gpt-o3 / tritonc1adb5
MoE FP8 block scale ds routing topk8 ng8 kg4 e32 h7168 i2048 · seq_len = 56 · bf16/fp32/fp8_e4m3 · run 01a02032-5e49…
●passedReported evidence
Not re-observed recently.
Primary measurement
14.2msmean
Rank 2 in its comparison group · source-native comparison · observed 2025-10-16
1.12× reference
Identity
implementationgpt-o3_triton_c1adb5
projectgpt-o3
revisionda915083d4c7c5e61aa3005e3d17ae488e0fc71c
workloadseq_len = 56 · bf16/fp32/fp8_e4m3
comparison keysha256:4f9d2d4df6e384fa…
sourceFlashInfer-Bench
external idtrace/gpt-o3_triton_c1adb5/4822167c-dae5-4bb1-bb53-e4adb256245b
sha256:d0248bc4d6ba74e2127127a…
Correctness
comparatorflashinfer_bench_eval
max absolute error0
max relative error0
resultpassed
Workload
seq_len56
routing_biasbf16 [256]
gemm1_weightsfp8_e4m3 [32, 4096, 7168]
gemm2_weightsfp8_e4m3 [32, 7168, 2048]
hidden_statesfp8_e4m3 [56, 7168]
routing_logitsfp32 [56, 256]
gemm1_weights_scalefp32 [32, 32, 56]
gemm2_weights_scalefp32 [32, 56, 16]
hidden_states_scalefp32 [56, 56]
definition comparatorsol_execbench_eval
Measurements
latency · mean14.2 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": 14197767
},
"primaryStatistic": "mean"
},
"observedAt": "2025-10-16T12:03:56.167Z",
"correctness": {
"comparator": "sol_execbench_eval",
"maximumAbsoluteError": 0,
"maximumRelativeError": 0
},
"sourceNative": {
"source": "flashinfer-bench",
"metrics": {
"latency_ms": 14.19776693979899,
"speedup_factor": 1.1167530217254982,
"reference_latency_ms": 15.855399131774902
},
"benchmark": "moe_fp8_block_scale_ds_routing_topk8_ng8_kg4_e32_h7168_i2048"
},
"protocolDigest": "sha256:7d44d206ad086b4bece35ce31f6531ebb11f07e0d9dcfb74c75be86d3ec02095",
"workloadDigest": "sha256:97f60afea9a2100d5eb24536e720ebf59891760a8a1aa9f876c402b316724c88",
"environmentDigest": "sha256:f4292a8be127b7230cd3995c1d605fb6c644e2c2f94566e1d28cc1be766ca5d5",
"implementationDigest": "sha256:e8b341c734b04e27659037ec4b0820b5559972d3f9df8f7b7d2164a09b3f86ce"
},
"metadata": {
"name": "sol-trace-moe-fp8-block-scale-ds-routing-topk8-ng8-kg4-e32-h7168-i2048-4822167c",
"title": "gpt-o3_triton_c1adb5 · moe_fp8_block_scale_ds_routing_topk8_ng8_kg4_e32_h7168_i2048"
},
"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 MoE FP8 block scale ds routing topk8 ng8 kg4 e32 h7168 i2048 →JSON