[monitor-config] feat: rl-insight supprot verl-omni dashboard

[mengchengTang]

What does this PR do?

rl-insight supprot verl-omni dashboard

Checklist Before Starting

• Search for similar PRs. Paste at least one query link here: ...
• Format the PR title as [{modules}] {type}: {description} (This will be checked by the CI)
  • {modules} include:
    • monitor-api, monitor-cli, monitor-collector, monitor-server, monitor-config for online monitor changes
    • recipe for offline analysis changes, including pipeline, parser, visualizer, data checker, recipe config, examples, and sample data
    • doc, ci, perf, deployment, misc for cross-cutting changes
  • If this PR involves multiple modules, separate them with , like [recipe, ci] or [monitor-server, monitor-config]
  • {type} is in feat, fix, refactor, chore, test
  • If this PR breaks any API (CLI arguments, config, function signature, etc.), add [BREAKING] to the beginning of the title.
  • Example: [BREAKING][mstx, torch_profile] feat: support timeline parsing

Test

verl-omni.demo.mp4

API and Usage Example

Demonstrate how the API changes if any, and provide usage example(s) if possible.

# Add code snippet or script demonstrating how to use this

Design & Code Changes

Demonstrate the high-level design if this PR is complex, and list the specific changes.

Checklist Before Submitting

Important

Please check all the following items before requesting a review, otherwise the reviewer might deprioritize this PR for review.

• Read the Contribute Guide.
• Apply pre-commit checks: pre-commit install && pre-commit run --all-files --show-diff-on-failure --color=always
• Add / Update the documentation.
• Add unit or end-to-end test(s) to the CI workflow to cover all the code. If not feasible, explain why: ...

[tardis-key]

As an extension of verl, what does the new dashboard provide that the original dashboard could not?

Additionally, as a further topic, how can we ensure the maintainability of the duplicated content?

[mengchengTang]

As an extension of verl, what does the new dashboard provide that the original dashboard could not?

Additionally, as a further topic, how can we ensure the maintainability of the duplicated content?

1. Although both dashboards are based on Trainer v1, the trainer metrics and vLLM-Omni metrics are different, so the new dashboard provides monitoring tailored to the vLLM-Omni integration.
2. In the long term, metrics exposed by RL frameworks may change. We should clearly document the supported frameworks and their compatible versions to make the corresponding dashboard versions explicit.

[mengchengTang]

@tardis-key