HPE · HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition-450W, 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": 4
    },
    "observedAt": "2026-03-26T19:39:54Z",
    "modelDigest": "sha256:25d396066173182e38fe499acf87750416b561f71db6feef2907188a1d59dff7",
    "measurements": [
      {
        "unit": "tokens_s",
        "value": 6687.25,
        "metric": "output_token_throughput_tps",
        "statistic": "reported"
      }
    ],
    "sourceNative": {
      "source": "mlperf-inference",
      "metrics": {
        "performance_units": "Tokens/s",
        "performance_result": 6687.25
      },
      "category": "datacenter",
      "division": "closed",
      "scenario": "server",
      "benchmark": "gpt-oss-120b",
      "externalId": "v6.0/6.0-0054"
    },
    "qualityPolicy": "mlperf_closed_99",
    "workloadDigest": "sha256:52e3b1e7fa21de01f01e265c62005486d26eb8d7086033cce45c4f87233367eb",
    "configurationDigest": "sha256:0711645a7848633e9a86e0f820e8e6f9e66270b57adc9afdf160078c9a83d3cc"
  },
  "metadata": {
    "name": "mlperf-v6-0-6-0-0054",
    "title": "HPE · gpt-oss-120b · 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_14_1_48_TRT"
      }
    ]
  },
  "apiVersion": "kernelindex.dev/v1alpha1"
}