximumRelativeError": 34.653892517089844
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.01647372880911358,
          "speedup_factor": 165.03439497185704,
          "reference_latency_ms": 2.718731866942511
        },
        "benchmark": "mla_paged_prefill_causal_h16_ckv512_kpe64_ps1"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:3b372b481e2fe84b2d67e7933f741c3429b88f76c6fbe167f6334ddd340b2b5a",
      "environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
      "implementationDigest": "sha256:bcc5e6b5c47e98f95a4c85f871621f8a2976c0963b289e9e14d9d10f13604c8b"
    },
    "metadata": {
      "name": "sol-trace-mla-paged-prefill-causal-h16-ckv512-kpe64-ps1-d88c9577",
      "title": "flashinfer_wrapper_ea3787 · mla_paged_prefill_causal_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 prefill causal h16 ckv512 kpe64 ps1 →JSON

flashinfer / wrapperea3787