MiTAC showcases full-stack AI infrastructure at SC26
MiTAC Computing Technology showcased a full-stack AI infrastructure ecosystem at SC26, combining high-density liquid cooling, disaggregated inference and end-to-end resource scheduling. The company and Skymizer proposed assigning Prefill to AMD Instinct GPUs and Decode to Skymizer HTX301 accelerators, while also showing rack systems, server platforms and the MiCoreView pod-management software. These capabilities and performance figures were presented by the vendors and were not independently tested in the supplied report.
The showcase puts MiTAC’s stage-based inference, liquid-cooling and orchestration technologies in one enterprise AI stack, but their real-world deployment and performance remain unverified.


全球高效能伺服器解決方案領導者神達控股股份有限公司子公司神雲科技(MiTAC Computing Technology),於 SC26 展會中揭曉其全方位的 AI 基礎設施生態系。
神雲科技位於第 4615 號攤位,以「全棧基礎設施,擴展 AI 代理式應用」(Scaling Agentic AI. Built on Full-Stack Infrastructure)為主題,展示全棧創新技術如何克服企業部署 AI 時所面臨的運算、散熱與資料傳輸瓶頸。隨著代理式 AI 帶動推論工作負載呈指數級暴增,擴展基礎設施所需的已不僅是單純的 GPU 算力。透過與 AMD、Canonical、DDN、Intel、NVIDIA 及 Rafay 等夥伴的戰略合作,神雲科技提供具備高度擴充性的 AI 工廠(AI Factory)架構,完美結合高密度液冷、解耦推論(Disaggregated Inference)以及端到端(End-to-End)的資源調度管理。
#MiTAC Computing Technology#Skymizer#AMD Instinct MI350X#Skymizer HTX301#MiCoreView#AMD#Canonical#DDN#Intel#NVIDIA#Rafay#ZutaCore