Hugging Face and FriendliAI partner to supercharge model deployment on the Hub

Hugging Face Blog · 1 year ago

FriendliAI's inference infrastructure is now available as a deployment option directly within the Hugging Face Hub, allowing developers to deploy models with a single click. Users can deploy open-source or custom models on NVIDIA H100 GPUs through Friendli Dedicated Endpoints or access serverless inference for open-source models at lower cost. This integration eliminates the need for developers to manage separate infrastructure, letting them focus on model development while reducing operational expenses through FriendliAI's optimized inference engine.