catsled

> https://github.com/comfyanonymous/ComfyUI/blob/ee2c5fa72d4fc1714576fac7ba64aa5d607303d0/main.py#L216 > > Could it work if I simply added more workers to the thread? (will try tomorrow) > > Would you accept a PR to have the amount...

我认为你可以在CPU上运行，而不是在GPU上运行，我运行的是medium模型，差不多占用了12GB的VRAM

openmm==8.0.0 and pdbfixer==1.9 is ok

> quanto does not use very fancy CUDA kernels, so I don't see any reason why it wouldn't work. Just give it a try and please report your feedback. ok,...

> It is strange that you get integer output. Did you take a look at the MNIST example ? If not, maybe compare with your script and see if something...

got stuck when calibration(i did't add it before )  

> How long does it take to run evaluate on the float model ? about 8s