HF ZeroGPU Space Hangs, No Output in the logs

Hi All, I am trying to create a ZeroGPU space for my model. I am able to pull the docker image for the container and run it flawlessly on my local GPU, but when I try to perform inference on the HF space, it just hangs. More specifically, when I click on “the Run Inference” button in the space, a GPU allocates, and the spinner spins until the GPU allocation times out. I have tried increasing the duration of my inference function to > 120s without success, whereas locally it works within 20 seconds. Any help in debugging this would be greatly appreciated!