News for hackers. Stuff that matters.
Re:Two new Gemini models, reduced 1.5 Pro pricing, increased... by Workaccount2 on Tuesday September 24, 2024 @02:04PM (#41639279)
Cerebras has ridiculously large LLM ASICs that can hit crazy speeds. You can try it with llama 8B and 70B:

https://inference.cerebras.ai/

It's pretty fast, but my understanding is that it is still too expensive even accounting for the speed-up.

Re:Two new Gemini models, reduced 1.5 Pro pricing, increased... by throwup238 on Tuesday September 24, 2024 @02:15PM (#41639397)
Is Cerebras an integrated circuit or more an integrated wafer? :-)

And yeah their cost is ridiculous, on the order for high 6 to low 7 figures per wafer. The rack alone looks several times more expensive than the 8x NVIDIA pods [1]

[1] https://web.archive.org/web/20230812020202/https://www.youtu...