- Developers will be able to utilize FriendliAI's accelerated generative AI infrastructure service to deploy and serve models in the Hugging Face Hub
REDWOOD CITY, Calif., Jan. 22, 2025 /PRNewswire/ -- 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."
About FriendliAI
FriendliAI is the leading provider of accelerated generative AI inference serving. FriendliAI provides fast, cost-efficient inference serving and fine-tuning to accelerate agentic AI and custom generative AI solutions. Enjoy the GPU-optimized, blazingly fast Friendli Inference through FriendliAI's Dedicated Endpoints, Serverless Endpoints, and Container solutions. Learn more at https://friendli.ai/.
About Hugging Face
Hugging Face is the leading open platform for AI builders. The Hugging Face Hub works as a central place where anyone can share, explore, discover, and experiment with open-source ML. Hugging Face empowers the next generation of machine learning engineers, scientists, and end users to learn, collaborate and share their work to build an open and ethical AI future together. With the fast-growing community, some of the most used open-source ML libraries and tools, and a talented science team exploring the edge of tech, Hugging Face is at the heart of the AI revolution.
Contacts:
Elizabeth Yoon, FriendliAI, press@friendli.ai