[BugFix] Fix dummy_run memory explosion in eager mode (#3132)

### What this PR does / why we need it?

It is a quick bugfix for the memory explosion issue that requires
further refactoring.
The dummy_run in eager mode may lead to OOM and the reason is that
`hidden_states` were not released in time.
The PR temporarily resolves the issue by manually clearing the cache,
and further refactoring will be conducted subsequently.

Before the modification, the dummy_run's memory showed an accumulation
issue.
<img width="1796" height="207" alt="image"
src="https://github.com/user-attachments/assets/05e2b04c-2f99-4085-9eda-c78b7d9a57b0"
/>

After modification, it can be observed that the memory is released
promptly.
And it was verified that the model responded normally after a single
data input.


- vLLM version: v0.10.2
- vLLM main:
vllm-project/vllm@b106890

---------

Signed-off-by: chenmenglong <chenmenglong1@huawei.com>

Author: dragondream-chen

vllm_ascend/ops/moe/fused_moe_prepare_and_finalize.py

@@ -183,6 +183,11 @@ def finalize(self, hidden_states: torch.Tensor,
                                 self.moe_config.tp_group.device_group)
                 hidden_states = torch.cat(self.split_hidden_states, dim=0)
 
+                # TODO: It is a quick bugfix for the memory explosion issue in eager mode.
+                # If the cache is not cleared after `self.split_hidden_states` is created,
+                # it can lead to the memory explosion in eager mode.
+                del self.split_hidden_states
+
             # Unpad if necessary
             if self.num_tokens < hidden_states.shape[0]:
                 hidden_states = hidden_states[:self.num_tokens]
@@ -267,6 +272,11 @@ def finalize(self, hidden_states: torch.Tensor,
                                 self.moe_config.tp_group.device_group)
                 hidden_states = torch.cat(self.split_hidden_states, dim=0)
 
+                # TODO: It is a quick bugfix for the memory explosion issue in eager mode.
+                # If the cache is not cleared after `self.split_hidden_states` is created,
+                # it can lead to the memory explosion in eager mode.
+                del self.split_hidden_states
+
             if self.num_tokens < hidden_states.shape[0]:
                 hidden_states = hidden_states[:self.num_tokens]