MLPerf v6.1 MangoBoost 8x MI300X (stock vLLM 0.24.0 ROCm): gpt-oss-120b Server 24863 tok/s
24863.0 tok/s aggregate Server
Fields
id
benchmarks/mlperf-v6-1-mangoboost-8xmi300x-gptoss-120b-server-tokensMetric
tps_aggregate
Value
24,863
Unit
tok/s aggregate Server
Model
gpt-oss-120b
Methodology
MLPerf Inference v6.1 published result (8xMI300X_2xEPYC_9534; software: vLLM 0.24.0 (stock vllm/vllm-openai-rocm:v0.24.0), ROCm 7.2.1). 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.