Add examples on how to profile a pipeline

[sayakpaul]

What does this PR do?

TL;DR: Adds a guide on how to profile a pipeline and fix issues like CPU overhead, CPU<->GPU syncs, etc.

Motivation

Since we provide first-class torch.compile support, it's important that our pipelines are set up for optimal success with it. This includes spotting any obvious issues that plague the torch.compile performance -- CPU overhead, CPU<->GPU syncs, graphbreaks, kernel launch delays, etc.

The best way to spot these bugs is to profile a pipeline, as it gives a granular measurement of where the GPU is spending time and if it is doing so in an expected manner. We can then uncover any unexpected issues and eventually fix them.

Workflow

The README.md added in the PR has all the descriptions, but in summary:

• take a popular pipeline like Flux/Flux2/QwenImage/Wan/LTX2
• run the profile with 2 inference steps
• load the trace on Perfetto
• spot the potential suspects
• piggy that back to Claude along with the trace
  • ask it to attempt a fix
  • review the fix
  • compare the results

With this Workflow, I was able to fix some issues in the Flux2 Klein pipeline and the Wan pipeline. All changes look quite harmless to me.

Plan

Not only is it helpful to profile pipelines to get a ceiling on performance, but the community could also help us improve our pipelines should this workflow prove to be useful.

Note to reviewers

Please review the changes in src/diffusers/*. And you can skip straight to the "Afterwards" section in the README.md document.

The tutorial is currently available here. Some inline comments.

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.