[Feat] shared expert dp for deepseek_mtp (#3811)

### What this PR does / why we need it?
Support shared expert DP for deepseek_mtp feature. 
`shared_expert_dp` requires `SP==True`, with corresponding parameter
restrictions.
Previously, due to the coupling between `shared_expert_dp` and torchair,
and the removal of `deepseek_mtp` in vllm_ascend, shared expert dp of
deepseek_mtp was temporarily removed.
Currently, by performing the `reduce_scatter` on the input of
deepssek_mtp in `mtp_proposer.py`, we ensure that it matches the
dimensions of `input_embedding`, and then perform the `all_gather` on
the output of mtp.

### How was this patch tested?
baseline:
<img width="1184" height="692" alt="image"
src="https://github.com/user-attachments/assets/9680d53a-7b1d-481a-accc-b8f3dae2b9e3"
/>

enable shared_expert_dp and multistream_overlap_shared_expert:
<img width="1167" height="687" alt="image"
src="https://github.com/user-attachments/assets/2531d06b-dfda-4e24-8628-6f4b0f677ddc"
/>

TPOT: 48ms -> 45.4ms
Average TPS per rank: 117.6 -> 126.1


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

---------

Signed-off-by: chenmenglong <chenmenglong1@huawei.com>
Signed-off-by: zengran <zengran2@huawei.com>
Co-authored-by: zengran <zengran2@huawei.com>

vllm_ascend/ops/layernorm.py

@@ -110,6 +110,7 @@ class AscendRMSNorm(RMSNorm):
         import torch_npu
 
         if residual is not None:
+            residual = torch.ops.vllm.maybe_chunk_residual(x, residual)
             assert x.size(0) == residual.size(0)
             x, residual = _addrmsnorm_forward_oot(
                 self, x, residual, self.next_need_quant_fusion_linear,