Morgan Funtowicz

Machine Learning Engineer - @HuggingFace / Paris 🇫🇷

[Morgan Funtowicz @MorganFunto]

What's next? Let us know what you'd like to see supported!

✍️ https://t.co/57p9v9woQn

[Morgan Funtowicz @MorganFunto]

Serving @OpenAI Whisper, powered by @vllm_project, deployed on @huggingface Inference Endpoint, with astonishing @Gradio demo ... What else? 😎

AI community is all you need to create blazing fast whisper transcriptions 💥🚀

More in our blog 📰 https://t.co/zE1G4VAvHb

[Morgan Funtowicz @MorganFunto]

Reference implementation sources 🧐https://t.co/tQgANybDa9

[Morgan Funtowicz @MorganFunto]

Qwen3 235B is now available on HuggingChat! And you know what? It's blazing fast✌️

👉https://t.co/NSBBjNue1Z

[Morgan Funtowicz @MorganFunto]

Last but not least, vLLM and llama.cpp are currently being worked on! 🚀

Initial artifacts for testing will be made available for the community around end of Q1'25 🛠️ and follow up blog posts will pop as we start rolling them out.

[Morgan Funtowicz @MorganFunto]

Anyone looking to deploy LLMs in production,🤗got something for you👀

@huggingface TGI is expanding its capabilities to bring support for different inference backends (vLLM, TensorRT-LLM, llama.cpp, etc. etc.) 🏋️

🗞️ More info in our last blogpost https://t.co/0vQnSXQZaJ

[Morgan Funtowicz @MorganFunto]

TensorRT-LLM, from our partner @nvidia, is the first backend we will be shipping. We are currently wrapping up the last parts.

It'll bring cutting edge float8, quantization & sparsity support🤏

We'll soon publish a part 2 with more in-depth about this integration, stay tuned!

[Morgan Funtowicz @MorganFunto]

@BramVanroy @AMDInstinct @Azure Stay tuned 🤠

[Morgan Funtowicz @MorganFunto]

Want to leverage @AMDInstinct MI300x GPUs for LLMs? Check out how easy it is and the performance in our blog post! 🚀

👉https://t.co/dyDXrQ6HYU

Still hungry?🧐Register for the next HuggingCast on June 6th 🎙️https://t.co/zUYJp41QRW

PS: Deploy these GPUs on @Azure right now! 😱

[Morgan Funtowicz @MorganFunto]

Hello @Free_1337 👋🏻, plus de fibre depuis le 19/12 sur Lessard le National (71530) est-ce que vous avez de la visibilité sur une résolution future ? 🤗🙏🏻

[Morgan Funtowicz @MorganFunto]

In the coming release we will focus on:
- Making optimum-nvidia pip installable
- Enabling GPTQ/AWQ models from the @huggingface hub
- Officially supporting Mistral models

Stay tuned! 🤗

[Morgan Funtowicz @MorganFunto]

We just released🤗optimum-nvidia 0.1.0b2 which brings many quality-of-life improvements, should ease the developer experience & extend NVIDIA GPU architectures coverage to Volta and Turing!

Check it out! 🚀

Release notes 📜: https://t.co/1ayU7KUZaJ

[Morgan Funtowicz @MorganFunto]

🚢Docker Hub image has been update to it's latest version for an easy start https://t.co/S0bVu98vCI

[Morgan Funtowicz @MorganFunto]

On-prem datacenter user? @huggingface is coming to you thanks to this new partnership with @DellTech 🤝.

Let's go team! 🚀

[Morgan Funtowicz @MorganFunto]

Can't tell how life changing the🤗Hub ability to quickly skim tensors & layout for a model is ...

Big thanks to the team for this! 😍

[Morgan Funtowicz @MorganFunto]

As part of @huggingface growth, we have been working on extending our data center capacities to meet the new challenges ahead 🚀😎.

Proud to partner with @VerneGlobal on sustainable AI powered by 100% renewable energy 🌎.

[Morgan Funtowicz @MorganFunto]

@julien_c Koyeb!