RedHat · LLM-D v0.5.0,Openshift 4.20.12,NVIDIA 8xB200-SXM-180GB

{
  "kind": "ServingRun",
  "spec": {
    "status": "valid",
    "harness": {
      "name": "mlperf_loadgen",
      "version": "v6.0"
    },
    "topology": {
      "nodeCount": 1,
      "acceleratorModel": "NVIDIA B200-SXM-180GB",
      "acceleratorVendor": "nvidia",
      "acceleratorsPerNode": 8
    },
    "observedAt": "2026-03-26T19:39:54Z",
    "modelDigest": "sha256:25d396066173182e38fe499acf87750416b561f71db6feef2907188a1d59dff7",
    "measurements": [
      {
        "unit": "tokens_s",
        "value": 93070.7,
        "metric": "output_token_throughput_tps",
        "statistic": "reported"
      }
    ],
    "sourceNative": {
      "source": "mlperf-inference",
      "metrics": {
        "performance_units": "Tokens/s",
        "performance_result": 93070.7
      },
      "category": "datacenter",
      "division": "closed",
      "scenario": "offline",
      "benchmark": "gpt-oss-120b",
      "externalId": "v6.0/6.0-0091"
    },
    "qualityPolicy": "mlperf_closed_99",
    "workloadDigest": "sha256:51bf73d7ec6f9d34eac7dec515275ae3acd0890eeab2278cd6c99b7a889352ee",
    "configurationDigest": "sha256:fafb3d4433929dfd688ebfb37a2c1536b37737a47d7139c2aa51f18755a858b8"
  },
  "metadata": {
    "name": "mlperf-v6-0-6-0-0091",
    "title": "RedHat · gpt-oss-120b · Offline",
    "sourceRefs": [
      {
        "url": "https://github.com/mlcommons/submissions_inference_v6.0/tree/main/closed/RedHat/results/8xB200-LLM-D-Openshift"
      }
    ]
  },
  "apiVersion": "kernelindex.dev/v1alpha1"
}