[WIP] add rl support for veomni backend

[ji-huazhong]

What does this PR do?

Add concise overview of what this PR aims to achieve or accomplish. Reference related GitHub issues and PRs that help with the review.

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 fsdp, megatron, sglang, vllm, rollout, trainer, ci, training_utils, recipe, hardware, deployment, ray, worker, single_controller, misc, perf, model, algo, env, tool, ckpt, doc, data, cfg, reward
  • If this PR involves multiple modules, separate them with , like [megatron, fsdp, doc]
  • {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][fsdp, megatron] feat: dynamic batching

Test

For changes that can not be tested by CI (e.g., algorithm implementation, new model support), validate by experiment(s) and show results like training curve plots, evaluation results, etc.

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: ...
• Once your PR is ready for CI, send a message in the ci-request channel in the verl Slack workspace. (If not accessible, please try the Feishu group (飞书群).)
• If your PR is related to the recipe submodule, please also update the reference to the submodule commit via git submodule update --remote or cd recipe && git pull origin main.

[gemini-code-assist]

Code Review

This pull request adds support for the veomni backend for RL training. It introduces new configuration files for veomni actor, critic, reference policy, and reward models, along with a main PPO trainer configuration. The changes also update the worker selection logic to handle the veomni strategy.

My review has identified a few critical issues in the new configuration files that would lead to runtime errors. Specifically, a misconfigured legacy worker flag, a non-portable model path, and a placeholder value that needs to be replaced. There is also a minor redundancy in one of the configuration files. Addressing these points will improve the correctness and usability of the new veomni backend configuration.

[gemini-code-assist]

The use_legacy_worker_impl is set to auto, but the veomni backend requires the new worker implementation. With the auto setting, the application will raise a NotImplementedError for the actor worker or a ValueError for the critic worker. To ensure the veomni backend functions correctly, this value must be set to disable.

  use_legacy_worker_impl: disable

[gemini-code-assist]

The model path ~/models/FsfairX-LLaMA3-RM-v0.1 uses a tilde (~) to refer to the user's home directory. This is not portable and will cause errors in environments like Docker containers or when run by different users. Please use a placeholder or a more robust path resolution mechanism, such as an environment variable, to make the configuration more robust and reproducible.

  path: <path_to_FsfairX-LLaMA3-RM-v0.1_model>

[gemini-code-assist]

The rollout.name is set to ???, which is a placeholder and will cause a runtime error. Please replace it with a valid rollout engine name (e.g., vllm, sglang).

  name: <your_rollout_engine_name>

[gemini-code-assist]

The strategy: veomni key is defined inside the veomni block, but it's also defined at the top level of this configuration file (line 10). This redundancy can be confusing and lead to maintenance issues. Please remove this nested strategy key.