[main][bugfix] Fix spec acceptance rate problem in vllm_0.15.0 (#6606)

### What this PR does / why we need it?
The speculative inference acceptance rate decreases after the vllm
version is upgraded to v0.15.0. This issue is resolved.

### Does this PR introduce _any_ user-facing change?
no

### How was this patch tested?
UT and tests case

- vLLM version: v0.15.0
- vLLM main:
d7e17aaacd

---------

Signed-off-by: lilinsiman <lilinsiman@gmail.com>

vllm_ascend/ascend_forward_context.py

@@ -19,6 +19,7 @@ from vllm_ascend.utils import (
     is_drafter_moe_model,
     is_moe_model,
     speculative_enable_dispatch_gmm_combine_decode,
+    vllm_version_is,
 )
 
 
@@ -152,6 +153,9 @@ def set_ascend_forward_context(
                 mc2_mask[num_actual_tokens:] = False
                 forward_context.mc2_mask = mc2_mask
 
+        if is_draft_model and vllm_version_is("0.15.0"):
+            forward_context.remaining_moe_layers = None
+
         try:
             yield
         finally:

vllm_ascend/spec_decode/eagle_proposer.py

@@ -553,17 +553,6 @@ class EagleProposer(VllmEagleProposer):
 
         model_hidden_states, model_positions = self.maybe_pad_and_reduce(model_hidden_states, model_positions)
 
-        # Expend the remaining moe layers for suiting vllm.
-        forward_context = get_forward_context()
-        if forward_context and hasattr(forward_context, "remaining_moe_layers"):
-            if self.num_speculative_tokens > 1:
-                moe_layers_needed = len(forward_context.remaining_moe_layers) * self.num_speculative_tokens
-                if len(forward_context.remaining_moe_layers) < moe_layers_needed:
-                    original_layers = list(forward_context.remaining_moe_layers)
-                    repeat_count = (moe_layers_needed + len(original_layers) - 1) // len(original_layers)
-                    expanded_layers = original_layers * repeat_count
-                    forward_context.remaining_moe_layers = expanded_layers
-
         ret_hidden_states = self.model(
             input_ids=model_input_ids,
             positions=model_positions,