Dell_MangoBoost · Dell PowerEdge XE9680 (8x MI300X-192GB MangoBoost-LLMBoost)
Llama-2-70B (MLPerf reference) · llama2-70b-99 · Server · run 01a00b49-43a6…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported24,532.7 tokens_s
Llama-2-70B (MLPerf reference) · llama2-70b-99 · Server · server · 8× AMD Instinct MI300X 192GB HBM3 · mlperf_closed_99 · observed 2025-09-04
Identity
modelLlama-2-70B (MLPerf reference)
stackMango LLMBoost AI Enterprise Platform, vllm-0.9.0.2.dev108+g71faa1880.d20250717.rocm641, ROCm 6.12.12
workloadllama2-70b-99 · Server
topology8× AMD Instinct MI300X 192GB HBM3
harnessmlperf_loadgen v5.1
quality policymlperf_closed_99
comparison keysha256:5fba460825f36637…
sha256:27a8dee12d964d66262c683…
Launch configuration
dtypefp8
systemDell PowerEdge XE9680 (8x MI300X-192GB MangoBoost-LLMBoost)
softwareMango LLMBoost AI Enterprise Platform, vllm-0.9.0.2.dev108+g71faa1880.d20250717.rocm641, ROCm 6.12.12
availabilityavailable
Workload
namellama2-70b-99 · Server
streamingyes
load generationopen_loop
Canonical manifest
Show manifestHide manifest
{
"kind": "ServingRun",
"spec": {
"status": "valid",
"harness": {
"name": "mlperf_loadgen",
"version": "v5.1"
},
"topology": {
"nodeCount": 1,
"acceleratorModel": "AMD Instinct MI300X 192GB HBM3",
"acceleratorVendor": "amd",
"acceleratorsPerNode": 8
},
"observedAt": "2025-09-04T19:30:14Z",
"modelDigest": "sha256:8005d6af1339caa02e60709ce2d7a6002ce9c51e436d21bb39dc5b8f93a24b0c",
"measurements": [
{
"unit": "tokens_s",
"value": 24532.7,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 24532.7
},
"category": "datacenter",
"division": "closed",
"scenario": "server",
"benchmark": "llama2-70b-99",
"externalId": "v5.1/5.1-0031"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:ee188c862b2e3bbbca29b194db4aa45d0f33b7da2bdc410aa953d53e6ad6a4ac",
"configurationDigest": "sha256:e09f52a15be7710a9d0d4050edff2e4ab1f1b1a84fd1ca403129e38a706c5f94"
},
"metadata": {
"name": "mlperf-v5-1-5-1-0031",
"title": "Dell_MangoBoost · llama2-70b-99 · Server",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/inference_results_v5.1/tree/main/closed/Dell_MangoBoost/results/8xMI300X_2xXeon_8460Y"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v5.1/5.1-0031 · shown unmodified as publishedAll serving results →JSON