George Hotz: belief

Transcript context

…Ubuntu. I like Ubuntu MATE, however you pronounce that MATE. You’ve gotten LLaMA into tinygrad, you’ve gotten stable diffusion into tinygrad. What was that like? What are these models, what’s interesting about porting them? What are the challenges? What’s naturally? What’s easy? All that kind of stuff. There’s a really simple way to get these models into tinygrad and you can just export them as Onyx and then tinygrad can run Onyx. So the ports that I did of LLaMA Stable Diffusion and now Whisper are more academic to teach me about the models, but they are cleaner than the PyTorch versions. You can read the code. I think the code is easier to read, it’s less lines. There’s just a few things about the way tinygrad writes things. Here’s a complaint I have about PyTorch. nn.ReLU is a class so when you create an NN module, you’ll put your nn ReLUs as in a nit, and this makes no sense. ReLU is completely stateless. Why should that be a class? But that’s more a software engineering thing, or do you think it has a cost on performance?…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.