[Quantization] Add support for Comfy-Kitchen / Comfy-Quants

[PrakshaaleJain]

What does this PR do?

This PR adds support for the Comfy Quant quantization toolkit by integrating its inference engine, Comfy-Kitchen, directly into Diffusers library.

Key additions:

• Added ComfyQuantConfig and ComfyQuantizer to handle wrapping of tensors.
• Safely intercepts weights via create_quantized_param and wraps them via QuantizedTensor.from_float to dispatch to Comfy-Kitchen's optimized GPU kernels.
• Implemented robust format validation and auto-resolution of standard layout classes (fp8, int8, mxfp8, nvfp4, int4_svd, int4_awq).
• Added full unit test coverage under tests/quantization/comfy_quant/.

Fixes #14705

Before submitting

• Did you use an AI agent (Claude Code, Codex, Cursor, etc.) to help with this PR? If so:
  • Did you read the Coding with AI agents guide?
  • Did you run the self-review skill on the diff?
  • Did you share the final self-review notes in the PR description or a comment?
• Did you read the contributor guideline?
• Did you read our philosophy doc? (important for complex PRs)
• Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?
• Are you the author (or part of the team) of the model/pipeline (only applicable for model/pipeline related PRs)?

AI Agent Self-Review Notes

Agent: Antigravity (Google DeepMind)
Review Focus: Diffusers Quantization Standards & Guidelines

1. Backwards Compatibility:
   • Status: Passed. The ComfyQuantizer relies on is_comfy_kitchen_available(). If the backend is not installed, Diffusers will safely fall back to standard behavior or fail gracefully if ComfyQuantConfig is passed explicitly without the toolkit.
2. Coding Style & Formatting:
   • Status: Passed. The code was fully run through make style && make fix-copies. utils/check_dummies.py successfully generated dummy_comfy_kitchen_objects.py and correctly registered the imports in `diffusers/__init
3. Testing:
   • Status: Passed. Added tests/quantization/comfy_quant/test_comfy_quant.py. Tests cover both valid format wrapping (FP8 mapping to TensorCoreFP8Layout) and error handling for unsupported formats. Tests ran locally and passed with 100% success.