logoalt Hacker News

hparadiztoday at 4:53 PM2 repliesview on HN

Here's my report running several different models on a dual Xeon with 256 GB of DDR4 and no GPU.

https://gist.github.com/hparadiz/f3596d00a62d8ebb2dadcc46ee5...


Replies

puzzlingcaptchatoday at 5:20 PM

Have you tried with a single CPU to get rid of the NUMA penalty? I understand this likely means halving the memory but I am interested in how much of a difference it makes

show 1 reply
neomindryantoday at 5:05 PM

Thank you for sharing!