Digital Newsletter
Each week our editor Phil Alsop rounds up the most popular articles, videos and expert opinions. We compile this into a Digital Newsletter and send it straight to your inbox every week.
Digital Magazines
We'll let you know each time a new edition of Data Centre Solutions is released so that you're always kept up-to-date with the latest and greatest news and press releases.
Video Magazines
The Data Centre Solutions Video magazine contains the latest Zoom interviews with experts in the industry.
OVHcloud, a global cloud player and the leading European cloud provider, has made a strategic move by selecting SambaNova, known for its next-generation AI infrastructure, to bolster its inference portfolio. This collaboration focuses on delivering ultra-low latency inference solutions, tailored to meet the demands of modern AI workloads.
In today's dynamic environment, enterprises encounter significant challenges while building advanced AI systems. These challenges include latency bottlenecks from sequential LLM calls, the need for immediate responses in user applications, and the requirement to manage millions of inferences efficiently. These constraints often hinder performance, especially regarding time to first token and output time per token.
The alliance between OVHcloud and SambaNova aims to unlock a plethora of use cases where every millisecond is critical. From financial services and cybersecurity to industrial automation and logistics, rapid inference speeds play a pivotal role in capitalizing on opportunities, preventing operational oversights, and enhancing user experiences.
OVHcloud AI Endpoints, enhanced by SambaNova's SambaStack platform, are set to offer production-grade capabilities. These endpoints promise exceptional performance, swift inference, energy efficiency, and an impressive 99.8% uptime SLA.
The platform powered by SambaNova fast inference technology is designed for the most demanding workloads that require reliable, large-scale inference. OVHcloud is gearing towards offering diverse endpoint options, including real-time performance-guaranteed endpoints and batch API solutions, ensuring rapid response down to the byte level and efficient token output time.
Bolstering its existing framework of GPU-powered AI Endpoint sessions, the integration of SambaNova's new inference node promises a blazing-fast experience. This is achieved through reconfigurable dataflow units (RDUs), purpose-built for superior AI performance. Moreover, the technology delivers high tokens per kilowatt-hour, optimizing resource use and data center density.
With enhanced inference capabilities, SambaNova-powered AI Endpoints are seamlessly suited for intense workloads like AI agents, live translation, and comprehensive batch operations, such as crawling and dataset refreshing.
Octave Klaba, founder and CEO of OVHcloud, emphasized the importance of this partnership in offering customers an unmatched inference experience, highlighting SambaNova's technology as key to unlocking efficient and powerful AI solutions.
Rodrigo Liang, Co-founder and CEO of SambaNova, expressed that the collaboration is setting new benchmarks for AI performance and provides enterprises a reliable platform for deploying large-scale models quickly and efficiently.
The SambaNova-powered AI Endpoints service marks a significant step in OVHcloud's strategy to deliver a robust, high-performance AI inferencing platform, tailored for both developers and enterprises seeking superior performance, support, and cutting-edge features for critical applications.
