Hugging Face Hub adds FriendliAI Endpoints for 1-click deployment on NVIDIA H100 GPUs

AI Impact Summary

The Hugging Face Hub now exposes FriendliAI Endpoints as a deployment option, enabling one-click deployment of open-source or private models and direct access to optimized GPU-backed inference. This partnership promises faster processing on NVIDIA H100 GPUs via Dedicated Endpoints or Serverless Endpoints, with potential cost reductions and simpler infrastructure management for production-grade generative models. Organizations should evaluate adopting this integration to reduce deployment friction and latency for model serving on the Hub.