Cisco · Cisco UCS C880A M8 (8x NVIDIA B300-SXM-270GB, TensorRT)
Llama-2-70B (MLPerf reference) · llama2-70b-99 · Server · run 01a00b49-bb23…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported114,504 tokens_s
Llama-2-70B (MLPerf reference) · llama2-70b-99 · Server · server · 8× NVIDIA B300-SXM-270GB · mlperf_closed_99 · observed 2026-03-26
Identity
modelLlama-2-70B (MLPerf reference)
stackTensorRT 10.13, CUDA 13.0
workloadllama2-70b-99 · Server
topology8× NVIDIA B300-SXM-270GB
harnessmlperf_loadgen v6.0
quality policymlperf_closed_99
comparison keysha256:247f375438ca9285…
sha256:6c2c69d9e1438b750d2949b…
Launch configuration
dtypefp4
notesB300 TGP 1100W
systemCisco UCS C880A M8 (8x NVIDIA B300-SXM-270GB, TensorRT)
softwareTensorRT 10.13, CUDA 13.0
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": 1,
"acceleratorModel": "NVIDIA B300-SXM-270GB",
"acceleratorVendor": "nvidia",
"acceleratorsPerNode": 8
},
"observedAt": "2026-03-26T19:39:54Z",
"modelDigest": "sha256:8005d6af1339caa02e60709ce2d7a6002ce9c51e436d21bb39dc5b8f93a24b0c",
"measurements": [
{
"unit": "tokens_s",
"value": 114504,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 114504
},
"category": "datacenter",
"division": "closed",
"scenario": "server",
"benchmark": "llama2-70b-99",
"externalId": "v6.0/6.0-0010"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:ee188c862b2e3bbbca29b194db4aa45d0f33b7da2bdc410aa953d53e6ad6a4ac",
"configurationDigest": "sha256:adff1ce510400b673c416b82c299f7f607c1a8ffc7a209d968c71f1244f52162"
},
"metadata": {
"name": "mlperf-v6-0-6-0-0010",
"title": "Cisco · llama2-70b-99 · Server",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/submissions_inference_v6.0/tree/main/closed/Cisco/results/C880A_M8_B300_288GBx8_TRT"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v6.0/6.0-0010 · shown unmodified as publishedAll serving results →JSON