fcalva @ fcalva @cyberplace.social

Posts

0
Comments

3
Joined

8 mo. ago

Lisp enjoyer, occasional code golfer.
I self host what i can, because i can.
As for the rest, i invite you to read my timeline.

5d ago

China solves 'century-old problem' with new analog chip that is 1,000 times faster than high-end Nvidia GPUs
Jump
fcalva @cyberplace.social 5d ago
@carrylex @kalkulat If you zoom in, you will see that it is in fact a real photo. It's just someone who thought putting a CPU upside down was a good idea.

5d ago

China solves 'century-old problem' with new analog chip that is 1,000 times faster than high-end Nvidia GPUs

@Treczoks @flemtone Thing is, the final LLM inference is usually done at reduced precision. 8-16 bits usually, but even 4bits or lower with different layers of varying precision.