MLPerf v6.1 Intel 2x Xeon 6980P: llama3.1-8b INT8 Server 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: Server. System: Intel 1-node-2S-GNR_128C. Same system as the Offline row. Server scenario is latency-constrained aggregate throughput, still not per-request decode. 1139.51 tok/s across two 128-core sockets. 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 system as the Offline row. Server scenario is latency-constrained aggregate throughput, still not per-request decode. 1139.51 tok/s across two 128-core sockets.