MLPerf v6.1 Supermicro 1-node-4x-BMG-B70: llama2-70b-99.9 Offline 2484.14 tok/s
2484.14 tok/s aggregate Offline
Fields
id
benchmarks/mlperf-v6-1-supermicro-4xarcb70-llama2-70b-offline-tokensMetric
tps_aggregate
Value
2,484.14
Unit
tok/s aggregate Offline
Model
Llama-2-70B (99.9 acc)
Methodology
MLPerf Inference v6.1 published result (Supermicro 1-node-4x-BMG-B70, 4x Arc Pro B70; software: PyTorch). System-AGGREGATE output tokens/s for the named scenario, submitter-measured under MLCommons audit.
Measured by
vendor
Reproducible
yes
notes
ENGINE_ID NOTE: pinned to 'vllm' as the closest existing engine record; the submission's actual stack is named in this methodology string.
Notes
ENGINE_ID NOTE: pinned to 'vllm' as the closest existing engine record; the submission's actual stack is named in this methodology string.