feat: fix the vLLM DP path

[guyueh1]

What does this PR do ?

Previously nemo-rl doesn't work for vllm's native DP (EP>TP), this PR wants to support this case.

The following basic tests have passed, now trying the nightly test

# eval test
uv run examples/run_eval.py \
generation.model_name=Qwen/Qwen3-30B-A3B \
cluster.num_nodes=2 \
cluster.gpus_per_node=4 \
generation.vllm_cfg.tensor_parallel_size=4 \
generation.vllm_cfg.expert_parallel_size=8 \
generation.vllm_cfg.async_engine=true \

# grpo test
uv run examples/run_grpo.py \
--config examples/configs/grpo_math_1B_megatron.yaml \
policy.model_name=Qwen/Qwen3-30B-A3B \
cluster.num_nodes=4 \
cluster.gpus_per_node=4 \
policy.generation.colocated.enabled=false \
policy.generation.colocated.resources.num_nodes=2 \
policy.generation.colocated.resources.gpus_per_node=4 \
policy.generation.vllm_cfg.tensor_parallel_size=4 \
policy.generation.vllm_cfg.expert_parallel_size=8 \
policy.generation.vllm_cfg.async_engine=true \
policy.megatron_cfg.expert_model_parallel_size=8 \
policy.sequence_packing.enabled=false \

New nightly test figures:
H100 with EP=8 async engine

https://wandb.ai/nvidia/nemo-rl/runs/4mcplb63

H100 with TP=2 EP=16 sync engine

https://wandb.ai/nvidia/nemo-rl/runs/b3mon8zg

Issues

List issues that this PR closes (syntax):

Usage

• You can potentially add a usage example below

# Add a code snippet demonstrating how to use this

Before your PR is "Ready for review"

Pre checks:

• Make sure you read and followed Contributor guidelines
• Did you write any new necessary tests?
• Did you run the unit tests and functional tests locally? Visit our Testing Guide for how to run tests
• Did you add or update any necessary documentation? Visit our Document Development Guide for how to write, build and test the docs.

Additional Information

• ...

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[guyueh1]

/ok to test efc6fc2

[guyueh1]

/ok to test 9f381f2

[guyueh1]

fast CI is failing for uuidgen: command not found, trying the full set to see if it helps

[guyueh1]

Ran a test on llama3-8B with vLLM TP=1 & PP=1 to study the impact of changing distributed_executor_backend from None to mp , there is no observable performance difference.

[guyueh1]

/ok to test d03ceee

[yuki-97]

@terrykong could you help to take a review as well?

[guyueh1]

/ok to test 2272d47

[guyueh1]

/ok to test 0ea633c

[guyueh1]

@terrykong could you help to take a review as well?

@terrykong please review

[guyueh1]

/ok to test 05db6ab

[terrykong]

Thanks @guyueh1 . I think there is some patching for fp8 (fp8.py) that patches the raydistributedexecutor. Does this mean that functionality is broken by this PR unless we fix? Or does mp backend natively solve this?