CUDA Out of Memory Error When Running sample.py with a large --num-samples

[JoshPhd]

I'm trying to generate a number of sequences with sample.py, so I set the --num-samples parameter to 100.

However, upon execution, I received the following error message:RuntimeError: CUDA out of memory. Tried to allocate 166.00 MiB (GPU 0; 9.77 GiB total capacity; 8.11 GiB already allocated; 149.81 MiB free; 8.15 GiB reserved in total by PyTorch). My GPU seems to run out of memory during the process.

Has anyone else experienced anything similar, or does anyone have a suggestion on how to get around this memory limitation? Thank you in advance for your time and help!

[jamesrgraham]

I got the same. I found I could run ~15 sequences at a time.

But I'm getting repeat sequences (100% ID to sequences from other runs) when I run multiple sets of 15 to get up to 100.

[JoshPhd]

I got the same. I found I could run ~15 sequences at a time.

But I'm getting repeat sequences (100% ID to sequences from other runs) when I run multiple sets of 15 to get up to 100.

Got it, Tks for your advice