AMD · AMD MI355X Custom Cluster
Llama-2-70B (MLPerf reference) · llama2-70b-99 · Server · run 01a00b49-ab68…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported1,016,380 tokens_s
Llama-2-70B (MLPerf reference) · llama2-70b-99 · Server · server · 8× AMD Instinct MI355X 288GB HBM3e × 11 nodes · mlperf_closed_99_9 · observed 2026-03-26
Identity
modelLlama-2-70B (MLPerf reference)
stackPyTorch 2.9.1+git8907517, ROCm 7.0.0
workloadllama2-70b-99 · Server
topology8× AMD Instinct MI355X 288GB HBM3e × 11 nodes
harnessmlperf_loadgen v6.0
quality policymlperf_closed_99_9
comparison keysha256:2393fc5a3caba6d3…
sha256:527430d7aa7f32e64c6d43c…
Launch configuration
dtypefp4
systemAMD MI355X Custom Cluster
softwarePyTorch 2.9.1+git8907517, ROCm 7.0.0
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": "v6.0"
},
"topology": {
"nodeCount": 11,
"acceleratorModel": "AMD Instinct MI355X 288GB HBM3e",
"acceleratorVendor": "amd",
"acceleratorsPerNode": 8
},
"observedAt": "2026-03-26T19:39:54Z",
"modelDigest": "sha256:8005d6af1339caa02e60709ce2d7a6002ce9c51e436d21bb39dc5b8f93a24b0c",
"measurements": [
{
"unit": "tokens_s",
"value": 1016380,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 1016380
},
"category": "datacenter",
"division": "closed",
"scenario": "server",
"benchmark": "llama2-70b-99.9",
"externalId": "v6.0/6.0-0001"
},
"qualityPolicy": "mlperf_closed_99_9",
"workloadDigest": "sha256:ee188c862b2e3bbbca29b194db4aa45d0f33b7da2bdc410aa953d53e6ad6a4ac",
"configurationDigest": "sha256:930a75706083243c9b0fd418dceb89a5cd68fd232ca3bd080dfc9c18b139216d"
},
"metadata": {
"name": "mlperf-v6-0-6-0-0001",
"title": "AMD · llama2-70b-99.9 · Server",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/submissions_inference_v6.0/tree/main/closed/AMD/results/87xMI355X_22xEPYC_9575F"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v6.0/6.0-0001 · shown unmodified as publishedAll serving results →JSON