[recipe] feat: support qwen2.5-32B DAPO training script on ASCEND NPU

[ZLiao097]

What does this PR do?

Provide an script for DAPO-training qwen2.5-32B on NPU, and update experiment result.

Checklist Before Starting

• Search for similar PRs. Paste at least one query link here: [recipe] feat: support qwen3-8B/14B DAPO training on ASCEND NPU
• 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
  • 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.

The following are some comparison charts of relevant data from script testing, where red represents NPU and blue represents GPU.

Critic/rewards/mean Comparison Chart

Response_length/mean Comparison Chart

Val-core/math_dapo/acc/mean@32 Comparison Chart (Test by aime-2024)

API and Usage Example

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

cd /path/to/verl
bash recipe/dapo/run_dapo_qwen2.5_32b_npu.sh

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).)

[gemini-code-assist]

Code Review

This pull request introduces a DAPO training script for the Qwen2.5-32B model on Ascend NPUs and updates the documentation accordingly. The changes look good, but I've found a critical shell syntax issue in the new script that will prevent it from running. Please see my comment for the fix.

[FightingZhen]

@ZLiao097 There is a issue #3248 related with this PR, can you have a check?