HPE · HPE ProLiant DL385 Gen11 (2x NVIDIA RTX PRO 6000 Blackwell Server Edition-600W, 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": 2
    },
    "observedAt": "2026-03-26T19:39:54Z",
    "modelDigest": "sha256:80245861fefd582d681d995dd4a278c0f97669415a5a9ee66bcab60e81a11738",
    "measurements": [
      {
        "unit": "tokens_s",
        "value": 8198.25,
        "metric": "output_token_throughput_tps",
        "statistic": "reported"
      }
    ],
    "sourceNative": {
      "source": "mlperf-inference",
      "metrics": {
        "performance_units": "Tokens/s",
        "performance_result": 8198.25
      },
      "category": "datacenter",
      "division": "closed",
      "scenario": "offline",
      "benchmark": "mixtral-8x7b",
      "externalId": "v6.0/6.0-0051"
    },
    "qualityPolicy": "mlperf_closed_99",
    "workloadDigest": "sha256:366e126d007ff4f040d0b49b8fa0235cd4a80ba470adf70d3d04fc323956e9df",
    "configurationDigest": "sha256:76b917e2fda1de680404f003b1d081157b0d0b0a3f6ebea2239498101530dacb"
  },
  "metadata": {
    "name": "mlperf-v6-0-6-0-0051",
    "title": "HPE · mixtral-8x7b · Offline",
    "sourceRefs": [
      {
        "url": "https://github.com/mlcommons/submissions_inference_v6.0/tree/main/closed/HPE/results/HPE_Proliant_DL385_RTX_PRO_6000_PCIe_96GBx2_TRT_10_11_0_33_TRT"
      }
    ]
  },
  "apiVersion": "kernelindex.dev/v1alpha1"
}