Oracle · BM.GPU.B200.8
Llama-3.1-8B (MLPerf reference) · llama3.1-8b · Server · run 01a00b49-862e…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported128,649 tokens_s
Llama-3.1-8B (MLPerf reference) · llama3.1-8b · Server · server · 8× NVIDIA B200-SXM-180GB · mlperf_closed_99 · observed 2025-09-04
Identity
modelLlama-3.1-8B (MLPerf reference)
stackTensorRT 10.11, CUDA 12.9
workloadllama3.1-8b · Server
topology8× NVIDIA B200-SXM-180GB
harnessmlperf_loadgen v5.1
quality policymlperf_closed_99
comparison keysha256:55612aa308f35a63…
sha256:e8fe80568e97837b99c675f…
Launch configuration
dtypefp4
notesB200 TGP 1000W
systemBM.GPU.B200.8
softwareTensorRT 10.11, CUDA 12.9
availabilityavailable
Workload
namellama3.1-8b · Server
streamingyes
load generationopen_loop
Canonical manifest
Show manifestHide manifest
{
"kind": "ServingRun",
"spec": {
"status": "valid",
"harness": {
"name": "mlperf_loadgen",
"version": "v5.1"
},
"topology": {
"nodeCount": 1,
"acceleratorModel": "NVIDIA B200-SXM-180GB",
"acceleratorVendor": "nvidia",
"acceleratorsPerNode": 8
},
"observedAt": "2025-09-04T19:30:14Z",
"modelDigest": "sha256:dafdb8bb411a12b698d36856eed69f16242fb467999fb68680ca09a5601b6bd4",
"measurements": [
{
"unit": "tokens_s",
"value": 128649,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 128649
},
"category": "datacenter",
"division": "closed",
"scenario": "server",
"benchmark": "llama3.1-8b",
"externalId": "v5.1/5.1-0076"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:209ab3ba41ef397171c081377f84bcb2512e3d47cd6334278a712a3858d8eedd",
"configurationDigest": "sha256:9563615440612fca75ecf7678599c41e56d31d7a3874fed2f0ecc865a8652637"
},
"metadata": {
"name": "mlperf-v5-1-5-1-0076",
"title": "Oracle · llama3.1-8b · Server",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/inference_results_v5.1/tree/main/closed/Oracle/results/B200-SXM-180GBx8_TRT"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v5.1/5.1-0076 · shown unmodified as publishedAll serving results →JSON