HPE · HPE ProLiant Compute DL380a Gen12 (8x NVIDIA RTX PRO 6000 Blackwell Server Edition, TensorRT)

{
  "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": 8
    },
    "observedAt": "2026-03-26T19:39:54Z",
    "modelDigest": "sha256:dafdb8bb411a12b698d36856eed69f16242fb467999fb68680ca09a5601b6bd4",
    "measurements": [
      {
        "unit": "tokens_s",
        "value": 44087.3,
        "metric": "output_token_throughput_tps",
        "statistic": "reported"
      }
    ],
    "sourceNative": {
      "source": "mlperf-inference",
      "metrics": {
        "performance_units": "Tokens/s",
        "performance_result": 44087.3
      },
      "category": "datacenter",
      "division": "closed",
      "scenario": "interactive",
      "benchmark": "llama3.1-8b",
      "externalId": "v6.0/6.0-0047"
    },
    "qualityPolicy": "mlperf_closed_99",
    "workloadDigest": "sha256:3f1df937735a6f8382c1cfd05c637a3c3b19a79fdb50979e1c14287fbaf1fad1",
    "configurationDigest": "sha256:8f055fbf467b02c032e4aa58d4359e345a174cc0cdbcccd1daa5e2cad8f15dda"
  },
  "metadata": {
    "name": "mlperf-v6-0-6-0-0047",
    "title": "HPE · llama3.1-8b · Interactive",
    "sourceRefs": [
      {
        "url": "https://github.com/mlcommons/submissions_inference_v6.0/tree/main/closed/HPE/results/HPE_PROLIANT_DL380A_RTX_PRO_6000_PCIE_96GBx8_TRT_10_14_1_48_TRT"
      }
    ]
  },
  "apiVersion": "kernelindex.dev/v1alpha1"
}