SemiAnalysis· @SemiAnalysis_ · X·· 20 天前AI 评分37
AI 导读
ALERT🚨🚨: @vllm_project、@Inferact 与 NVIDIA 将协同设计推向极致，通过 GB300 NVL72 推理优化，实现了比所有其他 AI 芯片🚀 高 7.2 倍 🚀 的单位 TCO 性能，使用名为 wideEP 的推理协同设计优化，充分发挥 NVL72 背板的优势。我们在下方解释👇️ (1/3)🧵
AI 生成摘要 · 以原文为准
正文
ALERT🚨🚨: @vllm_project, @Inferact & NVIDIA TOOK CO-DESIGN TO THE EXTREME WITH A GB300 NVL72 INFERENCE OPTIMIZATION TO GET 🚀 7.2x 🚀 BETTER PERF PER TCO THAN LITERALLY EVERY OTHER AI CHIP, using an inference co-design optimization called wideEP take full advantage of the NVL72 BACKPLANE. We explain below👇️ (1/3)🧵
来源：SemiAnalysis · x.com