gemini-2.5-pro_triton_zezbpc
GQA ragged prefill causal h32 kv4 d128 · total_q = 969 · total_kv = 969 · len_indptr = 16 · bf16 · run 01a02032-53a5…
●passedReported evidence
Not re-observed recently.
Primary measurement
563.0µsmean
Rank 2 in its comparison group · source-native comparison · observed 2025-10-20
72.33× reference
Identity
implementationgemini-2.5-pro_triton_zezbpc
projectgemini-2.5-pro
revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c
workloadtotal_q = 969 · total_kv = 969 · len_indptr = 16 · bf16
comparison keysha256:d263e8051b2ab468…
sourceFlashInfer-Bench
external idtrace/gemini-2.5-pro_triton_zezbpc/b3445888-8668-4721-9359-9da119ab9f34
sha256:ae7e5b3f8e2b1620bee55d1…
Correctness
comparatorflashinfer_bench_eval
max absolute error0.00390625
max relative error1.8219667673110962
resultpassed
Workload
total_q969
total_kv969
len_indptr16
kbf16 [969, 4, 128]
qbf16 [969, 32, 128]
vbf16 [969, 4, 128]
kv_indptrint32 [16]
qo_indptrint32 [16]
definition comparatorsol_execbench_eval
Measurements
latency · mean563.0 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": 563041
},
"primaryStatistic": "mean"
},
"observedAt": "2025-10-20T01:08:35.924Z",
"correctness": {
"comparator": "sol_execbench_eval",
"maximumAbsoluteError": 0.00390625,
"maximumRelativeError": 1.8219667673110962
},
"sourceNative": {
"source": "flashinfer-bench",
"metrics": {
"latency_ms": 0.5630413987182569,
"speedup_factor": 72.33027186219996,
"reference_latency_ms": 40.724937438964844
},
"benchmark": "gqa_ragged_prefill_causal_h32_kv4_d128"
},
"protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
"workloadDigest": "sha256:700527a4350d7f0e3c9cbd5650c827fc25e2a7bc5af80107e2db436a6ff8bcce",
"environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
"implementationDigest": "sha256:6c278eec14ff6845c07c4715a9cbb85d5bcaf49d7b90ecfbd3baf5b1787a1641"
},
"metadata": {
"name": "sol-trace-gqa-ragged-prefill-causal-h32-kv4-d128-b3445888",
"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