PulseAugur
实时 23:13:27

SGLang's MI355x boosts DeepSeekv4 Pro throughput over 10x per GPU

DeepSeekv4 Pro has seen a significant performance increase, achieving over tenfold improvement in throughput per GPU. This advancement was realized through the integration of MI355x on the SGLang framework. The gains represent a substantial leap in efficiency since the model's initial release. AI

影响 Demonstrates substantial efficiency gains in LLM inference, potentially lowering operational costs and increasing deployment feasibility.

排序理由 The cluster reports on a performance improvement for an existing model, not a new release or a significant industry event. [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's MI355x boosts DeepSeekv4 Pro throughput over 10x per GPU

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