NVIDIA just dropped the Vera Rubin NVL72 and it’s already crushing the MLPerf Inference leaderboard. Think massive GPU power, DeepSeek‑R1, Qwen3‑VL and TensorRT‑LLM running at warp speed. Dive into the numbers! #VeraRubinNVL72 #MLPerfInference #TensorRTLLM

🔗 aidailypost.com/news/nvidias...

🚀 NVIDIA just shattered the MLPerf inference record with its 288‑GPU Blackwell Ultra, cranking out insane token throughput for LLMs. Curious how this changes AI inference? Dive in for the full benchmark breakdown! #BlackwellUltra #MLPerfInference #AIInference

🔗 aidailypost.com/news/nvidias...