Hugging Face’s Post

Hugging Face reposted this

View profile for Philipp Schmid, graphic

Technical Lead & LLMs at Hugging Face 🤗 | AWS ML HERO 🦸🏻♂️

Build, Train, and Deploy AI Models with Google TPUs on Hugging Face! We're excited to announce the General Availability of Google TPUs on Hugging Face. Hugging Face users can now use the power of Google Cloud TPUs in both Spaces and Inference Endpoints to build, train, and deploy your Generative AI models. 🚀 TL;DR: 🚀 Google Cloud TPUs are available on Spaces and Inference Endpoints. 💡 3 new options from 16GB to 128GB TPU memory (1x1, 2x2, 2x4 v5e TPU) in us-west1 🛠 Use TPU in Spaces for ML demos or dev mode to easily training. 📈 Deploy LLMs starting with Meta Llama 3 and Google DeepMind Gemma with Mistral and others to follow on Inference Endpoints 🔄 New Text Generation Inference backend now supports Google TPUs. 🌟 Starting at just $1.38/hour. Blog: https://lnkd.in/e_au-mqt Spaces: https://lnkd.in/eCun-cb9 Inference Endpoints: https://lnkd.in/eqks3UKd Big Kudos to Alvaro Moran, Morgan Funtowicz, Simon Pagezy, Thibault Goehringer, Michelle Habonneau, Christophe Rannou, and the whole HF team for bringing Google TPUs to every Hugging Face user!

  • No alternative text description for this image
Fernando Rodrigues

Analista de Operações de Suporte

4mo

Philipp Schmid With the recent partnership between Google and Hugging Face to integrate TPUs, is there any information about which specific libraries, beyond those already mentioned for natural language processing, will be available or optimized for TPUs in the Hugging Face environment? Specifically, is there any update on the availability of libraries that are typically not accessible in TPU environments, such as in Kaggle?

Like
Reply
Avneet Singh

AVP Generative AI and NLP - Data Labs

4mo

Love the infra sadly these configurations are yet to be launched in India and the best we have is A10s . :(

Great to see the continued diversification of accelerated compute platforms available for AI. We need to see compute prices come down.

Like
Reply
Aleksandr Blekh, Ph.D.

Software Engineering | Cloud | ML/AI | Solution Architecture | IT Strategy

4mo

Very nice! Could you clarify why inference deployments at Hugging Face are billed by hour and not by token count like at most GenAI inference providers?

Like
Reply
Vishal Mishra

Director Engineering (ML), Google

4mo

Congratulations Philipp and team. Great to see this update and collaboration.

Bruno Da Cruz Portes

Blockchain Engineer | Solidity | Tokenização | AI | DeFi | Rust | NFT | Python | Cloud Computing

4mo

Good to know!

Like
Reply
Bella Go

Marketing Content Manager at ContactLoop | Productivity & Personal Development Hacks

4mo

Philipp Schmid Useful info on Google TPUs for AI. 👍 Donald Presnell, Jr Executive MBA, MIT IDSS Thanks for the repost!

Carlos Dueñas

Just me. Labels are overrated in this AI era.

4mo

These are such excellent news!!!

Like
Reply
See more comments

To view or add a comment, sign in

Explore topics