The service enhances AI deployment and performance
Core42, a G42 company specializing in sovereign cloud, AI infrastructure, and digital services, recently announced the global launch of its Inference-as-a-Service offering, powered by Qualcomm Technologies, Inc.’s comprehensive platform.
Available through all Core42 data centers worldwide, the service enhances AI deployment and performance for Software-as-a-Service (SaaS) providers and generative AI developers by providing immediate access to essential models while simplifying the complexities of infrastructure management.
The rapid rise of generative AI applications—from image and code generation to chatbots and text summarization—is creating complexity for customers trying to stay ahead when it comes to the optimal infrastructure options to leverage.
“Our Inference-as-a-Service offering, already powered by the Core42 Compass API, is now further enhanced with Qualcomm Technologies’ end-to-end advanced inference-as-a-service platform,” stated Raghu Chakravarthi, EVP, Engineering and GM, Americas, Core42.
Seamless integration
Core42’s Inference-as-a-Service allows seamless integration of new AI models, enabling users to stay current with the latest advancements and easily expand their AI capabilities. The platform enables users to choose from optimized inference containers compatible with any orchestration platform, accelerated APIs, or a user-friendly UI.
With high-availability containers that support autoscaling at both the server and model levels, the platform adapts to varying performance requirements seamlessly.
“We are proud to support Core42 with a seamless, scalable solution for delivering powerful generative AI capabilities and making AI accessible – both easy to use and optimized performance per TCO,” remarked Rashid Attar, VP, Cloud Computing, Qualcomm Technologies.
