PyTorch

"People want to use it how they're currently using it and going to continue to use it, which is based on Nvidia's stack but also primarily based on PyTorch."

Cliff Weitzman

mentioned

"Fireworks is amazing. Lyn, the founders — she's one of the co-founders of PyTorch."

John Coogan

mentioned

"The paper was implemented in Google's TensorFlow framework and people like PyTorch. So the Hugging Face team converted BERT from TensorFlow to PyTorch and released the conversion for free."

Dave Blundin

mentioned

"All the AI researchers in the world moved to Python and PyTorch to do the work because you can iterate your ideas so much more quickly in that environment."

"That team was the geniuses that understood Python the best — PyTorch in particular. So you've got this sort of team of people that have a different take and have a different set of aspirations in what they're doing."

"If not for TensorFlow or, more importantly, PyTorch — and the early versions of Caffe, Torch, Theano — all of those were open source. If not for all of that, how would we have modern AI?"

"The decision explicitly not to build an arbitrary graph compiler, not to support arbitrary PyTorch, not to support arbitrary CUDA, not to support arbitrary ONNX graphs — but instead we envisioned a world where there was going to be under a hundred..."