SIGGRAPH—NVIDIA today announced NVIDIA OVX™ servers featuring the new NVIDIA® L40S GPU, a powerful, universal data center processor designed to accelerate the most compute-intensive, complex applications, including AI training and inference, 3D design and visualization, video processing and industrial digitalization with the NVIDIA Omniverse™ platform.
The new GPU powers accelerated computing workloads for generative AI, which is transforming workflows and services across 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
NVIDIA OVX systems will enable up to eight NVIDIA L40S GPUs per server, each equipped with 48GB of memory. Based on the NVIDIA Ada Lovelace GPU architecture, the L40S includes fourth-generation Tensor Cores and an FP8 Transformer Engine, delivering over 1.45 petaflops of tensor processing power. For complex AI workloads with billions of parameters and multiple data modalities — such as text and video — L40S enables up to 1.2x more generative AI inference performance and up to 1.7x training performance compared with the NVIDIA A100 Tensor Core GPU.
To power high-fidelity professional visualization workflows like real-time rendering, product design and 3D content creation, the NVIDIA L40S GPU includes 142 third-generation RT Cores that deliver 212 teraflops of ray-tracing performance. This enables creative professionals to create immersive visual experiences and photorealistic content.
For computationally demanding workflows, such as engineering and scientific simulations, the NVIDIA L40S includes 18,176 CUDA® cores, delivering nearly 5x the single-precision floating-point (FP32) performance of the NVIDIA A100 GPU to accelerate complex calculations and data-intensive analyses.
Among the first cloud service providers to offer L40S instances is CoreWeave, which specializes in large-scale, GPU-accelerated workloads.
“With the explosion of generative AI, our customers across industries are seeking powerful compute offerings and scale to match the complexity of any workload — from interactive video to AI design and automation,” said Brian Venturo, chief technology officer at CoreWeave. “NVIDIA L40S GPUs will further expand our broad portfolio of NVIDIA solutions, making CoreWeave the first specialized cloud provider to offer these new 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 benefit from NVIDIA AI Enterprise software, which announced a major update today. The software provides production-ready enterprise support and security for over 100 frameworks, pretrained models, toolkits and software, including NVIDIA Modulus for simulations, NVIDIA RAPIDS™ for data science and NVIDIA Triton™ Inference Server for production AI.
NVIDIA also announced major updates to the Omniverse platform, introducing capabilities and platform 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 needed to supercharge generative AI pipelines and Omniverse workloads.
The NVIDIA L40S 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.