Revert "[Feat] Shared expert dp for deepseek and deepseek_mtp (#3495)" (#3586)

### What this PR does / why we need it?
This reverts commit
bf87606932.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
E2E vllm serving with `enable_shared_expert_dp: true` in eager mode as
before.


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

Signed-off-by: linfeng-yuan <1102311262@qq.com>

vllm_ascend/platform.py

@@ -284,7 +284,7 @@ class NPUPlatform(Platform):
         if parallel_config and parallel_config.worker_cls == "auto":
             # TODO: this is a tricky way to disable `use_sequence_parallel_moe` in vllm.
             os.environ["VLLM_ALL2ALL_BACKEND"] = "flashinfer_all2allv"
-            if ascend_config.torchair_graph_config.enabled:
+            if ascend_config.torchair_graph_config.enabled or ascend_config.enable_shared_expert_dp:
                 parallel_config.worker_cls = "vllm_ascend.torchair.torchair_worker.NPUTorchairWorker"
             else:
                 parallel_config.worker_cls = "vllm_ascend.worker.worker_v1.NPUWorker"
@@ -337,6 +337,8 @@ class NPUPlatform(Platform):
         ascend_config = get_ascend_config()
 
         if use_mla and ascend_config.enable_shared_expert_dp:
+            if use_mla and not use_sparse:
+                return "vllm_ascend.torchair.torchair_mla.AscendMLATorchairBackend"
             if use_mla and use_sparse:
                 return "vllm_ascend.torchair.torchair_sfa.AscendSFATorchairBackend"