[veomni, cfg] feat: add missing config fields to veomni.yaml

[mikequan0425]

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.

Supplement the configurations available in engine.py but missing in engine/veomni.yaml, and add new optional operators in the veomni OpsImplementationConfig.

Checklist Before Starting

• Search for similar PRs. Paste at least one query link here: https://github.com/verl-project/verl/pulls?q=is%3Apr+is%3Aopen+veomni+config
• Format the PR title as [{modules}] {type}: {description} (This will be checked by the CI)
  • {modules} include fsdp, megatron, veomni, 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, fully_async, one_step_off
  • 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.

After completing the configuration in the script, the logs show that it has taken effect successfully.

API and Usage Example

Demonstrate how the API changes if any, and provide usage example(s) if possible.
Add new configuration items for the veomni training engine

actor_rollout_ref.actor.veomni.entropy_from_logits_with_chunking=True \
actor_rollout_ref.actor.veomni.offload_policy=False

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.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[gemini-code-assist]

Code Review

This pull request introduces several new configuration options to the VeOmni engine, specifically adding support for Qwen3.5-related kernel implementations (such as gated RMSNorm, causal conv1d, and chunk gated delta-rule). It also adds several new configuration parameters to veomni.yaml. The review feedback correctly identifies that several of these newly added configuration parameters (including grad_offload, offload_policy, wrap_policy, dtype, and use_orig_params) are currently ignored or unsupported by the underlying VeOmniEngine implementation, and recommends either removing them or implementing proper support.

[FoolPlayer]

Thanks for your PR, the only problem is some args only for FSDP1, but VeOmni has already remove FSDP1 support after v0.1.10. And VeOmni 0.1.11 will be used with verl 0.8.0

[mikequan0425]

@FoolPlayer Thank you for your review and your excellent work on Veomni. I have revised everything based on your suggestions.

[mikequan0425]

@FoolPlayer @wuxibin89 pre-commit failed in CI, I've pushed the updates again. Could you help trigger CI again? Thanks!