Running the SYM384 model and I am running out of VRAM at batch size of 4 with a 3080Ti.
I am wondering if adding a second GPU only to be used to drive my display might free up some VRAM on the 3080Ti?
Anyone know if this is worth exploring?
Running the SYM384 model and I am running out of VRAM at batch size of 4 with a 3080Ti.
I am wondering if adding a second GPU only to be used to drive my display might free up some VRAM on the 3080Ti?
Anyone know if this is worth exploring?
Possibly, but Windows always seems to reserve some VRAM regardless. You shouldn't be running out of RAM though as that model was developed on a 2080Ti (under Linux) with 11GB of VRAM,
My word is final
I can run that model with batch size of 3 without issue. If I go to 4 it will run for a while then any stress at all on VRAM creates an OOM. This is on a Win 10 Pro box with 3080Ti and 80 gigs RAM and very little else running. Again... SYM384 Phaze_A with what I believe are default model settings but a few tweaks in the global loss settings, including training with a mask and penalized mask loss. Not using mixed precision. Maybe I will turn that back on and reduce my snapshot interval...