MLPerf v6.1 Supermicro 2x Xeon 6980P: llama3.1-8b INT8 Server aggregate tok/s
1101.19 tok/s AGGREGATE over 2x Xeon 6980P (Server scenario)
Fields
id
benchmarks/mlperf-v6-1-smci-2x6980p-llama31-8b-int8-serverMetric
tps_aggregate
Value
1,101.19
Unit
tok/s AGGREGATE over 2x Xeon 6980P (Server scenario)
Model
llama3.1-8b
Methodology
MLPerf Inference v6.1 closed division, CPU-only (summary.csv accelerator_model_name is N/A). Values copied from summary.csv, not from a per-system mlperf_log_summary.txt. AGGREGATE throughput for the whole node, NOT per-request decode and NOT per-socket. Prompt length, output length, and batch size are not in the summary row. weight_data_types INT8. Framework column is PyTorch. Scenario: Server. System: Supermicro SYS-422GA-NRT, 1-node-2S-GNR_128C. Server scenario companion to the Supermicro Offline row. 1101.19 vs Intel's 1139.51. measured_by vendor: these are submitter results inside the MLCommons closed division (Intel, Dell, Supermicro, Quanta, Red Hat, Cisco), not an independent re-run.
Measured by
vendor
Reproducible
yes
notes
Server scenario companion to the Supermicro Offline row. 1101.19 vs Intel's 1139.51.
Notes
Server scenario companion to the Supermicro Offline row. 1101.19 vs Intel's 1139.51.