alibaba / GraphTranslator

GraphTranslator:Aligning Graph Model to Large Language Model for Open-ended Tasks
BSD 3-Clause "New" or "Revised" License
68 stars 12 forks source link

CUDA out of memory. #6

Closed chen971103 closed 4 months ago

chen971103 commented 4 months ago

Hello, I have 8 RTX2080 graphics cards, can I reproduce this experiment? I changed device = torch.device('cuda') in the producer.py file, but it still runs with only one 2080 graphics card by default. Where else do I need to change to make all 8 2080s work?