PulseAugur
中
实时 06:18:44
English(EN) Canyon Overlook, @ZionNPS - MI355x on SGLang has achieved >10x improvement on throughput PER GPU since day-0 release for DeepSeekv4 Pro. HUGE W to the 10x en

SGLang的MI355x将DeepSeekv4 Pro每GPU吞吐量提升超过10倍

作者 PulseAugur 编辑部 · [1 个来源] ·

DeepSeekv4 Pro的性能显著提升，每GPU吞吐量实现了十倍以上的增长。这一进步是通过在SGLang框架上集成MI355x实现的。与模型最初发布相比，效率有了大幅飞跃。 AI

影响 展示了LLM推理方面显著的效率提升，可能降低运营成本并提高部署可行性。

排序理由 该集群报告了一个现有模型的性能改进，而不是新发布或重大的行业事件。[lever_c_demoted from research: ic=1 ai=1.0]

在 X — SemiAnalysis 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

SGLang的MI355x将DeepSeekv4 Pro每GPU吞吐量提升超过10倍

报道来源 [1]

  1. X — SemiAnalysis TIER_1 English(EN) · SemiAnalysis_ ·

    Canyon Overlook, @ZionNPS - MI355x on SGLang has achieved >10x improvement on throughput PER GPU since day-0 release for DeepSeekv4 Pro. HUGE W to the 10x en

    Canyon Overlook, @ZionNPS - MI355x on SGLang has achieved >10x improvement on throughput PER GPU since day-0 release for DeepSeekv4 Pro. HUGE W to the 10x engineers at Hai's team from @amd and @sgl_project! @EmadBarsoumPi @AnushElangovan https://t.co/O8DL9a1VD0

相关实体

相关话题