GigaComputing · G894-SD3-AAX7
DeepSeek-R1 (MLPerf reference) · deepseek-r1 · Interactive · run 01a00b49-e189…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported4,934.65 tokens_s
DeepSeek-R1 (MLPerf reference) · deepseek-r1 · Interactive · interactive · 8× NVIDIA B300-SXM-270GB · mlperf_closed_99 · observed 2026-03-26
Identity
modelDeepSeek-R1 (MLPerf reference)
stackTensorRT 10.14, CUDA 13.1
workloaddeepseek-r1 · Interactive
topology8× NVIDIA B300-SXM-270GB
harnessmlperf_loadgen v6.0
quality policymlperf_closed_99
comparison keysha256:62d493bbeafa545d…
sha256:3cb88dbac50efc45617bfed…
Launch configuration
dtypefp4
notesB300 TGP 1100W
systemG894-SD3-AAX7
softwareTensorRT 10.14, CUDA 13.1
availabilityavailable
Workload
namedeepseek-r1 · Interactive
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": "sha256:9c4d3f416e476a367a8351b29d53c726179e98b9f039335873b937afb40e7c29",
"measurements": [
{
"unit": "tokens_s",
"value": 4934.65,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 4934.65
},
"category": "datacenter",
"division": "closed",
"scenario": "interactive",
"benchmark": "deepseek-r1",
"externalId": "v6.0/6.0-0039"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:3051ae4be57a54fd73bff877d8a31001a5234ee890caf3fbf2b298941b096cc8",
"configurationDigest": "sha256:5d028f4b770dd052789f88f26d9b28237d6a8218d10216524e5fb3195c1dd10f"
},
"metadata": {
"name": "mlperf-v6-0-6-0-0039",
"title": "GigaComputing · deepseek-r1 · Interactive",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/submissions_inference_v6.0/tree/main/closed/GigaComputing/results/G894-SD3-AAX7_B300-SXM-270GBx8_TRT"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v6.0/6.0-0039 · shown unmodified as publishedAll serving results →JSON