MLPerf v6.1 Dell XE7745 8x MI350P: llama2-70b-99.9 Server 41830 tok/s
41830.0 tok/s aggregate Server
Fields
id
benchmarks/mlperf-v6-1-dell-8xmi350p-llama2-70b-server-tokensMetric
tps_aggregate
Value
41,830
Unit
tok/s aggregate Server
Model
Llama-2-70B (99.9 acc)
Methodology
MLPerf Inference v6.1 published result (Dell XE7745 8x MI350P, 2x EPYC 9455; software: vLLM 0.22.0, PyTorch 2.10.0, ROCm 7.2.2). 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.