News for hackers. Stuff that matters.
Re:Cerebras achieves 2,500T/s on Llama 4 Maverick (400B) by ryao on Saturday May 31, 2025 @03:11PM (#44146352)
Thanks for the correction. They are currently using FP16 for inference according to OpenRouter. I had thought that implied that they could not use FP8 given the pressure that they have to use as little memory as possible from being solely reliant on SRAM. I wonder why they opted to use FP16 instead of FP8.

There are no comments on this comment yet.