Skip to content
KernelIndex
Search⌘K

AMD · QuantaGrid D74A-7U

Mixtral-8x7B (MLPerf reference) · mixtral-8x7b · Offline · run 01a00b49-10df…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported68,781.4 tokens_s

Mixtral-8x7B (MLPerf reference) · mixtral-8x7b · Offline · offline · 8× AMD Instinct MI325X 256GB HBM3e · mlperf_closed_99 · observed 2025-09-04

Identity
modelMixtral-8x7B (MLPerf reference)
stackvLLM 0.9.0.2.dev108+g71faa1880.d20250731.rocm641, Pytorch 2.7.0+gitf717b2a, ROCm 6.4.1.60401-83~22.04
workloadmixtral-8x7b · Offline
topology8× AMD Instinct MI325X 256GB HBM3e
harnessmlperf_loadgen v5.1
quality policymlperf_closed_99
comparison keysha256:8857f8343595f777…
sha256:90d236c9882233f61435831…

Launch configuration

dtypefp8
notesMachine 1
systemQuantaGrid D74A-7U
softwarevLLM 0.9.0.2.dev108+g71faa1880.d20250731.rocm641, Pytorch 2.7.0+gitf717b2a, ROCm 6.4.1.60401-83~22.04
availabilityavailable

Workload

namemixtral-8x7b · Offline
streamingno
load generationoffline

Canonical manifest

Show manifest
{
  "kind": "ServingRun",
  "spec": {
    "status": "valid",
    "harness": {
      "name": "mlperf_loadgen",
      "version": "v5.1"
    },
    "topology": {
      "nodeCount": 1,
      "acceleratorModel": "AMD Instinct MI325X 256GB HBM3e",
      "acceleratorVendor": "amd",
      "acceleratorsPerNode": 8
    },
    "observedAt": "2025-09-04T19:30:14Z",
    "modelDigest": "sha256:80245861fefd582d681d995dd4a278c0f97669415a5a9ee66bcab60e81a11738",
    "measurements": [
      {
        "unit": "tokens_s",
        "value": 68781.4,
        "metric": "output_token_throughput_tps",
        "statistic": "reported"
      }
    ],
    "sourceNative": {
      "source": "mlperf-inference",
      "metrics": {
        "performance_units": "Tokens/s",
        "performance_result": 68781.4
      },
      "category": "datacenter",
      "division": "closed",
      "scenario": "offline",
      "benchmark": "mixtral-8x7b",
      "externalId": "v5.1/5.1-0002"
    },
    "qualityPolicy": "mlperf_closed_99",
    "workloadDigest": "sha256:366e126d007ff4f040d0b49b8fa0235cd4a80ba470adf70d3d04fc323956e9df",
    "configurationDigest": "sha256:b4f96468183a2fa131b81a4a13bf269dab6b76d567eae2d225c29b53e20edc6c"
  },
  "metadata": {
    "name": "mlperf-v5-1-5-1-0002",
    "title": "AMD · mixtral-8x7b · Offline",
    "sourceRefs": [
      {
        "url": "https://github.com/mlcommons/inference_results_v5.1/tree/main/closed/AMD/results/8xMI325X_2xEPYC_9575F_1"
      }
    ]
  },
  "apiVersion": "kernelindex.dev/v1alpha1"
}
Cite this result (permalink, digest, access date)
Report an issue with this serving run

A maintainer reviews every report. If accepted, the record is retracted or superseded; its history stays visible.