[Good First Issue]: Support aten::quantile

[mvafin]

Context

OpenVINO component responsible for support of PyTorch models is called as PyTorch Frontend (PT FE). PT FE converts a model represented as TorchScript model to a model in OpenVINO opset.

What needs to be done?

• Implement conversion rule and/or transformation to support the new operation.
• Implement operation tests in tests/layer_tests/pytorch_tests. Please consider different data types, but keep reasonable number of test cases

Example Pull Requests

#18998

Resources

• torch.quantile description
• Contribution guide - start here!
• What is OpenVINO?
• OpenVINO PyTorch Frontend
• Blog post on contributing to OpenVINO
• User documentation

Contact points

@openvinotoolkit/openvino-pytorch-frontend-maintainers

Ticket

TBD

[gatbontonp]

.take

[github-actions]

Thank you for looking into this issue! Please let us know if you have any questions or require any help.

[pawarmanasi07]

Hi @gatbontonp! I noticed you're working on this issue. Would you be open to collaboration? I'd be happy to help with implementation or testing. If you've already started, I could focus on specific parts of the task, like writing tests or documentation.

[geeky33]

hello @mvafin can you please look upto the PR made
@andrei-kochin I took the permission for creating the PR.

[gatbontonp]

Hi @geeky33, I think you're missing the other interpolation methods and q can be a float or a tensor. I'm pretty close to finishing up and submitting a PR. Not sure if we want to wait for mine and just use @geeky33 's

[geeky33]

Hi @gatbontonp thank you for your feedback and for pointing out the additional considerations! I really appreciate the work you've done so far, and I didn't mean to overlap or rush things—I just got excited about the issue and wanted to contribute.

I’ve already put in significant effort into my PR, and it’s ready for review. I believe it addresses the issue comprehensively, including the interpolation methods and handling cases where q is a float or tensor. I’d love for you to take a look and share your thoughts on it. If there are any improvements or adjustments needed, I’m happy to incorporate them.

Since my PR is already complete, I think it would be efficient to move forward with it to avoid duplication of effort. However, if there are specific aspects of your work that you feel should be included, I’m open to collaborating and integrating them into my PR.
Although before making any such PR, I have always ensured to ask the maintainers of the repository for the permissions and once I get the approval from them, hence I did it :)