4·
5 months agoJust beware that like AMD, Intel GPUs suffer a performance hit when using LLMs because of the CUDA specific optimizations in frameworks like llama.cpp
- 0 Posts
- 4 Comments
Joined 1 year ago
Cake day: August 10th, 2023
You are not logged in. If you use a Fediverse account that is able to follow users, you can follow this user.
Why would we PUNish you?
5·1 year agoAmazing! These are going in my.conf ASAP.
Do you have any tips (or examples) using quadlets? I tried using them but I couldn’t wrap my head around them.