[WIP][[V1][Metrics] Implement max_num_generation_tokens metrics

[markmc]

(WIP until #13774 merges)

Part of #10582

This metric tracks the maximum of num_generation_tokens across a set of identical requests under a parallel sampling parent.

It is the last remaining metric used by the example Grafana dashboard that makes sense in V1.

Add some additional tracking of child requests to ParentRequest in order to facilitate this.

[github-actions[bot]]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[mergify[bot]]

This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @markmc.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

[robertgshaw2-redhat]

LGTM - I think we should deprecate max_num_generation_tokens