AMD · Supermicro AS-8125GS-TNMR2
Llama-2-70B (MLPerf reference) · llama2-70b-99 · Interactive · run 01a00b49-0b2c…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported8,840.42 tokens_s
Llama-2-70B (MLPerf reference) · llama2-70b-99 · Interactive · interactive · 8× AMD Instinct MI300X 192GB HBM3 · mlperf_closed_99 · observed 2025-09-04
Identity
modelLlama-2-70B (MLPerf reference)
stackvLLM 0.9.0.2.dev108+g71faa1880.d20250730.rocm641, Pytorch 2.7.0+gitf717b2a, ROCm 6.4.1.60401-83~22.04
workloadllama2-70b-99 · Interactive
topology8× AMD Instinct MI300X 192GB HBM3
harnessmlperf_loadgen v5.1
quality policymlperf_closed_99
comparison keysha256:17713b9e814d10ad…
sha256:cf776f5ecc9fb9ba277b1d2…
Launch configuration
dtypefp8
systemSupermicro AS-8125GS-TNMR2
softwarevLLM 0.9.0.2.dev108+g71faa1880.d20250730.rocm641, Pytorch 2.7.0+gitf717b2a, ROCm 6.4.1.60401-83~22.04
availabilityavailable
Workload
namellama2-70b-99 · Interactive
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": 8840.42,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 8840.42
},
"category": "datacenter",
"division": "closed",
"scenario": "interactive",
"benchmark": "llama2-70b-99",
"externalId": "v5.1/5.1-0001"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:fec425e36d7e44b87a9f9ed1f29e0e9e07a28fb47dd30a4f7a618a7956a6bcf9",
"configurationDigest": "sha256:05015d6baaddc3ddb96db819a7dca7ca644a5dcf55c0488a5368df33c41a0794"
},
"metadata": {
"name": "mlperf-v5-1-5-1-0001",
"title": "AMD · llama2-70b-99 · Interactive",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/inference_results_v5.1/tree/main/closed/AMD/results/8xMI300X_2xEPYC_9575F"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v5.1/5.1-0001 · shown unmodified as publishedAll serving results →JSON