[Aclgraph][DP] Fix dp dummy run not in aclgraph error (#3208)

### What this PR does / why we need it?
When running DP in a non-equilibrium scenario, which means there is some
dp groups executing `dummy_run`, we need to make sure it running the
same mode as other dp, thus improving then performance in dp scenario

### How was this patch tested?
Tested by adding log in `_dummy_run`

- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/releases/v0.11.0

---------

Signed-off-by: MengqingCao <cmq0113@163.com>

vllm_ascend/worker/worker_v1.py

@@ -26,7 +26,7 @@ import torch_npu
 import vllm.envs as envs_vllm
 from torch_npu.op_plugin.atb._atb_ops import _register_atb_extensions
 from torch_npu.profiler import dynamic_profile as dp
-from vllm.config import VllmConfig
+from vllm.config import CUDAGraphMode, VllmConfig
 from vllm.distributed import (ensure_model_parallel_initialized,
                               init_distributed_environment)
 from vllm.distributed.kv_transfer import ensure_kv_transfer_initialized
@@ -356,7 +356,10 @@ class NPUWorker(WorkerBase):
         return self.model_runner.pin_lora(lora_id)
 
     def execute_dummy_batch(self) -> None:
-        self.model_runner._dummy_run(1)
+        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)
 
     def _init_worker_distributed_environment(self) -> None:
         """Initialize the distributed environment."""