Shulou(Shulou.com)11/24 Report--

CTOnews.com August 10 news, NVIDIA recently released a new NVIDIA L40S GPU, and equipped with the GPU OVX server system, CTOnews.com friends can find the corresponding technical documentation here.

▲ It is reported that this L40S GPU, together with the newly released OVX server, can be applied to AI large model training and reasoning, three-dimensional design, visualization, Media Processing Service, industrial digitalization and other purposes. Compared with A100 GPU, this "complementary" L40S system can "enhance the capabilities of generative AI, graphics and Media Processing Service, and meet the increasing computing power demand."

CTOnews.com has learned that the L40S GPU is an upgraded version of NVIDIA's previous L40 GPU, equipped with 48GB GDDR6 ECC memory. The GPU is based on Ada Lovelace architecture, equipped with the fourth generation Tensor Core and FP8 conversion engine, and the computing speed is five times that of the previous generation. NVLink is not supported.

Nvidia claims that the L40S's generative AI reasoning performance is 1.2 times higher and training performance is 1.7 times higher than that of the A100, and Nvidia says the L40S's performance is more outstanding for "complex AI work with billions of parameters and multiple data patterns."

Nvidia said the L40S GPU will be available this fall and that each Nvidia OVX server system can carry up to eight L40S accelerator cards, although Nvidia did not disclose the pricing of the GPU.

NVIDIA also said that ASUS, Dell, Giga, HPE, Lenovo, QCT and American Micro will "soon launch" OVX server systems equipped with L40S GPU.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.