Prefix caching possible also for structured output. Readme update.

[viktorpusTT]

Purpose

As a followup to tenstorrent/tt-metal#35904, this PR:

• Adds support for random-prefix-len arg to structured outputs benchmark, to make this more param-compatible with vllm bench serve.
• Updates readme.

Test Plan

Test Result

https://github.com/tenstorrent/tt-metal/actions/runs/22580104243/job/65410407537

---

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan, such as providing test command.
• The test results, such as pasting the results comparison before and after, or e2e results
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
• (Optional) Release notes update. If your change is user facing, please update the release notes draft in the Google Doc.