Yulin
Yulin
The flash-attn I installed is version 1.0.2, no problem. 
@1999kevin Can you tell me how to use a gpu to generate images using a pretrained model without the communication protocol nccl. Thank you
@1999kevin but in image_samping.py ，I don't find mpiexec.thanks
Can I have a look at the code after your changes, thanks, I would appreciate it if you could send it over
> > Btw, I found training with only 4 batchsize and 64 image size costs about 18G memory per GPU. Is there something wrong with it? > > I also...
@thorinf I know it but it need nccl,even it doesn't have mpiexec.Thank you.
mpiexec -n 8 python cm_train.py --training_mode consistency_distillation --sigma_max 80 --sigma_min 0.002 --target_ema_mode fixed --start_ema 0.95 --scale_mode fixed --start_scales 40 --total_training_steps 600000 --loss_norm lpips --lr_anneal_steps 0 --teacher_model_path /path/to/edm_bedroom256_ema.pt --attention_resolutions 32,16,8 --class_cond...
yes
so I change the code but it has a bug
@thorinf I changed it but also need nccl   