Fix forward functions for transformers v4.46+ compatibility

[airlanggawicaksono]

• Add position_embeddings to all decoder layer calls in forward(), forward_early(), and forward_remainder() required since transformers v4.46+ (fixes Recent changes break code #22)
• Fix decoder layer output unpacking to work with DynamicCache in-place updates
  (layer_outputs[0] instead of 2-value tuple unpacking)
• Remove unused per-layer past_key_value extraction in forward_remainder (fixes A variable past_key_value is defined but not used correctly. #25)
• Remove deprecated padding_mask=None argument
• Remove deprecated padding_mask=None argument
• Add _compute_position_embeddings helper for shared rotary embedding computation

[meta-cla]

Hi @airlanggawicaksono!

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 cla@meta.com. Thanks!

[meta-cla]

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