gemini-2.5-pro_triton_zezbpc
GQA ragged prefill causal h32 kv4 d128 · total_q = 1 · total_kv = 1 · len_indptr = 2 · bf16 · run 01a02032-53a2…
●passedReported evidence
Not re-observed recently.
Primary measurement
97.6µsmean
Rank 4 in its comparison group · source-native comparison · observed 2025-10-20
43.92× reference
Identity
implementationgemini-2.5-pro_triton_zezbpc
projectgemini-2.5-pro
revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c
workloadtotal_q = 1 · total_kv = 1 · len_indptr = 2 · bf16
comparison keysha256:00934e715f484a49…
sourceFlashInfer-Bench
external idtrace/gemini-2.5-pro_triton_zezbpc/9350509c-c2da-4d5e-9585-dec9aff01725
sha256:bed38c2b4af354c71e5908b…
Correctness
comparatorflashinfer_bench_eval
max absolute error4.76837158203125e-7
max relative error0.0000023971222162799677
resultpassed
Workload
total_q1
total_kv1
len_indptr2
kbf16 [1, 4, 128]
qbf16 [1, 32, 128]
vbf16 [1, 4, 128]
kv_indptrint32 [2]
qo_indptrint32 [2]
definition comparatorsol_execbench_eval
Measurements
latency · mean97.6 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 manifestHide manifest
{
"run": {
"kind": "BenchmarkRun",
"spec": {
"status": "passed",
"timing": {
"latencyNs": {
"mean": 97562
},
"primaryStatistic": "mean"
},
"observedAt": "2025-10-20T01:06:27.760Z",
"correctness": {
"comparator": "sol_execbench_eval",
"maximumAbsoluteError": 4.76837158203125e-7,
"maximumRelativeError": 0.0000023971222162799677
},
"sourceNative": {
"source": "flashinfer-bench",
"metrics": {
"latency_ms": 0.09756154659072341,
"speedup_factor": 43.91751220067719,
"reference_latency_ms": 4.284660412715032
},
"benchmark": "gqa_ragged_prefill_causal_h32_kv4_d128"
},
"protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
"workloadDigest": "sha256:7c206ff8f67b0c628846c5775b9ddea0ae25fc1a8bdaa0c3c03e0d7a12f0ad89",
"environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
"implementationDigest": "sha256:6c278eec14ff6845c07c4715a9cbb85d5bcaf49d7b90ecfbd3baf5b1787a1641"
},
"metadata": {
"name": "sol-trace-gqa-ragged-prefill-causal-h32-kv4-d128-9350509c",
"title": "gemini-2.5-pro_triton_zezbpc · gqa_ragged_prefill_causal_h32_kv4_d128"
},
"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 GQA ragged prefill causal h32 kv4 d128 →JSON