Support multistream of shared experts in FusedMoE (vllm-project#997)

Contains on vllm-project#1111 for completeness.

<!--  Thanks for sending a pull request!

BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html

-->
Implement multi-stream parallelism for MoE layers with shared experts,
where computation of shared experts will be overlapped with expert token
dispatch and combine. Also, when multi-stream is enabled, weights of
shared experts will be force to replicate across all cards, regardless
of any tensor parallelism configurations, to avoid AllReduce operations.

With the expected overlaping being:
```
| shared gate_up | shared act |              | shared down |
|    dispatch    | routed gate_up, act, down |   combine   |
```

<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.

- Please clarify why the changes are needed. For instance, the use case
and bug description.

- Fixes #
-->

No.

<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->

Tested on 1x16 910 node, with tailored 2 layer DSKv2.
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->

---------

Signed-off-by: sdmyzlp <lrwei2@petalmail.com>

Author: sdmyzlp

vllm_ascend/ascend_config.py

@@ -37,6 +37,7 @@ def __init__(self, vllm_config):
             ascend_scheduler_config)
 
         self.expert_map_path = additional_config.get("expert_map_path", None)
+        self.dynamic_eplb = additional_config.get("dynamic_eplb", False)
         self.chunked_prefill_for_mla = additional_config.get(
             "chunked_prefill_for_mla", False)
         self.enable_weight_nz_layout = additional_config.get(

vllm_ascend/models/deepseek_v2.py

@@ -733,9 +733,12 @@ def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
         quant_config = vllm_config.quant_config
         self.config = config
         self.quant_config = quant_config
+        self.num_dense_layers = self.config.first_k_dense_replace
+        self.num_moe_layers = self.config.num_hidden_layers - self.num_dense_layers
         self.model = CustomDeepseekV2Model(vllm_config=vllm_config,
-                                           prefix=maybe_prefix(
+                                   prefix=maybe_prefix(
                                                prefix, "model"))
+
         if get_pp_group().is_last_rank:
             self.lm_head = ParallelLMHead(config.vocab_size,
                                           config.hidden_size,