NVIDIA · NVIDIA GB200 NVL72 (72x GB200-186GB_aarch64, TensorRT)
DeepSeek-R1 (MLPerf reference) · deepseek-r1 · Server · run 01a00b4a-26ca…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported336,106 tokens_s
DeepSeek-R1 (MLPerf reference) · deepseek-r1 · Server · server · 4× NVIDIA GB200 × 18 nodes · mlperf_closed_99 · observed 2026-03-26
Identity
modelDeepSeek-R1 (MLPerf reference)
stackTensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentM
workloaddeepseek-r1 · Server
topology4× NVIDIA GB200 × 18 nodes
harnessmlperf_loadgen v6.0
quality policymlperf_closed_99
comparison keysha256:3b12dc71b58553e3…
sha256:771d23b09648fad617f66c8…
Launch configuration
dtypefp4
notesNVIDIA GB200 NVL72, 1200W TGP Per GPU
systemNVIDIA GB200 NVL72 (72x GB200-186GB_aarch64, TensorRT)
softwareTensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
availabilityavailable
Workload
namedeepseek-r1 · Server
streamingyes
load generationopen_loop
Canonical manifest
Show manifestHide manifest
{
"kind": "ServingRun",
"spec": {
"status": "valid",
"harness": {
"name": "mlperf_loadgen",
"version": "v6.0"
},
"topology": {
"nodeCount": 18,
"acceleratorModel": "NVIDIA GB200",
"acceleratorVendor": "nvidia",
"acceleratorsPerNode": 4
},
"observedAt": "2026-03-26T19:39:54Z",
"modelDigest": "sha256:9c4d3f416e476a367a8351b29d53c726179e98b9f039335873b937afb40e7c29",
"measurements": [
{
"unit": "tokens_s",
"value": 336106,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 336106
},
"category": "datacenter",
"division": "closed",
"scenario": "server",
"benchmark": "deepseek-r1",
"externalId": "v6.0/6.0-0075"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:51ac3e54124be56b08b48d2e88fb8878fda1ff10c64431a52e66b4530fc4d7d9",
"configurationDigest": "sha256:65fb87c0e4d4c4a1f32024f738291a53d1e243bac2f704a29cdf7a9d9bd977bc"
},
"metadata": {
"name": "mlperf-v6-0-6-0-0075",
"title": "NVIDIA · deepseek-r1 · Server",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/submissions_inference_v6.0/tree/main/closed/NVIDIA/results/GB200-NVL72_GB200-186GB_aarch64x72_TRT"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v6.0/6.0-0075 · shown unmodified as publishedAll serving results →JSON