NVIDIA Announces OVX Servers with New L40S GPU

NVIDIA has unveiled its new OVX servers featuring the powerful NVIDIA L40S GPU. This data center processor is designed to accelerate complex applications such as AI training and inference, 3D design and visualization, video processing, and industrial digitalization with the NVIDIA Omniverse platform. The L40S GPU enables accelerated computing workloads for generative AI, which is revolutionizing various industries including text, image, and video generation, chatbots, game development, product design, and healthcare.

"As generative AI transforms every industry, enterprises are increasingly seeking large-scale compute resources in the data center," said Bob Pette, vice president of professional visualization at NVIDIA. "OVX systems with NVIDIA L40S GPUs accelerate AI, graphics, and video processing workloads, and meet the demanding performance requirements of an ever-increasing set of complex and diverse applications."

Powerful Performance for AI and Graphics

The NVIDIA OVX systems can accommodate up to eight NVIDIA L40S GPUs per server, each equipped with 48 GB of memory. The L40S, based on the NVIDIA Ada Lovelace GPU architecture, features fourth-generation Tensor Cores and an FP8 Transformer Engine, delivering over 1.45 petaflops of tensor processing power. Compared to the NVIDIA A100 Tensor Core GPU, the L40S enables up to 1.2x more generative AI inference performance and up to 1.7x training performance for complex AI workloads with billions of parameters and multiple data modalities.

The NVIDIA L40S GPU also includes 142 third-generation RT Cores, providing 212 TeraFLOPS of ray tracing performance for high-fidelity professional visualization workflows like real-time rendering, product design, and 3D content creation. Additionally, it incorporates 18,176 CUDA cores, delivering nearly 5x the single-precision floating-point (FP32) performance of the NVIDIA A100 GPU, making it ideal for computationally demanding workflows such as engineering and scientific simulations.

Early Adoption

CoreWeave, a cloud service provider specializing in large-scale, GPU-accelerated workloads, is among the first to offer L40S instances. According to Brian Venturo, chief technology officer at CoreWeave, the NVIDIA L40S GPUs will expand their portfolio of NVIDIA solutions, making CoreWeave the first specialized cloud provider to offer these resources for fast, efficient, and cost-effective accelerated computing to power the next wave of generative AI applications.

Software to Boost AI

Enterprises deploying L40S GPUs can take advantage of NVIDIA AI Enterprise software, which provides production-ready enterprise support and security for over 100 frameworks, pretrained models, toolkits, and software. This includes NVIDIA Modulus for simulations, NVIDIA RAPIDS for data science, and NVIDIA Triton Inference Server for production AI.

Omniverse Expands

NVIDIA has also announced significant updates to the Omniverse platform, introducing capabilities and enhancements that enable developers to accelerate and advance OpenUSD pipelines and industrial digitalization applications with the power of generative AI. The next generation of NVIDIA OVX systems powering Omniverse Cloud will feature L40S GPUs to deliver the AI and graphics performance required to supercharge generative AI pipelines and Omniverse workloads.

Availability

The NVIDIA L40S GPU will be available starting this fall. Global system builders, including ASUS, Dell Technologies, GIGABYTE, HPE, Lenovo, QCT, and Supermicro, will soon offer OVX systems that include the NVIDIA L40S GPUs. These servers will help professionals worldwide advance AI and bring generative AI applications like intelligent chatbots, search, and summarization tools to users across industries.