[ci] fix: Add more test cases in e2e_ppo_trainer_megatron_sglang_ascend.yml

[xiazhahe]

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.

Fixed some problems of e2e_ppo_trainer_megatron_sglang.yml on Ascend and added more CI cases for maintenance.

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, 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.

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 removes the configuration enabling flash attention for the reference model on NPU in the PPO trainer Megatron end-to-end test. The reviewer notes that this removal could lead to severe performance degradation or Out-Of-Memory (OOM) errors, and suggests keeping the configuration by correcting the double plus (++) prefix to a single plus (+) prefix to avoid Hydra parsing issues.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[gemini-code-assist]

Removing use_flash_attn=True for the reference model (ref) on NPU can lead to severe performance degradation or Out-Of-Memory (OOM) errors during PPO training, as the reference model will run without flash attention. If this was removed due to a Hydra parsing error caused by the double plus (++), please consider keeping it with a single plus (+) to match the actor's configuration style.

Suggested change

	++actor_rollout_ref.ref.megatron.override_transformer_config.use_flash_attn=True \
	+actor_rollout_ref.ref.megatron.override_transformer_config.use_flash_attn=True \

References

1. Use + instead of ++ as the prefix for overriding configuration values in Hydra.