SoftBank’s latest software stack, Infrinia Cloud OS, has been developed to cater to the growing global demand for GPU-powered AI services. This innovative solution is designed to lower total cost of ownership (TCO) and simplify day-to-day operations, offering a more efficient alternative to internally developed or custom-made stacks. Infrinia Cloud OS aims to expedite the deployment of GPU cloud services, supporting every phase of the AI lifecycle, from model training to real-time utilization.
Initially, SoftBank will incorporate Infrinia Cloud OS into its current GPU cloud offerings before expanding its deployment to international data centers and cloud platforms in the future. The surge in demand for GPU-driven AI across various industries, such as science, robotics, and generative AI, has placed a strain on GPU cloud service providers, prompting the need for more advanced and efficient solutions.
Infrinia AI Cloud OS has been meticulously designed to address these challenges, maximizing GPU performance and simplifying the management and deployment of GPU cloud services. By automating the underlying infrastructure layers and offering features like automated node allocation and NVIDIA NVLink domain optimization, Infrinia Cloud OS streamlines operations and enhances GPU-to-GPU bandwidth for large-scale distributed workloads. The Inf-aaS component enables users to effortlessly implement inference workloads, facilitating faster and more scalable access to AI model inference through managed services.
By reducing operational complexities and TCO, Infrinia AI Cloud OS is poised to accelerate the adoption of GPU-based AI infrastructure across various sectors globally.
