OpenGVLab/OmniQuant

CUDA extension not installed

Arthur-Ling opened this issue · 2 comments

When I try to run scripts, "CUDA EXTENSION NOT INSTALLED" happens, and the running time is too long.
What should I do?

And when i run:
"
CUDA_VISIBLE_DEVICES=6 python main.py
--model facebook/opt-6.7b --eval_ppl
--epochs 0 --output_dir ./log/opt-6.7b-w4a4
--wbits 4 --abits 4 --lwc --let --alpha 0.75
--net opt-6.7b
--resume /home/Project/OmniQuant/pre_train/opt-6.7b-w4a4.pth
"

AttributeError: 'QuantOPTDecoderLayer' object has no attribute 'input_layernorm'

What should I do?

I have fixed the bug about opt models, please try again.