MLPerf v6.1 Supermicro 2x Xeon 6787P: llama3.1-8b INT8 Offline aggregate tok/s

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; the Dell notes field additionally names vLLM with an FP8 KV cache. Scenario: Offline. System: Supermicro SYS-422GB-NRT, 1-node-2S-GNR_86C. Same SKU as the Dell R770 row, different OEM. 1189.89 vs Dell 1227.99 Offline, about 3% lower. Framework column PyTorch; the Dell note naming vLLM is not repeated on this row. measured_by vendor: these are submitter results inside the MLCommons closed division (Intel, Dell, Supermicro, Quanta, Red Hat, Cisco), not an independent re-run.

Same SKU as the Dell R770 row, different OEM. 1189.89 vs Dell 1227.99 Offline, about 3% lower. Framework column PyTorch; the Dell note naming vLLM is not repeated on this row.