Dell · PowerEdge XE9680 (8x MI300X)
Llama-2-70B (MLPerf reference) · llama2-70b-99 · Offline · run 01a00b49-c51b…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported27,072.5 tokens_s
Llama-2-70B (MLPerf reference) · llama2-70b-99 · Offline · offline · 8× AMD Instinct MI300X 192GB HBM3 · mlperf_closed_99 · observed 2026-03-26
Identity
modelLlama-2-70B (MLPerf reference)
stackvLLM 0.9.0.2.dev108+g71faa1880.d20260213, Pytorch 2.7.0+gitf717b2a, ROCm 6.4.1
workloadllama2-70b-99 · Offline
topology8× AMD Instinct MI300X 192GB HBM3
harnessmlperf_loadgen v6.0
quality policymlperf_closed_99
comparison keysha256:f176b8802c394e7f…
sha256:f94c3b39a6864c037bca256…
Launch configuration
dtypefp8
systemPowerEdge XE9680 (8x MI300X)
softwarevLLM 0.9.0.2.dev108+g71faa1880.d20260213, Pytorch 2.7.0+gitf717b2a, ROCm 6.4.1
availabilityavailable
Workload
namellama2-70b-99 · Offline
streamingno
load generationoffline
Canonical manifest
Show manifestHide manifest
{
"kind": "ServingRun",
"spec": {
"status": "valid",
"harness": {
"name": "mlperf_loadgen",
"version": "v6.0"
},
"topology": {
"nodeCount": 1,
"acceleratorModel": "AMD Instinct MI300X 192GB HBM3",
"acceleratorVendor": "amd",
"acceleratorsPerNode": 8
},
"observedAt": "2026-03-26T19:39:54Z",
"modelDigest": "sha256:8005d6af1339caa02e60709ce2d7a6002ce9c51e436d21bb39dc5b8f93a24b0c",
"measurements": [
{
"unit": "tokens_s",
"value": 27072.5,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 27072.5
},
"category": "datacenter",
"division": "closed",
"scenario": "offline",
"benchmark": "llama2-70b-99",
"externalId": "v6.0/6.0-0019"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:65632b1fcd025d277521ab3869f904644b69e0e5322392b1d05ab8a0be7d84b9",
"configurationDigest": "sha256:745d7dccd175b0a516e5ffdf948112e12cd343eb300611500ed34dc1a34d1251"
},
"metadata": {
"name": "mlperf-v6-0-6-0-0019",
"title": "Dell · llama2-70b-99 · Offline",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/submissions_inference_v6.0/tree/main/closed/Dell/results/8xMI300X_2xPlatinum_8470"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v6.0/6.0-0019 · shown unmodified as publishedAll serving results →JSON