[Fix] Refactor dummy attention metadata creation (#3497)

### What this PR does / why we need it?
The `force_attention` parameter is designed for flash infer kernel
warmup, we don't actually need it on Ascend device (at least for
now).And it tends to make things more complicated. So we replace the
`force_attention` parameter with `aclgraph_runtime_mode` in the
attention metadata creation logic.

This change makes the control flow more explicit by directly using the
graph runtime mode to determine how to build attention metadata, rather
than relying on an intermediate boolean flag. This simplification
removes redundant logic and clarifies the conditions for building
attention metadata for full decode graph mode.

### Does this PR introduce _any_ user-facing change?
None.

### How was this patch tested?
DP + `FULL_DECODE_ONLY` + online serving.

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

---------

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.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 CUDAGraphMode, VllmConfig
+from vllm.config import VllmConfig
 from vllm.distributed import (ensure_model_parallel_initialized,
                               init_distributed_environment)
 from vllm.distributed.kv_transfer import ensure_kv_transfer_initialized
@@ -360,11 +360,9 @@ class NPUWorker(WorkerBase):
         return self.model_runner.pin_lora(lora_id)
 
     def execute_dummy_batch(self) -> None:
-        force_attention = self.compilation_config.cudagraph_mode == CUDAGraphMode.FULL_DECODE_ONLY
         self.model_runner._dummy_run(
             num_tokens=self.model_runner.decode_token_per_req,
-            uniform_decode=True,
-            force_attention=force_attention)
+            uniform_decode=True)
 
     def _init_worker_distributed_environment(self) -> None:
         """Initialize the distributed environment."""