SemiAnalysis· @SemiAnalysis_ · X·· 2 小时前AI 评分29
AI 导读
重磅警报🚨：NVIDIA vLLM 推理 Rubin 每吉瓦利润💰️提升 3.2 倍，每美元性能甚至比 GB300 NVL72 高出🚀 10 倍。这是基于广泛使用的生产级 LLM 引擎 @vllm_project。我们下面解释。👇️(1/3)🧵
正文
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