claude-opus-4-1 / triton8f159a
GEMM n4096 k14336 · m = 8192 · fp16 · run 01a02032-4c86…
●passedReported evidence
Not re-observed recently.
Primary measurement
2.90msmean
Rank 4 in its comparison group · source-native comparison · observed 2025-10-20
0.03× reference
Identity
implementationclaude-opus-4-1_triton_8f159a
projectclaude-opus-4-1-20250805
revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c
workloadm = 8192 · fp16
comparison keysha256:f618bca4a110d45f…
sourceFlashInfer-Bench
external idtrace/claude-opus-4-1_triton_8f159a/86b21a3d-66e2-4837-9e15-948f282ed2df
sha256:a4e93fa897cce929e0bd20e…
Correctness
comparatorflashinfer_bench_eval
max absolute error0.5
max relative error983.2174072265625
resultpassed
Workload
m8192
afp16 [8192, 14336]
bfp16 [4096, 14336]
definition comparatorsol_execbench_eval
Measurements
latency · mean2.90 ms
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 manifestHide manifest
{
"run": {
"kind": "BenchmarkRun",
"spec": {
"status": "passed",
"timing": {
"latencyNs": {
"mean": 2899435
},
"primaryStatistic": "mean"
},
"observedAt": "2025-10-20T03:27:10.652Z",
"correctness": {
"comparator": "sol_execbench_eval",
"maximumAbsoluteError": 0.5,
"maximumRelativeError": 983.2174072265625
},
"sourceNative": {
"source": "flashinfer-bench",
"metrics": {
"latency_ms": 2.8994351944892234,
"speedup_factor": 0.030245202204786617,
"reference_latency_ms": 0.08769400373700137
},
"benchmark": "gemm_n4096_k14336"
},
"protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
"workloadDigest": "sha256:37e21e07c28f7a4bb101066d0ffb10edfa583b6bc047580aa7ac44578975038d",
"environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
"implementationDigest": "sha256:b6a8b41d4edc7ecc23d239c0e96ae879d037f8af72a29c73dbcd374f818ac079"
},
"metadata": {
"name": "sol-trace-gemm-n4096-k14336-86b21a3d",
"title": "claude-opus-4-1_triton_8f159a · gemm_n4096_k14336"
},
"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 2026-08-20 · FlashInfer-Bench · Apache-2.0All results for GEMM n4096 k14336 →JSON