Fix assertions in slice_scatter decomposition

[kkimmk]

• fix: allow slice_scatter decomposition with SymInt parameters for the case when returning the source tensor

Description

Originally, the assertions only allowed int types for start, end, and step. However, end can be a SymInt when set to dim_size, which only causes issues latter with range(start, end, step). This PR allows returning src_tensor when the condition is met with a SymInt typed end.

[facebook-github-bot]

Hi @kkimmk!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at [email protected]. Thanks!

[facebook-github-bot]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!

[apbose]

Ok got it. Looks like it is for dynamic shape case.

As such yes, the decomposition at present is not meant for dynamic shaped input. This code modification covers a very specific dynamic use case. But this change should work and should not affect the rest of the cases. So LGTM. But we need to expand these to support dynamic cases.

[narendasan]

@apbose what is the AI here? Should we merge the PR and work on broader cases later or is the expectation that this PR would have these changes?

[apbose]

We can merge this and work on the broader cases later.