Google · NVIDIA DGX B200 (8x B200-SXM-180GB, TensorRT)

{
  "kind": "ServingRun",
  "spec": {
    "status": "valid",
    "harness": {
      "name": "mlperf_loadgen",
      "version": "v5.1"
    },
    "topology": {
      "nodeCount": 1,
      "acceleratorModel": "NVIDIA B200-SXM-180GB",
      "acceleratorVendor": "nvidia",
      "acceleratorsPerNode": 8
    },
    "observedAt": "2025-09-04T19:30:14Z",
    "modelDigest": "sha256:9c4d3f416e476a367a8351b29d53c726179e98b9f039335873b937afb40e7c29",
    "measurements": [
      {
        "unit": "tokens_s",
        "value": 31920.3,
        "metric": "output_token_throughput_tps",
        "statistic": "reported"
      }
    ],
    "sourceNative": {
      "source": "mlperf-inference",
      "metrics": {
        "performance_units": "Tokens/s",
        "performance_result": 31920.3
      },
      "category": "datacenter",
      "division": "closed",
      "scenario": "offline",
      "benchmark": "deepseek-r1",
      "externalId": "v5.1/5.1-0047"
    },
    "qualityPolicy": "mlperf_closed_99",
    "workloadDigest": "sha256:20751717faabf71240c85d6eb6b522cbec69414c79482674b84366cd6db70be5",
    "configurationDigest": "sha256:4d8f1912136672ed41ee1e85dad233cd0253d2c8f2b4a037eb941a619c7abad1"
  },
  "metadata": {
    "name": "mlperf-v5-1-5-1-0047",
    "title": "Google · deepseek-r1 · Offline",
    "sourceRefs": [
      {
        "url": "https://github.com/mlcommons/inference_results_v5.1/tree/main/closed/Google/results/B200-SXM-180GBx8_TRT"
      }
    ]
  },
  "apiVersion": "kernelindex.dev/v1alpha1"
}