Dilshod Tadjibaev

I have started working on this issue and I have a good design solution that's flexible and robust.

@Arjun31415, @AntBlo, @agelas, @hexd0t, @will-maclean, @mosure, @JachymPutta, @johnhuichen, @mepatrick73, @cBournhonesque, @Dirleye, @laggui Thank you very much for answering Burns' call for help. Your contributions have greatly enhanced ONNX Op coverage!...

Your PR changes are part of Burn 0.14: https://github.com/tracel-ai/burn/releases/tag/v0.14.0

@Luni-4 > @antimora > > Can we add the `Split` operator to the list too? Looking at [this list](https://github.com/tracel-ai/burn/blob/main/crates/burn-import/SUPPORTED-ONNX-OPS.md), it's not present in `burn` as well though 🤔 This ticket...

I'll be on a two week break. I'll finish off after May 28th. Any feedback is welcome.

Progress output of Whisper model: ``` Whisper { encoder: Encoder { conv1: Conv1d {stride: 1, kernel_size: 3, dilation: 1, groups: 1, padding: Explicit(1)} conv2: Conv1d {stride: 2, kernel_size: 3, dilation:...

CC @laggui

I have file a ticket to support 0D tensors: https://github.com/tracel-ai/burn/issues/1689

Blocked by https://github.com/tracel-ai/burn/issues/1689

The upstream issue in PyTorch seems to be fixed (https://github.com/pytorch/pytorch/issues/124009).