[refactor] Refactoring AscendFusedMoE (#1229)

<!--  Thanks for sending a pull request!

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

-->
### What this PR does / why we need it?
This PR is used for resolved [issue
1147](https://github.com/vllm-project/vllm-ascend/issues/1147)
1. Move fused_moe code into one file `fused_moe.py`.
2. Integrate branch conditions into function `get_fused_moe_state`.
<!--
- 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 #
-->

### Does this PR introduce _any_ user-facing change?
1. This PR has removed the env `VLLM_ENABLE_MC2`, because I think this
env is useless, we can make judgments based on the current scenario
without this env, it will only increase complexity.
2. This PR has removed the env `USING_LCCL_COM`, because this env has
already expired.
3. `additional_config.expert_tensor_parallel_size` has already expired,
and now we also use parameter `enable_expert_parallel`, consistent with
the vLLM.
<!--
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.
-->

### How was this patch tested?
<!--
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: zzzzwwjj <1183291235@qq.com>

vllm_ascend/envs.py

@@ -50,18 +50,10 @@ env_variables: Dict[str, Callable[[], Any]] = {
     # value is None, which means the system default C compiler will be used.
     "C_COMPILER":
     lambda: os.getenv("C_COMPILER", None),
-    # Whether to enable MC2 for DeepSeek. If not set, the default value is False.
-    # MC2 is a fusion operator provided by Ascend to speed up computing and communication.
-    # Find more detail here: https://www.hiascend.com/document/detail/zh/canncommercial/81RC1/developmentguide/opdevg/ascendcbestP/atlas_ascendc_best_practices_10_0043.html
-    "VLLM_ENABLE_MC2":
-    lambda: bool(int(os.getenv("VLLM_ENABLE_MC2", '0'))),
     # Whether to enable the topk optimization. It's disabled by default for experimental support
     # We'll make it enabled by default in the future.
     "VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE":
     lambda: bool(int(os.getenv("VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE", '0'))),
-    # Whether to use LCCL communication. If not set, the default value is False.
-    "USING_LCCL_COM":
-    lambda: bool(int(os.getenv("USING_LCCL_COM", '0'))),
     # The version of the Ascend chip. If not set, the default value is
     # ASCEND910B1. It's used for package building. Please make sure that the
     # version is correct.