MLPerf v6.1 Quanta 2x Xeon 6788P: 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. Scenario: Offline. System: QuantaGrid D75E-4U, 1-node-2S-GNR_86C. 2-socket 6788P. 1170.51 tok/s, close to the 2S 6787P Dell row (1227.99) — same core count and channel count, different SKU (6788P is the 4S/8S-capable part). INT8, PyTorch. measured_by vendor: these are submitter results inside the MLCommons closed division (Intel, Dell, Supermicro, Quanta, Red Hat, Cisco), not an independent re-run.

2-socket 6788P. 1170.51 tok/s, close to the 2S 6787P Dell row (1227.99) — same core count and channel count, different SKU (6788P is the 4S/8S-capable part). INT8, PyTorch.