CogVLM icon indicating copy to clipboard operation
CogVLM copied to clipboard

Published 20 hours ago • verified publisher icon THUDM

Why is it that running inference on two cards is slower than running on a single card?

Open Leeon-K opened this issue 6 months ago • 0 comments

cogvlm-chat-v1.1 model H800 machine Why is it that running inference on two cards is slower than running on a single card?"

Leeon-K avatar Aug 07 '24 05:08 Leeon-K