近日，全球芯片巨头英伟达（NVIDIA）在官网上线了针对中国市场特别推出的RTX 5880 Ada工作站显卡。这款显卡主要面向消费级和AI训练推理等专业领域应用。然而，与旗舰级RTX 6000相比，这款显卡的单精度浮点性能降低了约24%，整体性能下降了近1/4，实际表现接近次旗舰性能的RTX 5000。
对于英伟达消费级RTX 5880和4090D显卡在AI模型训练和推理方面的应用，行业人士透露，RTX 5880仅能用于训练70亿-650亿参数模型，无法处理万亿级参数模型；而4090D显卡则能稳定运行。这一举措被看作是英伟达为了应对美国出口禁令，对向中国出口的芯片产品进行性能限制。
英文标题：NVIDIA Unveils “China-Exclusive” Chips With Nearly 25% Performance Drop
关键词：NVIDIA, China-Exclusive, Performance Reduction
News content:
Recently, NVIDIA, the global chip giant, has launched the RTX 5880 Ada workstation graphics card specifically for the Chinese market on its official website. This graphics card is mainly aimed at professional fields such as consumer-grade and AI training and inference. However, compared to the flagship RTX 6000, the performance of this graphics card has decreased by about 24% in single-precision floating-point performance, and the overall performance has decreased by nearly one-quarter, with actual performance approaching that of the mid-range RTX 5000.
As for the application of NVIDIA’s consumer-grade RTX 5880 and 4090D graphics cards in AI model training and inference, industry insiders reveal that RTX 5880 can only be used for training models with 70 billion to 650 billion parameters and cannot handle trillion-level parameter models; while the 4090D graphics card can run stably. This move is seen as NVIDIA’s strategy to limit the performance of its chip products exported to China in response to the U.S. export ban.
【来源】https://www.tmtpost.com/6868819.html
Views: 1