炒股就看金麒麟分析师研报，权威，专业，及时，全面，助您挖掘潜力主题机会！

IT之家 7 月 13 日消息，专注基于 AMD 硬件构造 AI 基础设施的企业 TensorWave 当地时间昨日宣布其成功创建了基于 Instinct MI325X 显卡加速器的北美最大 AMD GPU 训练集群。

这一集群配备了共计 8192 块 MI325X，同时也是首个基于该 GPU 的 DLC 液冷计算集群。

AMD 的 Instinct MI325X 显卡加速器发布于 2024 年 10 月，可视为 MI300X 的“显存扩容版”。其基于台积电 5nm 与 6nm 工艺，采用 "CDNA3" 微架构、配备 256GB HBM3E，可提供 2.61 PFLOPs 的原始峰值 FP8 计算性能。

MI325X 的下一代产品 MI350 系列已于今年 6 月发布，原始峰值 FP8 计算性能大幅提升至 5 PFLOPs。

（转自：网易科技）

海量资讯、精准解读，尽在新浪财经APP

Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.