I followed all instructions which this project provide, and I get this error:
ValueError: torch.cuda.is_available() should be True but is False. xformers' memory efficient attention is only available for GPU
After that I removed --enable_xformers_memory_efficient_attention argument from my command, the error changed like this:
...src/inference.py", line 226, in main
generator = torch.Generator("cuda").manual_seed(args.seed)
^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Device type CUDA is not supported for torch.Generator() api.
I've searched that error and then I've found pytorch mps document. I changed the src/inference.py:226 code to:
So maybe I've been trying something wrong, because it didn't work too. I was going to try without GPU but i didn't do it. Is there a way to close cuda/GPU?
Thank you
My environment:
Macbook Pro 14-inch, 2021
chip: Apple M1 Pro
os: 13.6 (22G120)
python: 3.11
I followed all instructions which this project provide, and I get this error:
After that I removed
--enable_xformers_memory_efficient_attentionargument from my command, the error changed like this:I've searched that error and then I've found pytorch mps document. I changed the src/inference.py:226 code to:
So maybe I've been trying something wrong, because it didn't work too. I was going to try without GPU but i didn't do it. Is there a way to close cuda/GPU?
Thank you
My environment: Macbook Pro 14-inch, 2021 chip: Apple M1 Pro os: 13.6 (22G120) python: 3.11