[Feat]Make full graph mode compalible with MTP (#3276)

### What this PR does / why we need it?
Make the Full Graph mode can run with MTP.

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

Signed-off-by: anon189Ty <Stari_Falcon@outlook.com>

vllm_ascend/worker/worker_v1.py

@@ -361,9 +361,10 @@ class NPUWorker(WorkerBase):
 
     def execute_dummy_batch(self) -> None:
         force_attention = self.compilation_config.cudagraph_mode == CUDAGraphMode.FULL_DECODE_ONLY
-        self.model_runner._dummy_run(num_tokens=1,
-                                     uniform_decode=True,
-                                     force_attention=force_attention)
+        self.model_runner._dummy_run(
+            num_tokens=self.model_runner.decode_token_per_req,
+            uniform_decode=True,
+            force_attention=force_attention)
 
     def _init_worker_distributed_environment(self) -> None:
         """Initialize the distributed environment."""