Loading activity…
@ngxson
Engineer @huggingface
AI
finkd says the model runs well on new Mac Studios, crediting work with Apple and John Ternus.
AI
The speaker says the talk explains how speculative decoding can speed up token generation and shows its use on llama.cpp.
AI
The speaker says the Gran Sala session will explore setup needs, which models fit and performance, with another talk planned on llama.cpp and Gemma at DeepMind Happy Hour.
AI
A post on X shares Bloomberg details on a potential Nvidia purchase of the AI company Hugging Face.
AI
Mark Zuckerberg posted that Meta opened weights for a local model with another release planned soon.
