HPE · HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition-450W, TensorRT)
Llama-3.1-8B (MLPerf reference) · llama3.1-8b · Server · run 01a00b4a-0749…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported22,916.3 tokens_s
Llama-3.1-8B (MLPerf reference) · llama3.1-8b · Server · server · 4× NVIDIA RTX PRO 6000 Blackwell Server Edition · mlperf_closed_99 · observed 2026-03-26
Identity
modelLlama-3.1-8B (MLPerf reference)
stackTensorRT 10.11.0.33, CUDA 13.0
workloadllama3.1-8b · Server
topology4× NVIDIA RTX PRO 6000 Blackwell Server Edition
harnessmlperf_loadgen v6.0
quality policymlperf_closed_99
comparison keysha256:54245202f74d4a49…
sha256:6f69812d693a0e967392343…
Launch configuration
dtypefp4
notesGPU 450W / 600W (reduced)
systemHPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition-450W, TensorRT)
softwareTensorRT 10.11.0.33, CUDA 13.0
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": "v6.0"
},
"topology": {
"nodeCount": 1,
"acceleratorModel": "NVIDIA RTX PRO 6000 Blackwell Server Edition",
"acceleratorVendor": "nvidia",
"acceleratorsPerNode": 4
},
"observedAt": "2026-03-26T19:39:54Z",
"modelDigest": "sha256:dafdb8bb411a12b698d36856eed69f16242fb467999fb68680ca09a5601b6bd4",
"measurements": [
{
"unit": "tokens_s",
"value": 22916.3,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 22916.3
},
"category": "datacenter",
"division": "closed",
"scenario": "server",
"benchmark": "llama3.1-8b",
"externalId": "v6.0/6.0-0053"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:209ab3ba41ef397171c081377f84bcb2512e3d47cd6334278a712a3858d8eedd",
"configurationDigest": "sha256:2a2666591c956e36275de52ef0a208f88f0fe719a6faa0451f89a50a37871693"
},
"metadata": {
"name": "mlperf-v6-0-6-0-0053",
"title": "HPE · llama3.1-8b · Server",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/submissions_inference_v6.0/tree/main/closed/HPE/results/HPE_Proliant_DL385_RTX_PRO_6000_PCIe_96GBx4_TRT_10_11_0_33_TRT"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v6.0/6.0-0053 · shown unmodified as publishedAll serving results →JSON