FriendliAI and Hugging Face Announce Strategic Partnership
FriendliAI, a leader in accelerated generative AI inference serving, and Hugging Face today announced a strategic partnership that allows developers to utilize FriendliAI’s inference infrastructure service to deploy and serve models directly in the Hugging Face Hub.
FriendliAI Endpoints, the fastest GPU-based generative AI inference provider according to Artificial Analysis, is now available as a deployment option on the Hugging Face platform. Directly from any model page on Hugging Face, developers can now easily deploy models using FriendliAI’s accelerated, low-cost inference endpoints. This partnership leverages the convenience of Hugging Face’s platform alongside FriendliAI’s high-performance infrastructure, enabling developers to streamline their AI development workflow and focus on innovation.
Setting up and deploying generative AI models at production scale presents challenges such as complex infrastructure management and high operational costs. Friendli Dedicated Endpoints handles the hassle of infrastructure management, enabling developers to deploy and serve generative AI models efficiently on autopilot. Powered by FriendliAI’s GPU-optimized inference engine, Friendli Dedicated Endpoints delivers fast and cost-effective inference serving as a managed service with dedicated GPU resources and automatic resource management.
The addition of FriendliAI as a key inference provider advances Hugging Face’s mission to democratize AI, while furthering FriendliAI’s mission to empower everyone to harness the full potential of generative AI models with ease and cost-efficiency. With this partnership, FriendliAI becomes a strategic inference provider for Hugging Face.
“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.”
