From the source
Hugging Face announces that
Google Cloud TPUs are now available on Inference Endpoints and Spaces, with three TPU v5e instance configurations and pricing per hour.
Supported models include Gemma, Llama, and Mistral.
From the source
We're excited to share some great news! AI builders are now able to accelerate their applications with Google Cloud TPUs on Hugging Face Inference Endpoints and Spaces!
huggingface.co
