Lenovo · ThinkSystem SR780a V3 (8x B200-SXM-180GB, TensorRT)
Llama-3.1-8B (MLPerf reference) · llama3.1-8b · Offline · run 01a00b49-6478…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported146,960 tokens_s
Llama-3.1-8B (MLPerf reference) · llama3.1-8b · Offline · offline · 8× NVIDIA B200-SXM-180GB · mlperf_closed_99 · observed 2025-09-04
Identity
modelLlama-3.1-8B (MLPerf reference)
stackTensorRT 10.8, CUDA 12.8
workloadllama3.1-8b · Offline
topology8× NVIDIA B200-SXM-180GB
harnessmlperf_loadgen v5.1
quality policymlperf_closed_99
comparison keysha256:881c1a5517a4f678…
sha256:09f6727d4296ba7eadd9677…
Launch configuration
dtypefp4
notesB200 TGP 1000W
systemThinkSystem SR780a V3 (8x B200-SXM-180GB, TensorRT)
softwareTensorRT 10.8, CUDA 12.8
availabilityavailable
Workload
namellama3.1-8b · Offline
streamingno
load generationoffline
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": 146960,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 146960
},
"category": "datacenter",
"division": "closed",
"scenario": "offline",
"benchmark": "llama3.1-8b",
"externalId": "v5.1/5.1-0062"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:a49a37592d011507287e85cda6488466913158a2cd8c7ecb16cf07f92327bf15",
"configurationDigest": "sha256:013a5f9db053126b3efab8136cf38b2eb5b0f654c0f0290e54e07108abdb24e0"
},
"metadata": {
"name": "mlperf-v5-1-5-1-0062",
"title": "Lenovo · llama3.1-8b · Offline",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/inference_results_v5.1/tree/main/closed/Lenovo/results/SR780a_V3_B200SXMx8_TRT"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v5.1/5.1-0062 · shown unmodified as publishedAll serving results →JSON