Quanta_Cloud_Technology · QuantaGrid D74H-7U (8x H200-SXM-141GB, TensorRT)
Llama-3.1-405B (MLPerf reference) · llama3.1-405b · Offline · run 01a00b49-888d…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported550.106 tokens_s
Llama-3.1-405B (MLPerf reference) · llama3.1-405b · Offline · offline · 8× NVIDIA H200-SXM-141GB · mlperf_closed_99 · observed 2025-09-04
Identity
modelLlama-3.1-405B (MLPerf reference)
stackTensorRT 10.8, CUDA 12.8
workloadllama3.1-405b · Offline
topology8× NVIDIA H200-SXM-141GB
harnessmlperf_loadgen v5.1
quality policymlperf_closed_99
comparison keysha256:22dad2c5e81c1ab1…
sha256:3ff6b3ccb98a5bd33e4b30e…
Launch configuration
dtypefp8
notesQuantaGrid D74H-7U
systemQuantaGrid D74H-7U (8x H200-SXM-141GB, TensorRT)
softwareTensorRT 10.8, CUDA 12.8
availabilityavailable
Workload
namellama3.1-405b · 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 H200-SXM-141GB",
"acceleratorVendor": "nvidia",
"acceleratorsPerNode": 8
},
"observedAt": "2025-09-04T19:30:14Z",
"modelDigest": "sha256:bc69ffe83643f1c91a137a177c5ef85829a1f5b65ae51771adb75ef783baf031",
"measurements": [
{
"unit": "tokens_s",
"value": 550.106,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 550.106
},
"category": "datacenter",
"division": "closed",
"scenario": "offline",
"benchmark": "llama3.1-405b",
"externalId": "v5.1/5.1-0079"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:2babc3741fcd2593147288def78c4600c4f396b6f0f7ff4bbba39445ec3cb174",
"configurationDigest": "sha256:5c9030424604ff3c359e4788c3ca5f0289b47d531ad7838913eabf4855060de8"
},
"metadata": {
"name": "mlperf-v5-1-5-1-0079",
"title": "Quanta_Cloud_Technology · llama3.1-405b · Offline",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/inference_results_v5.1/tree/main/closed/Quanta_Cloud_Technology/results/D74U-7U_H200-SXM-141GBx8_TRT"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v5.1/5.1-0079 · shown unmodified as publishedAll serving results →JSON