[main] [refactor] refactor fused_moe.py to enable token_dispatchers (#2570)

### What this PR does / why we need it?
Enable token_dispatcher to replace fused_experts_with_xxx in eager mode
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
e2e & ut


- vLLM version: v0.10.1.1
- vLLM main:
704432af3c

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Co-authored-by: sherie <963372609@qq.com>
Co-authored-by: weijinqian0 <12153182+weijinqian0@users.noreply.github.com>
Co-authored-by: shiyuan680 <72335504+shiyuan680@users.noreply.github.com>

vllm_ascend/ascend_forward_context.py

@@ -46,6 +46,18 @@ def _get_fused_moe_state(ep_size: int, with_prefill: bool,
         return FusedMoEState.MC2
 
 
+def get_dispatcher_name(ep_size: int, with_prefill: bool) -> str:
+    if ep_size == 1:
+        return "TokenDispatcherWithAllGather"
+
+    if ep_size < 16:
+        return "TokenDispatcherWithAll2AllV"
+
+    if with_prefill:
+        return "TokenDispatcherWithAll2AllV"
+    return "TokenDispatcherWithMC2"
+
+
 @contextmanager
 def set_ascend_forward_context(
         attn_metadata: Any,
@@ -87,6 +99,14 @@ def set_ascend_forward_context(
         forward_context.fused_moe_state = fused_moe_state
         forward_context.in_profile_run = in_profile_run
 
+        with_quant = vllm_config.quant_config is not None
+        forward_context.with_quant = with_quant
+        from vllm_ascend.ops.moe_dispatcher.token_dispatcher import \
+            get_token_dispatcher
+        dispatcher_name = get_dispatcher_name(ep_size, with_prefill)
+        dispatcher = get_token_dispatcher(dispatcher_name)
+        forward_context.token_dispatcher = dispatcher
+
         # NOTE: This cannot be set using set_forward_context
         # due to multiple warmups before actual capturing
         forward_context.capturing = False