Run 01a00b1d · KernelIndex

Primary measurement

137.3µsmean

Rank 6 in its comparison group · source-native comparison · observed 2026-06-06

Compare with #1 →

9.74× reference

Identity

implementationmm_fp4_nvfp4_cudnn_n4096_k4096

projectFlashInfer-Bench baselines

revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c

workloadm = 1024 · int8

comparison keysha256:591c3fc4454e8295…

sourceFlashInfer-Bench

sha256:79e6fe7d3a269927819b1fb…

Correctness

comparatorflashinfer_bench_eval

max absolute error0

max relative error0

resultpassed

Workload

m1024

a_fp4int8 [1024, 2048]

b_fp4int8 [4096, 2048]

a_scaleint8 [1024, 256]

b_scaleint8 [4096, 256]

definition comparatorsol_execbench_eval

Measurements

latency · mean137.3 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": 137343
        },
        "primaryStatistic": "mean"
      },
      "observedAt": "2026-06-06T21:33:43.574Z",
      "correctness": {
        "comparator": "sol_execbench_eval",
        "maximumAbsoluteError": 0,
        "maximumRelativeError": 0
      },
      "sourceNative": {
        "source": "flashinfer-bench",
        "metrics": {
          "latency_ms": 0.13734333333333335,
          "speedup_factor": 9.739133072834502,
          "reference_latency_ms": 1.337605
        },
        "benchmark": "gemm_nvfp4_n4096_k4096"
      },
      "protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
      "workloadDigest": "sha256:17946874a71497e00df2798525198fed396103b592c3ffba9724681e3bca625d",
      "environmentDigest": "sha256:83c9b6e78d493927f18878d57448d9a0d2221a70840b562455b2665a2897ba19",
      "implementationDigest": "sha256:18fa0b9785c9bd605848a831c2f8819866388f3b30f63f13b4b5ea5be4fe5924"
    },
    "metadata": {
      "name": "sol-trace-gemm-nvfp4-n4096-k4096-b477f118",
      "title": "mm_fp4_nvfp4_cudnn_n4096_k4096 · gemm_nvfp4_n4096_k4096"
    },
    "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 GEMM NVFP4 n4096 k4096 →JSON