Daniël de Kok

danieldk.eu

09 May 2025 15:45

We just released text-generation-inference 3.3.0. This release adds prefill chunking for VLMs 🚀. We have also Gemma 3 faster & use less VRAM by switching to flashinfer for prefills with images. github.com/huggingface/...

Erik

erikkaum.bsky.social

22 March 2025 00:21

We just refreshed 🍋 our analytics in @hf.co endpoints. More info below!

Thomas Wolf

thomwolf.bsky.social

12 March 2025 16:52

We've kept pushing our Open-R1 project, an open initiative to replicate and extend the techniques behind DeepSeek-R1 And even we were mind-blown by the results we got with this latest model we're releasing: ⚡️OlympicCoder [1/3]

Thomas Wolf

thomwolf.bsky.social

28 February 2025 22:13

Oh! My TED talk is just out. I talk about how open-source is critical for AI safety and humanity's resilience. Yes, you don't hear that perspective often! :) It's called "What if AI just works" It's here: www.ted.com/talks/thomas...

Daniël de Kok

danieldk.eu

10 December 2024 18:52

All the hard work of the last few months has culminated in stellar performance of TGI 3.0. It's such an honor to work in this team! 🔥