Hi Hugging Face team,

I’m Kyle Shao from GMI Cloud. Our team has been working on building a stable inference engine designed to make people’s lives more efficient through a single, unified API. To reach more users, we’re very interested in becoming one of the inference providers on Hugging Face.

This PR adds GMI Cloud as a new inference provider in the Hugging Face Inference framework. Our team at GMI Cloud is building a scalable and reliable inference engine with the goal of providing developers a unified, efficient API for running AI workloads.

Following the “How to be registered as an inference provider on the Hub” guide, this PR includes the required updates:
• Added GMI Cloud provider entry
• Updated provider helper logic
• Updated related types
• Updated README with provider information

Please let me know if any additional changes or information are needed — happy to help.
Thank you for reviewing this contribution.