News for hackers. Stuff that matters.
Re:YaLM-100B: Pretrained language model with 100B parameters by uniqueuid on Thursday June 23, 2022 @07:01AM (#31847393)
Although memory capacity may matter more than speed for inference. As long as you're not training or fine tuning, the mac pro / studio may be just fine.

apart from the fact that you can't use any of the many nvidia-specific things; if you're dependent on cuda, nvcuvid, AMP or other things that's a hard no.

Re:YaLM-100B: Pretrained language model with 100B parameters by calrizien on Friday June 24, 2022 @12:50AM (#31857920)
What are the current best ML language models to play with on the M1Max?