Frank Odom

Thanks for this contribution! Just FYI -- I'll probably get to look over this in the next few days. Super busy lately haha 👍

@aminaab96 Sorry for the late response here. Do you think this is a bug with the `fft_conv_pytorch` package? @GuanghuiFU may be correct -- it could be the size of your...

@GuanghuiFU You're correct about keeping Tensors in the Fourier domain. When it's possible, that will help to reduce latency and memory footprints for your models. Unfortunately, I don't think it's...

I may not be the best person to ask. 😅 But I'll try to give an answer, based on my limited knowledge. Although that paper uses **complex** convolutions, it doesn't...

I'm running into the exact same problem. `torch.jit.script` works just fine, but `trtorch.compile` throws an exception. Here's a Dockerfile to reproduce the issue: ```dockerfile FROM pytorch/pytorch:1.8.1-cuda11.1-cudnn8-devel # Have to download...

@HIMANSHUSINGHYANIA Yep, that's what this PR is fixing. 👍

@mvoodarla I believe @Innary is right -- I had the same issue locally until I installed both `cargo` and `rustc`. ```bash sudo apt update && sudo apt install -y cargo...

Hey @leor-c! Wanted to let you know I see this, and will try to look at it soon. Sorry, I'm a bit swamped with other things this week. 😅

@draguve Thanks for this! I'm not seeing a significant change in training convergence. Here are some brief training logs on the Project Gutenberg example: - red -> `main` with `bias=False`...