← 返回列表

@SemiAnalysis_: MINECRAFT STEVE ALERT: GB300 ultra NVL72 is already 2.7x faster 🚀 than GB200 NVL72 on one of the industry standard inference engine known a...

@SemiAnalysis_ 3 信息等级 3 1 噪音/剔除；2 较弱；3 普通事实；4 重要行业动态；5 极重大事件。该分数是信息显著性，不是投资建议。 发布：2026-05-04T21:00 抓取：2026-05-05 04:04
🔗 原文链接
AI 算力 行业
摘要

据推特消息，GB300 ultra NVL72在vllm推理引擎上比GB200 NVL72快2.7倍。虽然理论性能提升仅1.5倍，但通过全栈优化实现了更高实际性能。该临时样机由英伟达、Inferact和CoreWeave提供用于开源项目。

客观事实
  • GB300 ultra NVL72在vllm上比GB200 NVL72快2.7倍
  • 理论上GB300仅有1.5倍NVFP4 FLOP和1.5倍HBM容量
  • 性能提升源于全栈优化带来的复合增益
NVIDIA CoreWeave vllm

原文

MINECRAFT STEVE ALERT: GB300 ultra NVL72 is already 2.7x faster 🚀 than GB200 NVL72 on one of the industry standard inference engine known as @vllm_project. On paper, GB300 only has ~1.5x faster NVFP4 FLOP & 1.5x more HBM capacity & same HBM BW than GB200 but due to the full stack optimization with compounding gains, in the middle of the curve where most providers serve at, GB300 is up to 2.7x faster. End to End performance is the gold standard of performance, not on paper theoretical flops.

Thanks to the 10x engineers at NVIDIA & @inferact & @coreweave for this temporary gb300 for open source projects!

likes: 206 | retweets: 25 | replies: 7 | views: 24036