Groq

“There's also, like, non-NVIDIA stacks, like the Grok, or Cerebris, or some of these custom silicon companies that are super interesting, and all, and outperformed the NVIDIA stack in terms of latency and things like that.”

“You know, if you look at Cerebrus and Grok and others, they've really tried to do this, their cloud kind of portal. And for us, you know, it shows two things. One is the difficulty of software for third party to implement that, that that's why they're kind of …”

“Grok is very inflexible hardware so that you kind of, if you want to do like a Mamba SSM on it, you're going to have a really hard time because instead of having like a low level CUDA compiler, like everything is like Designed it at the hardware level, right?”

“The reason why my hit rate for every AI accelerator trip is, like, very, like, I just don't believe in them is because, like, where are they? Until Cerebrus and Grok, honestly, they were all considered failures, and even then, we're like, what are they gonna d…”

“I think what's, what's going to end up happening is they're going to end up focusing on significantly smaller models. You know, if you have that limitation in your architecture, then I think that's what ends up happening.”

“To run a frontier level model, like, let's say, a few trillion parameters, you need thousands and thousands of Grok LPUs just to hold the weights, right?”

“One of our chips has, You know, order a hundred times more memory than one of their chips, right? So you got two orders of magnitude difference in scale kind of for free, right?”