Developers will be able to utilize FriendliAI’s accelerated generative AI infrastructure service to deploy and serve models in the Hugging Face Hub
FriendliAI, a prominent player in accelerated generative AI inference services, has entered into a strategic partnership with Hugging Face, enabling developers to seamlessly deploy and serve models using FriendliAI’s inference infrastructure directly through the Hugging Face Hub.
FriendliAI Endpoints, recognized as the fastest GPU-based generative AI inference solution by Artificial Analysis, is now integrated as a deployment option on the Hugging Face platform. This integration empowers developers to launch models effortlessly from any Hugging Face model page, benefiting from FriendliAI’s accelerated, cost-effective inference capabilities. The collaboration combines Hugging Face’s user-friendly platform with FriendliAI’s high-performance infrastructure, allowing developers to streamline their AI workflows and focus on driving innovation.
Deploying generative AI models at scale often involves intricate infrastructure management and significant operational expenses. Friendli Dedicated Endpoints simplifies this process by providing an automated, managed service that handles infrastructure complexities. Powered by a GPU-optimized inference engine, Friendli Dedicated Endpoints ensures rapid and budget-friendly inference services with dedicated GPU resources and automated resource allocation.
Also Read: Leonardo.AI Boosts Growth with Google Cloud Gen AI
By integrating FriendliAI as a core inference provider, Hugging Face takes a significant step toward its mission of democratizing AI, while FriendliAI furthers its commitment to enabling easy and cost-efficient utilization of generative AI models. This partnership solidifies FriendliAI’s role as a strategic inference provider within the Hugging Face ecosystem.
“FriendliAI and Hugging Face share a vision for making generative AI, and further agentic AI, more accessible and impactful for developers,” said Byung-Gon Chun, CEO of FriendliAI. “This partnership gives developers on Hugging Face easy access to FriendliAI Endpoints, a fast, low-cost inference solution without the burden of infrastructure management. We’re excited to see what the amazing developer community at Hugging Face will build with our inference solution, and we look forward to any future opportunities to partner with Hugging Face to provide developers with even more powerful tools and resources.”
“FriendliAI has been at the forefront of AI inference acceleration progress,” said Julien Chaumond, CTO of Hugging Face. “With this new partnership, we will make it easy for Hugging Face users and FriendliAI customers to leverage leading optimized AI infrastructure and tools from FriendliAI to run the latest open-source or their custom AI models at scale.”