[Feature] implement basic framework for batch invariant (#5517)

### What this PR does / why we need it?
This PR implement the basic framework for batch invariant, please see
https://github.com/vllm-project/vllm-ascend/issues/5487.
### Does this PR introduce _any_ user-facing change?
we reuse the function `vllm_is_batch_invariant` in vllm to judge if
batch invariant is enabled.

- vLLM version: v0.13.0
- vLLM main:
45c1ca1ca1
---------
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Signed-off-by: Lord_of_Ironhill <suiweiyi@huawei.com>
Signed-off-by: zjchenn <zjchenn@gmail.com>
Signed-off-by: wangx700 <wangxin700@huawei.com>
Co-authored-by: Lord_of_Ironhill <suiweiyi@huawei.com>
Co-authored-by: zjchenn <zjchenn@gmail.com>
Co-authored-by: wangx700 <wangxin700@huawei.com>

vllm_ascend/worker/worker.py

@@ -50,6 +50,7 @@ from vllm.v1.worker.workspace import init_workspace_manager
 
 import vllm_ascend.envs as envs_ascend
 from vllm_ascend.ascend_config import get_ascend_config, init_ascend_config
+from vllm_ascend.batch_invariant import init_batch_invariance
 from vllm_ascend.cpu_binding import bind_cpus
 from vllm_ascend.device_allocator.camem import CaMemAllocator
 from vllm_ascend.distributed.parallel_state import init_ascend_model_parallel
@@ -453,6 +454,7 @@ class NPUWorker(WorkerBase):
 
     def _init_worker_distributed_environment(self) -> None:
         """Initialize the distributed environment."""
+        init_batch_invariance()
         init_distributed_environment(self.parallel_config.world_size,
                                      self.rank, self.distributed_init_method,
                                      self.local_rank, "hccl")