Supermicro · SYS-422GA-NBRT-LCC (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:bc69ffe83643f1c91a137a177c5ef85829a1f5b65ae51771adb75ef783baf031",
    "measurements": [
      {
        "unit": "tokens_s",
        "value": 1641.34,
        "metric": "output_token_throughput_tps",
        "statistic": "reported"
      }
    ],
    "sourceNative": {
      "source": "mlperf-inference",
      "metrics": {
        "performance_units": "Tokens/s",
        "performance_result": 1641.34
      },
      "category": "datacenter",
      "division": "closed",
      "scenario": "offline",
      "benchmark": "llama3.1-405b",
      "externalId": "v5.1/5.1-0087"
    },
    "qualityPolicy": "mlperf_closed_99",
    "workloadDigest": "sha256:2babc3741fcd2593147288def78c4600c4f396b6f0f7ff4bbba39445ec3cb174",
    "configurationDigest": "sha256:538be0e50b2920802de31fadca6ca58a2cac8680d2493d8ff1cd9e0c4400f30b"
  },
  "metadata": {
    "name": "mlperf-v5-1-5-1-0087",
    "title": "Supermicro · llama3.1-405b · Offline",
    "sourceRefs": [
      {
        "url": "https://github.com/mlcommons/inference_results_v5.1/tree/main/closed/Supermicro/results/SYS-422GA-NBRT-LCC_B200-SXM-180GBx8_TRT"
      }
    ]
  },
  "apiVersion": "kernelindex.dev/v1alpha1"
}