frozenport
Joined 14 years ago
Joined 14 years ago
A year ago it wasn't clear if they'd stay competitive but it seems they are.
There isn't to be shared between the two techs, Groq's hardware is a like a railgun that installs all the weights into the optimal location before firing off an inference. Cerebras computer engineering more convention requiring the same data movement that GPUs struggle with optimizing.
Suspect Groq is complementary/superior to nvidia's GPUs, while it is unclear what Cerebras brings other then maybe some deals with TSMC.
Typically running something like git would be an opt in permission.
Despite posturing by some academic administrators, most folks have no social agenda for a country they recently immigrated to.
So ideally the ml network would solve the problem end to end but these authors seem to be using a network for only one step of their otherwise classic image processing pipeline
Term sheets from vcs increasingly include a “don’t do an ico”
In the immediate it seems to have cut short the next generation of scientists leaving more of the entrenched old hands.
Its been quiet a journey!
From wordpress to ai by way of hustling and a PhD!
Professional experience in hpc, publishing, wet lab biology, optical physics, startups, medicine, compilers and AI.