cublaslt_nvfp4_scaled_mm_n4096_k4096
GEMM NVFP4 n4096 k4096 · m = 128 · int8 · run 01a00b1d-0cd1…
●passedReported evidence
Primary measurement
97.8µsmean
Rank 2 in its comparison group · source-native comparison · observed 2026-06-06
8.29× reference
Identity
implementationcublaslt_nvfp4_scaled_mm_n4096_k4096
projectFlashInfer-Bench baselines
revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c
workloadm = 128 · int8
comparison keysha256:52545bdd1e1f9070…
sourceFlashInfer-Bench
external idtrace/cublaslt_nvfp4_scaled_mm_n4096_k4096/27d3dd8d-91ba-4927-8789-74a5cd42f8f7
sha256:b519f5eab93369903c4dcef…
Correctness
comparatorflashinfer_bench_eval
max absolute error2
max relative error0.0078125
resultpassed
Workload
m128
a_fp4int8 [128, 2048]
b_fp4int8 [4096, 2048]
a_scaleint8 [128, 256]
b_scaleint8 [4096, 256]
definition comparatorsol_execbench_eval
Measurements
latency · mean97.8 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 manifestHide manifest
{
"run": {
"kind": "BenchmarkRun",
"spec": {
"status": "passed",
"timing": {
"latencyNs": {
"mean": 97813
},
"primaryStatistic": "mean"
},
"observedAt": "2026-06-06T21:33:33.763Z",
"correctness": {
"comparator": "sol_execbench_eval",
"maximumAbsoluteError": 2,
"maximumRelativeError": 0.0078125
},
"sourceNative": {
"source": "flashinfer-bench",
"metrics": {
"latency_ms": 0.09781283333333333,
"speedup_factor": 8.2892105160025,
"reference_latency_ms": 0.8107911666666666
},
"benchmark": "gemm_nvfp4_n4096_k4096"
},
"protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
"workloadDigest": "sha256:c1f9dfb8467b9846f2c9e83cd71cc31f82b96400d5fbcf1d9f9db6889a2aa33b",
"environmentDigest": "sha256:83c9b6e78d493927f18878d57448d9a0d2221a70840b562455b2665a2897ba19",
"implementationDigest": "sha256:516d6dd27b7a158a52b5ba6606ab3a6cb1a92c862d28a272f3cdcad9842fc96b"
},
"metadata": {
"name": "sol-trace-gemm-nvfp4-n4096-k4096-27d3dd8d",
"title": "cublaslt_nvfp4_scaled_mm_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