MLPerf v6.1 Intel 1-node-4x-BMG-B70: llama2-70b-99.9 Server 1745.48 tok/s
1745.48 tok/s aggregate Server
Fields
id
benchmarks/mlperf-v6-1-intel-4xarcb70-llama2-70b-server-tokensMetric
tps_aggregate
Value
1,745.48
Unit
tok/s aggregate Server
Model
Llama-2-70B (99.9 acc)
Methodology
MLPerf Inference v6.1 published result (Intel 1-node-4x-BMG-B70, 4x Arc Pro B70 32GB, Xeon host; 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.