Hacker News Reader

Comment by pjs_ | Hacker News Reader

Cerebras is truly one of the maddest technical accomplishments that Silicon Valley has produced in the last decade or so. I met Andy seven or eight years ago and I thought they must have been smoking something - a dinner plate sized chip with six tons of clamping force? They made it real, and in retrospect what they did was incredibly prescient

View on HN

It's a modern take on an old idea. I first saw it in European research for wafer-scale, analog, neural networks. I found another project while looking for it. I'll share both.

https://www.kip.uni-heidelberg.de/Veroeffentlichungen/downlo...

https://archive.ll.mit.edu/publications/journal/pdf/vol02_no...

The second's patents would also be long-expired since it's from 1989.

The concept is super cool but does anyone actually use them instead of just buying Nvidia?

Most people don't buy nvidia; they use a provider, like Openrouter.

Mistral uses them for Le Chat, it is really fast.

https://chat.mistral.ai/chat

https://www.cerebras.ai/blog/mistral-le-chat

nah, it was designed for hpc and raw flops. llm inference really requires memory bandwidth.

Memory bandwidth, eh? You should learn the basics about what Cerebras does. https://www.cerebras.ai/chip

Sheeeesh. 21 petabytes per second of memory bandwidth? That’s bonkers.

I'd say llm inference requires both memory capacity and bandwidth. Cerebras provides bandwidth with on-chip SRAM, but not capacity (an entire wafer has only 44GB SRAM).

Wafer-scale integration was done decades before.

Reply on news.ycombinator.com