Quanta_Cloud_Technology · QuantaGrid D74H-7U (8x H200-SXM-141GB, TensorRT)

{
  "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": "sha256:8005d6af1339caa02e60709ce2d7a6002ce9c51e436d21bb39dc5b8f93a24b0c",
    "measurements": [
      {
        "unit": "tokens_s",
        "value": 33352.6,
        "metric": "output_token_throughput_tps",
        "statistic": "reported"
      }
    ],
    "sourceNative": {
      "source": "mlperf-inference",
      "metrics": {
        "performance_units": "Tokens/s",
        "performance_result": 33352.6
      },
      "category": "datacenter",
      "division": "closed",
      "scenario": "server",
      "benchmark": "llama2-70b-99.9",
      "externalId": "v5.1/5.1-0079"
    },
    "qualityPolicy": "mlperf_closed_99_9",
    "workloadDigest": "sha256:ee188c862b2e3bbbca29b194db4aa45d0f33b7da2bdc410aa953d53e6ad6a4ac",
    "configurationDigest": "sha256:5c9030424604ff3c359e4788c3ca5f0289b47d531ad7838913eabf4855060de8"
  },
  "metadata": {
    "name": "mlperf-v5-1-5-1-0079",
    "title": "Quanta_Cloud_Technology · llama2-70b-99.9 · Server",
    "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"
}