Supermicro · SYS-A21GE-NBRT (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": 1242.84,
        "metric": "output_token_throughput_tps",
        "statistic": "reported"
      }
    ],
    "sourceNative": {
      "source": "mlperf-inference",
      "metrics": {
        "performance_units": "Tokens/s",
        "performance_result": 1242.84
      },
      "category": "datacenter",
      "division": "closed",
      "scenario": "server",
      "benchmark": "llama3.1-405b",
      "externalId": "v5.1/5.1-0089"
    },
    "qualityPolicy": "mlperf_closed_99",
    "workloadDigest": "sha256:3428d964054278646d17c2f6064b4e29982b970b7fa607362cf50b7f7dff994c",
    "configurationDigest": "sha256:b75580cb87447c0d914a266b56ca64183f4a60f4c96df17f5d0cd13e81687ec7"
  },
  "metadata": {
    "name": "mlperf-v5-1-5-1-0089",
    "title": "Supermicro · llama3.1-405b · Server",
    "sourceRefs": [
      {
        "url": "https://github.com/mlcommons/inference_results_v5.1/tree/main/closed/Supermicro/results/SYS-A21GE-NBRT_B200-SXM-180GBx8_TRT"
      }
    ]
  },
  "apiVersion": "kernelindex.dev/v1alpha1"
}