gpt-o3 / cuda9abd34
GQA ragged prefill causal h32 kv4 d128 · total_q = 34 · total_kv = 34 · len_indptr = 2 · bf16 · run 01a02032-5e34…
●passedReported evidence
Not re-observed recently.
Primary measurement
215.0µsmean
Rank 4 in its comparison group · source-native comparison · observed 2025-10-20
24.15× reference
Identity
implementationgpt-o3_cuda_9abd34
projectgpt-o3
revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c
workloadtotal_q = 34 · total_kv = 34 · len_indptr = 2 · bf16
comparison keysha256:8a8ef34a805636b0…
sourceFlashInfer-Bench
external idtrace/gpt-o3_cuda_9abd34/3ca7457e-e4b1-42a4-b6c7-c0b37c461054
sha256:58ab0123113513be845fb8e…
Correctness
comparatorflashinfer_bench_eval
max absolute error0.001953125
max relative error0.06107652187347412
resultpassed
Workload
total_q34
total_kv34
len_indptr2
kbf16 [34, 4, 128]
qbf16 [34, 32, 128]
vbf16 [34, 4, 128]
kv_indptrint32 [2]
qo_indptrint32 [2]
definition comparatorsol_execbench_eval
Measurements
latency · mean215.0 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": 214968
},
"primaryStatistic": "mean"
},
"observedAt": "2025-10-20T01:06:37.992Z",
"correctness": {
"comparator": "sol_execbench_eval",
"maximumAbsoluteError": 0.001953125,
"maximumRelativeError": 0.06107652187347412
},
"sourceNative": {
"source": "flashinfer-bench",
"metrics": {
"latency_ms": 0.21496787453510424,
"speedup_factor": 24.15403571619253,
"reference_latency_ms": 5.192341719354903
},
"benchmark": "gqa_ragged_prefill_causal_h32_kv4_d128"
},
"protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
"workloadDigest": "sha256:816a2cbeb81a5575a845db1b0158c1a9a7c7277239ec6f15354a6dde24fc00e5",
"environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
"implementationDigest": "sha256:3a73a83021dd9abc23c3f9cf84a55ebd359eadfde4346501fc90586dd7f3116c"
},
"metadata": {
"name": "sol-trace-gqa-ragged-prefill-causal-h32-kv4-d128-3ca7457e",
"title": "gpt-o3_cuda_9abd34 · 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