注册并分享邀请链接,可获得视频播放与邀请奖励。

SemiAnalysis
@SemiAnalysis_
加入 January 2024
34 正在关注    168K 粉丝
ALERT🚨 GB300 NVL72 NVLINK BACKPLANE ENABLES 13x BETTER PERF PER DOLLAR THAN HOPPER ON AGENTIC INFERENCE Through extreme co-design, GB300 NVL72 uses an innovative copper backplane to expand the scale-up domain to 72 versus 8 on Hopper. This allows optimizations like @vllm_project wide expert parallelism, which allows each GPU to have only a subset of experts.
显示更多
0
15
266
15
转发到社区