feat: add compilation algorithms

[minettekaum]

Description

Added x fast and ipex llm to Pruna.

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested?

It has been tested in as the other algorithms.

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

[cursor]

Comment @cursor review or bugbot run to trigger another review on this PR

[johannaSommer]

Looks supergood already, just had two quick comments! 🌻😊

[github-actions]

This PR has been inactive for 10 days and is now marked as stale.

[ParagEkbote]

Unfortunately, it seems that the IPEX backend will be deprecated soon. While there is no specific indication about the IPEX LLM library being deprecated, perhaps there could be a re-consideration to add this backend? WDYT?

[minettekaum]

Hi @ParagEkbote,

Thanks so much for the feedback! 🙌

IPEX LLM was previously part of Pruna Pro, and we're excited to open-source it alongside many of the algorithms we’re bringing into the Pruna package.

Given Intel’s deprecation timeline (EOL March 2026) and their recommendation to use PyTorch directly, we're still evaluating whether this backend makes sense to maintain long-term in the open-source version. For now, we're including it so users can benefit from the functionality today, but we may phase it out in the future as Intel’s features continue to be upstreamed into PyTorch.