Add multimodal benchmarking usage docs

[markurtz]

Summary

This PR adds documentation for benchmarking multimodal models (image, video, and audio) with GuideLLM using OpenAI-compatible endpoints, and links these guides into the broader docs navigation.

Details

• Added dedicated guides for image, video, and audio benchmarking, covering setup, data loading, request formatting, metrics, and example guidellm benchmark commands.
• Introduced a multimodal benchmarking index page that explains prerequisites and links to each modality-specific guide.
• Updated the main Guides index to surface the new multimodal benchmarking docs.

Test Plan

• Manual testing

---

• "I certify that all code in this PR is my own, except as noted below."

Use of AI

• Includes AI-assisted code completion
• Includes code generated by an AI application
• Includes AI-generated tests (NOTE: AI written tests should have a docstring that includes ## WRITTEN BY AI ##)

[Copilot]

Pull request overview

This PR adds documentation for benchmarking multimodal models (image, video, and audio) with GuideLLM using OpenAI-compatible endpoints, and links these guides into the broader docs navigation.

Changes:

• Added dedicated guides for image, video, and audio benchmarking, covering setup, data loading, request formatting, metrics, and example guidellm benchmark commands.
• Introduced a multimodal benchmarking index page that explains prerequisites and links to each modality-specific guide.
• Updated the main Guides index to surface the new multimodal benchmarking docs.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 5 comments.

Show a summary per file

File	Description
docs/guides/multimodal/image.md	New guide for benchmarking vision-language models with image inputs, including data-column mapping, request formatting, metrics, and VQA/captioning examples.
docs/guides/multimodal/video.md	New guide for benchmarking video-language models with video inputs, including data loading, video request formatting, metrics, and QA/captioning examples.
docs/guides/multimodal/audio.md	New guide for benchmarking audio models for ASR, translation, and audio chat, with detailed encoder options, metrics, and three example benchmark commands.
docs/guides/multimodal/index.md	New multimodal overview page describing prerequisites and linking to image, video, and audio benchmarking guides.
docs/guides/index.md	Adds a “Multimodal Benchmarking” card that links the main Guides index to the new multimodal documentation.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[sjmonson]

Overall just a few nits around explaining arguments. There is also a lot of redundancy around explaining column mapping, output files, etc that would possible be better to have dedicated docs for with backlinks, but we can address that in a future PR.