docs: add sustainability benchmarking tutorial

[zinichakraborty]

Description

Adds a tutorial notebook demonstrating sustainability benchmarking with the EvaluationAgent: a stable-diffusion-v1-5 baseline is compared against deepcache and torch_compile on total_time, energy_consumed, co2_emissions, and clip_score, using a 10-sample subset of LAION256 on a T4. Includes side-by-side comparison figures and a takeaway on interpreting efficiency gains vs. quality cost (with a pointer to the CMMD tutorial for stricter quality evaluation). Also registers the notebook in docs/tutorials/index.rst.

Related Issue

Fixes #602

Type of Change

• Documentation update

Testing

• I added or updated tests covering my changes
• Existing tests pass locally (uv run pytest -m "cpu and not slow")

No library code is changed, so no unit tests were added. The notebook was executed end-to-end on a Colab T4 (pruna 0.3.4) with all cells completing; outputs are stripped per the convention in the existing tutorials. Comparison figures from the run are attached below for review. ruff check passes on the notebook with the repo config.

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of my code, especially for agent-assisted changes
• I updated the documentation where necessary

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB