[Bugfix] Fixed an accuracy problem of sp with eagle3 (#5816)

### What this PR does / why we need it?
Fixed an accuracy problem when using eagle3 with sp.

The problem is described in
https://github.com/vllm-project/vllm-ascend/issues/5825.

It also adds a much more precise way to determine whether drafter should
use `sp` or not.

Also, it changes the `eager` of drafter to be a real `eager` in frontend
to avoid a `fx-graph` problem.

### Does this PR introduce _any_ user-facing change?

N/A

### How was this patch tested?

For simpilicity, we test it as in
https://github.com/vllm-project/vllm-ascend/issues/5825.

And we get the same result of `eagle3` with `sp` disabled.

```text
--------------------------------------------------
total_num_output_tokens: 1000
num_drafts: 437
num_draft_tokens: 1311
num_accepted_tokens: 564
mean acceptance length: 2.29
--------------------------------------------------
acceptance at token 0: 0.62
acceptance at token 1: 0.40
acceptance at token 2: 0.27
acceptance at token 3: 0.00
acceptance at token 4: 0.00
acceptance at token 5: 0.00
```

* vLLM version: v0.13.0
* vLLM main:
2f4e6548ef

Signed-off-by: drslark <slarksblood@qq.com>

vllm_ascend/ascend_forward_context.py

@@ -14,7 +14,7 @@ import vllm_ascend.envs as envs_ascend
 from vllm_ascend.ascend_config import get_ascend_config
 from vllm_ascend.utils import (AscendDeviceType, enable_sp, flashcomm2_enable,
                                get_ascend_device_type, has_layer_idx,
-                               is_moe_model,
+                               is_drafter_moe_model, is_moe_model,
                                speculative_enable_dispatch_gmm_combine_decode)
 
 
@@ -73,7 +73,10 @@ def set_ascend_forward_context(
         # the performance benefits can be maximized. Conversely, if the concurrency is below the threshold,
         # the performance may degrade due to the switching of communication methods.
         mmrs_fusion = True
-        if is_moe_model(vllm_config):
+        # main model and drafter model may have different architecture
+        is_context_moe_model = is_drafter_moe_model(vllm_config) \
+            if is_draft_model else is_moe_model(vllm_config)
+        if is_context_moe_model:
             sp_enabled = enable_sp(vllm_config) and num_tokens is not None
             mmrs_fusion = False
         else: