Zmj/add qwen3.5 npu longcontext

[Mengyuyang]

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, 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 introduces a new launch script for running Qwen 3.5 35B GRPO training using Megatron and vLLM on Ascend NPUs. The feedback points out a critical configuration issue where the expert parallel size (EP) is set to 8 on a single-node 16-GPU setup. Because the calculated data parallel size (DP) is 1, having EP=8 violates Megatron-Core's constraint that EP must be less than or equal to DP, which will cause an assertion failure. It is recommended to set EP to 1.

[gemini-code-assist]

In this single-node 16-GPU configuration (trainer.nnodes=1, trainer.n_gpus_per_node=16), the data parallel size is DP = World_Size / (TP * PP * CP) = 16 / (2 * 2 * 4) = 1. Since Megatron-Core requires the expert model parallel size (EP) to be less than or equal to the data parallel size (DP), setting EP=8 will cause an assertion failure during model parallel initialization. For a single-node run, EP must be set to 1.

Suggested change

	EP=${EP:-8}
	EP=${EP:-1}

[tardis-key]

Refer to other scripts for naming conventions