SemiAnalysis_· @SemiAnalysis_ · X·· 2 天前AI 评分
NVIDIA Rubin推理性能与利润优势分析
HOLY ALERT🚨: NVIDIA vLLM INFERENCE RUBIN IS 3.2x BETTER IN PROFIT💰️ PER GIGAWATT & HAS UP TO 🚀 10x BETTER PERF PER DOLLAR THAN EVEN GB300 NVL72. This is on the widely used production LLM engine called @vllm_project. We explain below.👇️(1/3)🧵
HOLY ALERT🚨: NVIDIA vLLM INFERENCE RUBIN IS 3.2x BETTER IN PROFIT💰️ PER GIGAWATT & HAS UP TO 🚀 10x BETTER PERF PER DOLLAR THAN EVEN GB300 NVL72. This is on the widely used production LLM engine called @vllm_project. We explain below.👇️(1/3)🧵
来源：SemiAnalysis_ · x.com