MLPerf v3.0: Dell r7515, 4x Qualcomm Cloud AI 100 Pro, BERT-99 Offline 3059.8 samples/s

MLPerf Inference v3.0 CLOSED submission, Dell r7515 with 4x Qualcomm Cloud AI 100 Pro cards (q4_pro config, Qualcomm Apps SDK v1.8.3.7, 'aic100' backend). BERT-large SQuAD INT8, Offline scenario: throughput = completed samples/s read verbatim from performance/run_1/mlperf_log_summary.txt ('Result is : VALID ; Scheduled samples per second'). Non-LLM encoder workload; filed to give qualcomm-ai100 a verified vendor-submitted row since no public LLM tok/s exists for the base AI100 (all published LLM numbers are for the AI100 Ultra, filed under qualcomm-ai200).

3059.8 samples/s on 4 AI100 Pro = ~765/card. MLPerf v3.0 was the last round Qualcomm submitted the base AI100; v4.0+ entries are community (CTuning/glow) or the Ultra variant.