[DP][V1] Fix rank set in DP scenario & Bump torch-npu version to 2.5.1.post1.dev20250528 (#1235)

### What this PR does / why we need it?
1. Fix rank set in DP scenario. The new poc version of torch-npu support
setting `ASCEND_RT_VISIBLE_DEVICES` dynamically, thus we could use the
rank set in `DPEngineCoreProc` directly instead of calculating local
rank across dp by hand in the patched `_init_data_parallel`

Closes: https://github.com/vllm-project/vllm-ascend/issues/1170

2. Bump torch-npu version to 2.5.1.post1.dev20250528

Closes: https://github.com/vllm-project/vllm-ascend/pull/1242
Closes: https://github.com/vllm-project/vllm-ascend/issues/1232


### How was this patch tested?
CI passed with new added test.

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: Icey <1790571317@qq.com>
Co-authored-by: Icey <1790571317@qq.com>

vllm_ascend/worker/worker_v1.py

@@ -75,12 +75,6 @@ class NPUWorker(WorkerBase):
                          distributed_init_method=distributed_init_method,
                          is_driver_worker=is_driver_worker)
 
-        # NOTE(Yizhou): Since we do not set ASCEND_RT_VISIBLE_DEVICES in
-        # vllm_ascend, we need to set the device id manually.
-        local_dp_rank = self.vllm_config.parallel_config.data_parallel_rank_local
-        world_size = self.vllm_config.parallel_config.world_size
-        self.local_rank_across_dp = local_dp_rank * world_size + self.local_rank
-
         # Try to import mindie_turbo to accelerate vLLM inference.
         try_register_lib(
             "mindie_turbo",
@@ -124,7 +118,7 @@ class NPUWorker(WorkerBase):
 
     def init_device(self):
         if self.device_config.device.type == "npu":
-            self.device = torch.device(f"npu:{self.local_rank_across_dp}")
+            self.device = torch.device(f"npu:{self.local_rank}")
             NPUPlatform.set_device(self.device)
             NPUPlatform.empty_cache()
             self.init_npu_memory = NPUPlatform.mem_get_info()[0]