[vllm] fix: verl + vllm-ascend(version 0.9.1) running failed issue (verl-project#3345)

### What does this PR do?

After
[pr#3285](verl-project@19020f6),
[issue 2564](verl-project#2564) began to
reappear. Following the modification of
[pr#2782](verl-project#2782), [issue
2564](verl-project#2564) was solved.

### Checklist Before Starting

- [x] Search for similar PRs. Paste at least one query link here:
[pr#2782](verl-project#2782)
- [x] 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.

### API and Usage Example

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

```python
# 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.

- [x] Read the [Contribute
Guide](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md).
- [x] Apply [pre-commit
checks](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md#code-linting-and-formatting):
`pre-commit install && pre-commit run --all-files --show-diff-on-failure
--color=always`
- [ ] Add / Update [the
documentation](https://github.com/volcengine/verl/tree/main/docs).
- [ ] Add unit or end-to-end test(s) to [the CI
workflow](https://github.com/volcengine/verl/tree/main/.github/workflows)
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](https://verl-project.slack.com/archives/C091TCESWB1) in [the
`verl` Slack
workspace](https://join.slack.com/t/verl-project/shared_invite/zt-3855yhg8g-CTkqXu~hKojPCmo7k_yXTQ).
(If not accessible, please try [the Feishu group
(飞书群)](https://applink.larkoffice.com/client/chat/chatter/add_by_link?link_token=772jd4f1-cd91-441e-a820-498c6614126a).)

Author: baymax591

verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.py

@@ -61,7 +61,6 @@
 from verl.utils.ray_utils import ray_noset_visible_devices
 from verl.utils.torch_functional import get_response_mask, pad_2d_list_to_length
 from verl.utils.vllm import TensorLoRARequest, VLLMHijack, is_version_ge
-from verl.utils.vllm.patch import patch_vllm_moe_model_weight_loader
 from verl.workers.config import HFModelConfig, RolloutConfig
 from verl.workers.rollout.base import BaseRollout
 
@@ -432,6 +431,8 @@ async def update_weights(self, weights: Generator[tuple[str, torch.Tensor], None
             self.inference_engine.llm_engine.add_lora(lora_reqest)
             logger.info(f"vLLM load weights, loaded_params: {len(weights)}")
         else:
+            from verl.utils.vllm.patch import patch_vllm_moe_model_weight_loader
+
             model = self.inference_engine.llm_engine.model_executor.driver_worker.worker.model_runner.model
             patch_vllm_moe_model_weight_loader(model)
             model.load_weights(weights)
@@ -550,6 +551,8 @@ async def update_weights(self, weights: Generator[tuple[str, torch.Tensor], None
         Args:
             weights: A generator that yields the name of the weight tensor and the tensor itself.
         """
+        from verl.utils.vllm.patch import patch_vllm_moe_model_weight_loader
+
         model = self.inference_engine.worker.model_runner.model
         patch_vllm_moe_model_weight_loader(model)
         model.load_weights(weights)